# Using CVMFS on a distributed Kubernetes cluster - The PRP experience

- Institution: CERN
- Department: General
- Speaker: Igor Sfiligoi
- Year: 2019
- Language: English
- Source: [CERN](https://videos.cern.ch/record/3013749)
- Licence: [CERN](http://copyright.web.cern.ch)
- Who can watch: Teens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

The Pacific Research Platform (PRP) is operating a Kubernetes cluster that manages over 2.5k CPU cores and 250 GPUs. The compute nodes are distributed over several locations, mostly in California, all connected with high speed networking of 10Gbps or higher.

In order to support OSG users, we were in need of providing CVMFS support in the Kubernetes cluster. Since user containers run unprivileged, CVMFS could not be used from the user containers themselves. The chosen path forward was to provide CVMFS as a mountable Kubernetes volume. We started with the CERN-provided CSI plugin, but had to make some changes to make it to work in our environment.

In this talk, we will detail the actual setup used, as well as the operational experience of the last 4 months. The perceived missing functionality will also be outlined..

0:00:00 Slide 1

0:00:24 Slide 2

0:00:58 Slide 3

0:01:31 Slide 4

0:02:04 Slide 5

0:03:07 Slide 6

0:03:30 Slide 7

0:04:29 Slide 8

0:05:16 Slide 9

0:05:52 Slide 10

0:07:24 Slide 11

0:07:28 Slide 12

0:07:32 Slide 13

0:07:36 Slide 14

0:07:41 Slide 15

0:07:51 Slide 16

0:08:12 Slide 17

0:08:16 Slide 18

0:08:20 Slide 19

0:08:24 Slide 20

0:08:29 Slide 21

0:08:34 Slide 22

0:08:44 Slide 23

0:09:10 Slide 24

0:10:20 Slide 25

0:11:25 Slide 26

0:12:11 Slide 27

0:12:36 Slide 28

0:12:56 Slide 29

0:14:11 Slide 30

0:15:00 Slide 31

0:15:28 Slide 32

0:15:39 Slide 33

0:15:46 Slide 34

0:16:01 Slide 35

0:17:32 Slide 36

## Lectures

1. [Using CVMFS on a distributed Kubernetes cluster - The PRP experience](https://invisiblenetwork.ai/learn/cern/3013749/6cc9f90423d6), 21 min (CERN's player)