JINR cloud infrastructure evolution
To fulfil JINR commitments in different national and international projects related to the use of modern information technologies such as cloud and grid computing as well as to provide a modern tool for JINR users for their scientific research a cloud infrastructure was deployed at Laboratory of Information Technologies of Joint Institute for Nuclear Research. OpenNebula software was chosen as a cloud platform. Initially it was set up in simple configuration with single front-end host and a few cloud nodes. Some custom development was done to tune JINR cloud installation to fit local needs: web form in the cloud web-interface for resources request, a menu item with cloud utilization statistics, user authentication via Kerberos, custom driver for OpenVZ containers. Because of high demand in that cloud service and its resources over-utilization it was re-designed to cover increasing users’ needs in capacity, availability and reliability. Recently a new cloud instance has been deployed in high-availability configuration with distributed network file system and additional computing power.
Unable to display preview. Download preview PDF.
- 1.A. V. Baranov, N. A. Balashov, N. A. Kutovskiy, and R. N. Semenov, “Cloud infrastructure at JINR,” Comput. Res. Model. 4, 463–467 (2015).Google Scholar
- 2.KVM. http://www.linux-kvm.org/page/Main_Page.Google Scholar
- 3.Red Hat Cluster Suite. https://en.wikipedia.org/wiki/Red_Hat_cluster_suite.Google Scholar
- 4.rOCCI: https://github.com/EGI-FCTF/rOCCI-server.Google Scholar
- 5.OpenVZ. http://openvz.org.Google Scholar
- 6.Distributed Replication Block (DRDB). http://drbd.org.Google Scholar
- 7.Heartbeat. http://linux-ha.org/wiki/Heartbeat.Google Scholar
- 8.LizardFS. http://lizardfs.com.Google Scholar
- 9.Nagios. www.nagios.org.Google Scholar
- 10.https://miccom.jinr.ru/en/jinr-resources/jinr-cloudservice/#Cloud_service_utilization.Google Scholar
- 11.https://miccom.jinr.ru/en/jinr-resources/jinr-cloudservice/#Training.Google Scholar