Multi-resource packing for cluster schedulers

Abstract

Abstract-Tasks in modern data-parallel clusters have highly diverse resource requirements along CPU, memory, disk and network. We present Tetris, a multi-resource cluster scheduler that packs tasks to machines based on their requirements of all resource types. Doing so avoids resource fragmentation as well as over-allocation of the resources that are not explicitly allocated, both of which are drawbacks of current schedulers. Tetris adapts heuristics for the multidimensional bin packing problem to the context of cluster schedulers wherein task arrivals and machine availability change in an online manner and wherein task's resource needs change with time and with the machine that the task is placed at. In addition, Tetris improves average job completion time by preferentially serving jobs that have less remaining work. We observe that fair allocations do not o er the best performance and the above heuristics are compatible with a large class of fairness policies; hence, we show how to simultaneously achieve good performance and fairness. Tracedriven simulations and deployment of our Apache YARN prototype on a node cluster show gains of over in makespan and job completion time while achieving nearly perfect fairness.

ROSE: Cluster Resource Scheduling via Speculative Over-Subscription

“…In order to comprehensively consider various resource dimensions, ROSE leverages a modified tetris algorithm [26] to calculate where speculative tasks should be packed. The method predominantly comprises task packing as an optimal projecting problem within a multi-dimensional euclidean space.…”

Tempo

“…WOHA [33] improves workflow deadline satisfactions in Hadoop. Tetris [23] avoids resource fragmentation by introducing multi-resource packing of tasks to machines. Tetris improves the average job completion time, and achieves high cluster makespan.…”

“…This process is brittle and increasingly hard as workloads evolve, data and cluster sizes change, and new workloads are added. Thus, techniques have been proposed in the literature to support specific SLOs such as deadlines [14,33,20,45], fast job response times [10,14,23,39], high resource utilization [2,10,14], scalability [2,41,49], and transparent failure recovery [49].…”

Improved YARN resource scheduling algorithm based on network load sensing

“…Qing proposed a method to calculate the number of sub tasks and assignment priority index for allocating resources [11], which could balance resources and tasks. Grandl introduced the heuristic method and proposed the multi-type resources scheduling algorithm [12]. The algorithm not only took into account of the computing resources and memory resources, storage resources and network resources, at the same time, gave assignments based on multi-type resources demand to prevent resource fragmentation and excessive allocation problem.…”