CaltechAUTHORS
  A Caltech Library Service

Automatic log analysis with NLP for the CMS workflow handling

Layer, Lukas and Abercrombie, Daniel Robert and Bakhshiansohi, Hamed and Adelman-McCarthy, Jennifer and Agarwal, Sharad and Vargas Hernandez, Andres and Si, Weinan and Vlimant, Jean-Roch (2020) Automatic log analysis with NLP for the CMS workflow handling. EPJ Web of Conferences, 245 . Art. No. 03006. ISSN 2100-014X. https://resolver.caltech.edu/CaltechAUTHORS:20201116-155027342

[img] PDF - Published Version
Creative Commons Attribution.

1649Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20201116-155027342

Abstract

The central Monte-Carlo production of the CMS experiment utilizes the WLCG infrastructure and manages daily thousands of tasks, each up to thousands of jobs. The distributed computing system is bound to sustain a certain rate of failures of various types, which are currently handled by computing operators a posteriori. Within the context of computing operations, and operation intelligence, we propose a Machine Learning technique to learn from the operators with a view to reduce the operational workload and delays. This work is in continuation of CMS work on operation intelligence to try and reach accurate predictions with Machine Learning. We present an approach to consider the log files of the workflows as regular text to leverage modern techniques from Natural Language Processing (NLP). In general, log files contain a substantial amount of text that is not human language. Therefore, different log parsing approaches are studied in order to map the log files’ words to high dimensional vectors. These vectors are then exploited as feature space to train a model that predicts the action that the operator has to take. This approach has the advantage that the information of the log files is extracted automatically and the format of the logs can be arbitrary. In this work the performance of the log file analysis with NLP is presented and compared to previous approaches.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1051/epjconf/202024503006DOIArticle
ORCID:
AuthorORCID
Abercrombie, Daniel Robert0000-0003-0293-1944
Adelman-McCarthy, Jennifer0000-0002-4100-8928
Agarwal, Sharad0000-0002-6492-5390
Vargas Hernandez, Andres0000-0002-8911-7197
Si, Weinan0000-0002-5879-6326
Vlimant, Jean-Roch0000-0002-9705-101X
Additional Information:© The Authors, published by EDP Sciences, 2020. This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Published online: 16 November 2020.
Record Number:CaltechAUTHORS:20201116-155027342
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20201116-155027342
Official Citation:Automatic log analysis with NLP for the CMS workflow handling. Lukas Layer, Daniel Robert Abercrombie, Hamed Bakhshiansohi, Jennifer Adelman-McCarthy, Sharad Agarwal, Andres Vargas Hernandez, Weinan Si and Jean-Roch Vlimant. EPJ Web Conf., 245 (2020) 03006; DOI: https://doi.org/10.1051/epjconf/202024503006
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:106684
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:17 Nov 2020 00:04
Last Modified:17 Nov 2020 00:04

Repository Staff Only: item control page