[Gluster-devel] Gluster resource scheduling

[jcanter at CLEMSON.EDU]

Hi,

I have a cluster with 10 servers setup in afr mode(set from client side) which may be called upon
by any of 14 clients.  When I attempt to read from the machines, they all try to pull data from a
single server.  Is there a way to configure the load to be spread out among the mirrored servers
rather than on a single one?  Would server side afr work better in such a case?  My setup is as
follows:

#Client Setup
volume server1
  type protocol/client
  option transport-type tcp/client
  option remote-host server1
  option remote-subvolume brick
end-volume
...
volume server10
  type protocol/client
  option transport-type tcp/client
  option remote-host server10
  option remote-subvolume brick
end-volume

volume mirror0
  type cluster/afr
  subvolumes server1 server2 server3 server4 server5 server6 server7 server8 server9 server10
end-volume



#server config
volume brick
  type storage/posix
  option directory /dfs/
end-volume

volume server
  type protocol/server
  option transport-type tcp/server
  option auth.ip.brick.allow *
  subvolumes brick
end-volume


Thank you

Josh