Quiet Neighborhoods: Key to Protect Job Performance Predictability
Authors:
- Ana JokanovicAJAna Jokanovic
- Jose Carlos SanchoJSJose Carlos Sancho
- German RodriguezGRGerman Rodriguez
- Alejandro LuceroALAlejandro Lucero
- Cyriel MinkenbergCMCyriel Minkenberg
- Jesus LabartaJLJesus Labarta
- 1 May 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 449-459
Abstract
Interference of nearby jobs has been recently identified as the dominant reason for the high performance variability of parallel applications running on High Performance Computing (HPC) systems. Typically, HPC systems are dynamic with multiple jobs coming and leaving in an unpredictable fashion, sharing simultaneously the system interconnection network. In such environment contention for network resources is causing random stalls in the progress of application execution degrading application and system performance overall. Eliminating job interactions in their neighbourhoods is key for guaranteeing performance predictability of applications. In this paper we are proposing the concept of quiet neighbourhoods that significantly reduce job interactions. Quiet neighbourhoods are created by the system resource manager in two phases. First, multiple virtual network blocks are defined on the top of the physical network resources based on typical workload distributions. Second, newly arriving jobs are allocated in these virtual blocks based on their size.Keywords
This publication has 17 references indexed in Scilit:
- There goes the neighborhood2013
- On the trade‐off of mixing scientific applications on capacity high‐performance computing systemsIET Computers & Digital Techniques, 2013
- Comprehensive Workload Analysis and Modeling of a Petascale Supercomputer2013
- Effects of Topology-Aware Allocation Policies on Scheduling Performance2009
- Lessons from the Netflix prize challengeACM SIGKDD Explorations Newsletter, 2007
- k-ary n-trees: high performance networks for massively parallel architectures2002
- On generalized fat trees2002
- Impact of job mix on optimizations for space sharing schedulers1996
- Packing schemes for gang scheduling1996
- The network architecture of the Connection Machine CM-5 (extended abstract)1992