Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-3336
Publication type: | Conference paper |
Type of review: | Peer review (abstract) |
Title: | Impact of pacemaker failover configuration on mean time to recovery for small cloud clusters |
Authors: | Benz, Konstantin Bohnert, Thomas Michael |
DOI: | 10.21256/zhaw-3336 10.1109/CLOUD.2014.59 |
Proceedings: | 2014 IEEE 7th International Conference on Cloud Computing |
Page(s): | 384 |
Pages to: | 391 |
Conference details: | 2014 IEEE 7th International Conference on Cloud Computing, Anchorage, 27 June - 2 July 2014 |
Issue Date: | 2014 |
Publisher / Ed. Institution: | IEEE |
ISBN: | 978-1-4799-5063-8 978-1-4799-5062-1 |
ISSN: | 2159-6190 2159-6182 |
Language: | English |
Subjects: | Recovery time test; Dependability; High availability; Cloud |
Subject (DDC): | 004: Computer science 005: Computer programming, programs and data |
Abstract: | In cloud environments High Availability characteristics are established by the usage of failover software (like e.g. HAProxy, Keepalive or Pacemaker). Though these tools enable automatic recovery of cloud services from outages, the recovery can still be very slow if it is not configured adequately. In this paper we developed a "Recovery Time Test" to determine if recovery time depends on configuration of the failover software and how recovery time depends on configuration settings. Another goal of the Recovery Time Test is to determine the factor by which recovery time can be decreased by a given configuration. As proof of concept, we applied the Recovery Time Test to an OpenStack cloud environment which is controlled by the Pacemaker failover software. Pacemaker mean recovery time can take a value between 110 and 160 seconds, if the tool is configured badly. We found that with a proper configuration Pacemaker mean recovery time can be reduced significantly to a value between 15 and 20 seconds. |
URI: | https://digitalcollection.zhaw.ch/handle/11475/16400 |
Fulltext version: | Accepted version |
License (according to publishing contract): | Licence according to publishing contract |
Departement: | School of Engineering |
Organisational Unit: | Institute of Computer Science (InIT) |
Appears in collections: | Publikationen School of Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Impact of Pacemaker.pdf | 380.65 kB | Adobe PDF | View/Open |
Show full item record
Benz, K., & Bohnert, T. M. (2014). Impact of pacemaker failover configuration on mean time to recovery for small cloud clusters [Conference paper]. 2014 IEEE 7th International Conference on Cloud Computing, 384–391. https://doi.org/10.21256/zhaw-3336
Benz, K. and Bohnert, T.M. (2014) ‘Impact of pacemaker failover configuration on mean time to recovery for small cloud clusters’, in 2014 IEEE 7th International Conference on Cloud Computing. IEEE, pp. 384–391. Available at: https://doi.org/10.21256/zhaw-3336.
K. Benz and T. M. Bohnert, “Impact of pacemaker failover configuration on mean time to recovery for small cloud clusters,” in 2014 IEEE 7th International Conference on Cloud Computing, 2014, pp. 384–391. doi: 10.21256/zhaw-3336.
BENZ, Konstantin und Thomas Michael BOHNERT, 2014. Impact of pacemaker failover configuration on mean time to recovery for small cloud clusters. In: 2014 IEEE 7th International Conference on Cloud Computing. Conference paper. IEEE. 2014. S. 384–391. ISBN 978-1-4799-5063-8
Benz, Konstantin, and Thomas Michael Bohnert. 2014. “Impact of Pacemaker Failover Configuration on Mean Time to Recovery for Small Cloud Clusters.” Conference paper. In 2014 IEEE 7th International Conference on Cloud Computing, 384–91. IEEE. https://doi.org/10.21256/zhaw-3336.
Benz, Konstantin, and Thomas Michael Bohnert. “Impact of Pacemaker Failover Configuration on Mean Time to Recovery for Small Cloud Clusters.” 2014 IEEE 7th International Conference on Cloud Computing, IEEE, 2014, pp. 384–91, https://doi.org/10.21256/zhaw-3336.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.