As Alan mentioned latency is more important.
Also consider using an SSD for all arbiter bricks and set maxpct (man 8
mkfs.xfs) to a high level (I prefer to use '90').
Best Regards,
Strahil Nikolov
В събота, 31 декември 2022 г., 10:43:50 ч. Гринуич+2, Alan Orth
написа:
Hi Filipe,
I
Hi Filipe,
I think it would probably be fine. The Red Hat Storage docs list the
important thing being *5ms latency*, not link speed:
https://access.redhat.com/documentation/en-us/red_hat_gluster_storage/3.5/html/administration_guide/creating_arbitrated_replicated_volumes
I haven't used an arbite
As the arbiter doesn't receive or provide any data to the clients - just
metadata ,so bandwith is not critical but lattency is.Ensure that lattency is
the same or lower for the arbiter node and you can use an SSD/NVME to ensure
that storage lattency won't be a bottleneck.
Also, don't forget to s
Hi glusters,
I'm close to deploy my first GlusterFS replica 3 arbiter 1 volume.
Below I will describe my hardware / plans:
Node1: two bricks, 2 x raid0 arrays 40gbe network
Node2: two bricks, 2 x raid0 arrays 40gbe network
Node3: Arbiter 1gbe network
Between Node1 and Node2, I have a 40gbe netw