A Spatiotemporal Data Aggregation Technique for Performance Analysis of Large-scale Execution Traces

Damien Dosimont 1 Robin Lamarche-Perrin 2, * Lucas Mello Schnorr 3 Guillaume Huard 1 Jean-Marc Vincent 4
* Corresponding author
1 MOAIS - PrograMming and scheduling design fOr Applications in Interactive Simulation
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
4 MESCAL - Middleware efficiently scalable
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
Abstract : Analysts commonly use execution traces collected at runtime to understand the behavior of an application running on distributed and parallel systems. These traces are inspected post mortem using various visualization techniques that, however, do not scale properly for a large number of events. This issue, mainly due to human perception limitations, is also the result of bounded screen resolutions preventing the proper drawing of many graphical objects. This paper proposes a new visualization technique overcoming such limitations by providing a concise overview of the trace behavior as the result of a spatiotemporal data aggregation process. The experimental results show that this approach can help the quick and accurate detection of anomalies in traces containing up to two hundred million events.
Liste complète des métadonnées

Cited literature [18 references]  Display  Hide  Download

https://hal.inria.fr/hal-01065093
Contributor : Damien Dosimont <>
Submitted on : Wednesday, September 17, 2014 - 5:54:39 PM
Last modification on : Thursday, October 11, 2018 - 8:48:03 AM
Document(s) archivé(s) le : Thursday, December 18, 2014 - 11:57:01 AM

File

dlpaggreg.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01065093, version 1

Collections

Citation

Damien Dosimont, Robin Lamarche-Perrin, Lucas Mello Schnorr, Guillaume Huard, Jean-Marc Vincent. A Spatiotemporal Data Aggregation Technique for Performance Analysis of Large-scale Execution Traces. IEEE Cluster 2014, Sep 2014, Madrid, Spain. ⟨hal-01065093⟩

Share

Metrics

Record views

598

Files downloads

384