Analysis of the Jobs Resource Utilization on a Production System

Joseph Emeras 1 Cristian Ruiz 1 Jean-Marc Vincent 1 Olivier Richard 1
1 MESCAL - Middleware efficiently scalable
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
Abstract : In HPC community the System Utilization metric enables to determine if the resources of the cluster are efficiently used by the batch scheduler. This metric considers that all the allocated resources (memory, disk, processors, etc) are full-time utilized. To optimize the system performance, we have to consider the effective physical consumption by jobs regarding the resource allocations. This information gives an insight into whether the cluster resources are efficiently used by the jobs. In this work we propose an analysis of production clusters based on the jobs resource utilization. The principle is to collect simultaneously traces from the job scheduler (provided by logs) and jobs resource consumption. The latter has been realized by developing a job monitoring tool, whose impact on the system has been measured as lightweight (0.35% speed-down). The key point is to statistically analyze both traces to detect and explain underutilization of the resources. This could enable to detect abnormal behavior, bottlenecks in the cluster leading to a poor scalability, and justifying optimizations such as gang scheduling or best-effort scheduling. This method has been applied to two medium sized production clusters on a period of eight months.
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal.inria.fr/hal-00918372
Contributor : Arnaud Legrand <>
Submitted on : Friday, December 13, 2013 - 2:11:53 PM
Last modification on : Tuesday, July 9, 2019 - 1:26:56 AM
Long-term archiving on : Tuesday, March 18, 2014 - 12:35:41 PM

File

emeras.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00918372, version 1

Collections

Citation

Joseph Emeras, Cristian Ruiz, Jean-Marc Vincent, Olivier Richard. Analysis of the Jobs Resource Utilization on a Production System. Job Scheduling Strategies for Parallel Processing, 2013, Boston, United States. ⟨hal-00918372⟩

Share

Metrics

Record views

470

Files downloads

222