[Gluster-users] libgfapi failover problem on replica bricks

[Paul Penev]

I am in the same boat as Fabio. I'm using glusterfs in production too.
Rebooting a brick might mean loosing a customer at this time.

However I did shorten the ping-timeout from the default 42 seconds to
5 seconds. I have been more successful at rebooting bricks, but still,
I am experiencing the death of vm (altough not every time).

I am setting up a small test cluster for experimenting more easily.
This will be a simple replica with two bricks only.