[Gluster-users] distribute replicated volume and tons of questions

Gandalf Corvotempesta gandalf.corvotempesta at gmail.com
Wed Feb 22 20:18:54 UTC 2017


2017-02-22 21:16 GMT+01:00 Joe Julian <joe at julianfamily.org>:
> I've been using btrfs for that. In my own tests, btrfs has performed better
> for my use cases.

I had about 7 XFS crashes in 2 month on my backup server.
*every* time i had to run xfs_repair to fix. It took 18hours, the
second time. The first failed due to OOM (16GB)
I don't think you'll be able to run fsck in parallel on 12 disks at
the same time, the server will crash. I also had crashes during an xfs
repair.

No, i'll never use XFS again.


More information about the Gluster-users mailing list