[Gluster-users] poor performance on distributed system

[Gilberto Ferreira]

Hi

It will useful if you could provide some info:

gluster vol status
gluster vol info

How about the disk itself? HDD? SSD? NVME? RAID of some sort? ZFS? XFS?

In this way, people in the list can help






Em qua., 25 de jun. de 2025 às 07:21, Ricardo Román-Brenes <
ricardo at bilkent.edu.tr> escreveu:

> Hi. I have a system with 15 nodes. 4 of those nodes have disks that make
> up a gluster volume, that is then mounted on each of the 15 nodes as /home
> directory for users.
>
> The system performs fine at start but as time goes by, it comes unusable
> to a point where people cannot login or it takes over 5minutes for a login
> to be successful; and after that doing almost any operation on /home
> directory is again unusable due to the large amount of time it takes to
> finish.
>
> Is there a way I can make this better? If i restart the daemon, the system
> becomes usable again, but this is not a stable solution for me.
>
> THanks
>
> -Ricardo
> ________
>
>
>
> Community Meeting Calendar:
>
> Schedule -
> Every 2nd and 4th Tuesday at 14:30 IST / 09:00 UTC
> Bridge: https://meet.google.com/cpu-eiue-hvk
> Gluster-users mailing list
> Gluster-users at gluster.org
> https://lists.gluster.org/mailman/listinfo/gluster-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.gluster.org/pipermail/gluster-users/attachments/20250625/5b928925/attachment.html>