Hi Laura, thanks for your reply.
It seems the OSSs will share the disks created from a shared SAN. So the
OSS-pairs can failover in a pre-defined manner if one node is down,
coordinated by a HA manager.
This can certainly work on a limited scale. I'm curious if this static
schema can scale to a
We have been using ZFS on our LFS for about the last 7 years. Back then, we
were using ZFS 0.7 and lustre 2.10 and there was a significant decrease in
metadata performance compared to ldiskfs. Most of our workflows at the time
didn’t need a lot of metadata performance and so we were OK with th
Hi Jon,
We have been running ZFS MDSs for 10-ish years, and while I'm sure there is
still some performance to be gained by using ldiskfs due to among other
things the missing support for ZFS ZIL, it's worth it to get rid of the of
the absolute BS mess that ldiskfs is. The big performance hits wher
Hi,
Me again! I now have a successful build of lustre server with ZFS support,
thanks all for your help with this. I'm now stuck on getting ldiskfs support to
work - specifically it requires the kernel-debuginfo and debugsource packages,
which on Rocky 8.6, don't exist for the kernel I'm buildi