Achieving Zero Asymptotic Queueing Delay for Parallel Jobs

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 $d = \omega\left(\frac{\log N}{1-\lambda}\right)$, and it is impossible when $d = O\left(\frac{1}{1-\lambda}\right)$, where $N$ is the number of servers and $\lambda$ 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 $d = \omega\left(\frac{1}{(1-\lambda)\log k}\right)$ 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 $d = \exp\left({o\left(\frac{\log N}{\log k}\right)}\right)$.