[Gluster-devel] cache doesn t seem to be taken into account

[Sebastien COUPPEY]

hello,

I discovered the GLFS 2 days ago, and have been since testing it.


I have 2 node AFR client side
1 client
version 1.3.7 everywhere
100 Mbits 

I did some transferts test with CP :

 Reference test : 

 scp laptop -> 1 node
  (128Mo) 11s
  (256Mo) 23s
  (1Go) 1m 33s


 cp laptop -> 2 nodesAFR (= cp localfile on the mount)
  (128Mo) 23s
  (256Mo) 47s
  (1Go) 3m 10 s

 the client is using 100 % of the bandwidth and as the AFR definition
 in on the client side such results seems normal to me.

 reference test : 
 cp localfs -> localfs
  (128Mo) 7s

 cp 2 nodeAFR -> laptop (=cp from the mount to localfilesystem)
  (128Mo) 0m11.864s

2nd try : 

 (128Mo) 0m11.878s

and on both time of the CP, it was the same node1
  
I thought that after the 1 read, the second one would have been like
the local filesystem. and all the file is read always from the same
node, I don t have 50%(node1) + 50%(node2) -> 100% laptop bandwidth.

is it normal ?
I attach my config files, maybe the order of a translator is missing
in the configuration.

Thanks for your advices.

glusterfs-client.vol
Description: Text document

glusterfs-server.vol
Description: Text document