arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.02081cs.PF
收藏

并行工件零渐近延迟的实现

Achieving Zero Asymptotic Queueing Delay for Parallel Jobs

Wentao Weng, Weina Wang

摘要:

在大规模计算系统中,零延迟是非常理想的。现有的工作已经表明,它可以渐近地实现通过使用著名的电源的$d$选择(pod)的政策与探测开销$d = ω\left(\frac{\log N}{1-λ}\right)$,这是不可能的,当$d = O\left(\frac{1}{1-λ}\right)$,其中$N$是服务器的数量和$λ$是系统的负载。然而,这些结果是基于模型,其中每个作业是一个不可分割的单元,这并没有捕捉到在今天的主流并行计算范式的并行结构的作业。因此,本文考虑了一个模型,其中每个作业由一批并行任务。在此模型下,我们提出了一个新的零(渐近)延迟的概念,要求在一个策略下的作业延迟接近其任务的服务时间的最大值,即,作业延迟假设其任务在到达时立即进入服务。这个概念量化的影响,在一个工作水平上的工作由多个任务,从而偏离了传统的零排队延迟单任务的工作在文献中。我们表明,零延迟并行作业可以实现使用批填充政策(著名的豆荚政策的变体)与探测开销$d = ω\left(\frac{1}{(1-λ)\log k}\right)$在次Halfin-惠特重交通制度,其中$k$是在每个作业的任务数{和$k$适当的规模与$N$(服务器的数量)}。这一结果表明,对于并行作业,可以实现零延迟与较小的探测开销。我们还建立了一个不可能的结果:我们表明,零延迟不能实现,如果$d = \exp\left({o\left(\frac{\log N}{\log k}\right)}\right)$。

英文摘要:

Zero queueing delay is highly desirable in large-scale computing systems. Existing work has shown that it can be asymptotically achieved by using the celebrated Power-of-$d$-choices (pod) policy with a probe overhead $d = ω\left(\frac{\log N}{1-λ}\right)$, and it is impossible when $d = O\left(\frac{1}{1-λ}\right)$, where $N$ is the number of servers and $λ$ is the load of the system. However, these results are based on the model where each job is an indivisible unit, which does not capture the parallel structure of jobs in today's predominant parallel computing paradigm. This paper thus considers a model where each job consists of a batch of parallel tasks. Under this model, we propose a new notion of zero (asymptotic) queueing delay that requires the job delay under a policy to approach the job delay given by the max of its tasks' service times, i.e., the job delay assuming its tasks entered service right upon arrival. This notion quantifies the effect of queueing on a job level for jobs consisting of multiple tasks, and thus deviates from the conventional zero queueing delay for single-task jobs in the literature. We show that zero queueing delay for parallel jobs can be achieved using the batch-filling policy (a variant of the celebrated pod policy) with a probe overhead $d = ω\left(\frac{1}{(1-λ)\log k}\right)$ in the sub-Halfin-Whitt heavy-traffic regime, where $k$ is the number of tasks in each job { and $k$ properly scales with $N$ (the number of servers)}. This result demonstrates that for parallel jobs, zero queueing delay can be achieved with a smaller probe overhead. We also establish an impossibility result: we show that zero queueing delay cannot be achieved if $d = \exp\left({o\left(\frac{\log N}{\log k}\right)}\right)$.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑