[Gluster-users] Read from fastest node only

Gionatan Danti g.danti at assyoma.it
Thu Aug 5 06:53:28 UTC 2021

Il 2021-08-05 06:00 Strahil Nikolov ha scritto:
> I'm not so sure. Imagine that local copy needs healing (outdated).
> Then gluster will check if other node's copy is blaming the local one
> and if it's "GREEN" , it will read locally. This check to the other
> servers is the slowest part due to the lattency between the nodes.

Sure, I was thinking about the "all replicas contain correct data" 
scenario. When a node is degraded/outdated, all bets are off.

> I guess the only way is to use the FUSE client mount options and
> manually change the source brick.

This should not be enough in case of degraded/failed/outdated node: from 
my understanding, the FUSE client only points to a specific server to 
have some information about the brick/server layout, re-connecting to 
the various brick as needed for the actual data transfer.

> Another option that comes to my mind is pacemaker with a IPaddr2
> reaource and the option globally-unique=true. If done properly,
> pacemaker will bring the IP on all nodes, but using IPTABLES
> (manipulated automatically by the cluster) only 1 node will be active
> at a time with a preference to the fastest node.
> Then the FUSE client can safely be configured to use that VIP, which
> in case of failure (of the fast node), will be moved to another node
> of the Gluster TSP.
> Yet, this will be a very complex design

Yeah, quite complex and fragile... I would not debug such a scenario 
when the cluster manager fails to setup the correct rules ;)


Danti Gionatan
Supporto Tecnico
Assyoma S.r.l. - www.assyoma.it
email: g.danti at assyoma.it - info at assyoma.it
GPG public key ID: FF5F32A8

More information about the Gluster-users mailing list