About
In this communication, we are going to present the deployment project of the EOS storage software solution at the GRIF site. GRIF is a distributed site made of four (4) different subsites, in different locations of the Paris region. The worst network latency between the subsites is within 2-4 msec with 3 of them connected with a 100G connection. The objective is to consolidate the four (4) currently independent DPM instances into (a new) one EOS instance. The EOS capabilities such as the service structure (simple roles based on xrootd), the failover mechanism, the redundancy of metadata nodes, and the backend key/store database (quarkdb)) ensure with a straightforward installation and configuration the high availability requirements for the geographically distributed environment of GRIF. We are going to discuss the future EOS service structure and capacities at GRIF and present a summary of the organization of the EOS filesystems over legacy raid6 storage devices on heterogeneous hardware..
0:00:00 Slide 1
0:01:56 Slide 2
0:03:20 Slide 3
0:04:42 Slide 4
0:06:56 Slide 5
0:08:38 Slide 6
0:09:55 Slide 7
0:12:23 Slide 8
0:16:16 Slide 9
0:17:46 Slide 10
0:19:28 Slide 11
The talk
Credits and licence
- Institution
- CERN
- Department
- HEP Computing
- Speaker
- Emmanouil Vamvakopoulos
- Year
- 2022
- Language
- English
- Subjects
- Computer science
- Source
- CERN
- Licence
- CERN, as CERN states it. CERN's terms
- Attribution
- © CERN. CERN provides its audiovisual media free of charge for educational and informational use, credited to CERN; this lecture is shown in CERN's own player.
- Who can watch
- CERN gives no rating. Invisible Network shows it to Tweens profiles and older, judged from what the source says about it. How courses are placed