EasyBuild VS GlusterFS

Use tools like easybuild or spack to maintain the software and the modules at the same time.

For one nice way to install software in a reproducible way for HPC and manage it via modules check: https://easybuild.io/

Get comfortable with environment modules (see e.g., lmod), and check out installation systems like EasyBuild and Spack.

Modules, in this context, refer to Environment Modules). The article would be better than any summary I could hastily provide, but I would recommend the functionally equivalent Lmod as an alternative. Furthermore, I would strongly recommend managing software installation via EasyBuild.

Software administration: https://easybuild.io/

There is an Easybuild recipe available for building Julia from source (not merged into the repo yet, but it works):

https://github.com/gluster/glusterfs/issues/894

And apparently apart from modern coreutils using that, it is mostly gentoo users hitting the bugs in lseek.

This Product Appendix does not apply to online service offerings managed by Red Hat or generally available open source projects such as www.wildfly.org, www.fedoraproject.org, www.openstack.redhat.com, www.gluster.org, www.centos.org, okd.io, Ansible Project Software or other community projects.

Just because Red Hat will stop selling commercial support for their product, does not mean GlusterFS itself is dying. It's an open source project like any other - https://github.com/gluster/glusterfs

https://www.gluster.org/ Is the way to do this across nodes

This allows us to fetch the desired quality of the video as per the user's request, and once the media file finishes processing, it will be uploaded to a distributed file storage such as HDFS, GlusterFS, or an object storage such as Amazon S3 for later retrieval during streaming.

GlusterFS

But where can we store files at scale? Well, object storage is what we're looking for. Object stores break data files up into pieces called objects. It then stores those objects in a single repository, which can be spread out across multiple networked systems. We can also use distributed file storage such as HDFS or GlusterFS.

GlusterFS - same as above (https://www.gluster.org/)

What you look for is a clustered file system. Like https://www.gluster.org/. As long as all units are closeby with low latency there are a couple solutions that allow you to create distributed storage solutions of various kinds. Key value stores applenty, clustered file systems that pretent to be one file system etc. If you have geographically distributed solutions with high latencies it becomes harder. Most open source systems don't work really well in this scenario. There were a couple attempts like Hydrabase but they didn't go so far. It normally is solved by doing two clusters and then replicate between them.

I'd imagine most managed service providers are going to require a credit card, though most of them have a free tier. If you want to take an unmanaged approach, maybe look into Gluster. I've used it before and never had issue with it, but I also had an infrastructure team that set it up, so I'm not familiar with the challenges that way: https://www.gluster.org/