Hello,<div>I am a Trainee in an IT-Firm and have been tasked with creating a basic gluster System for testing purposes. The setup went fine and creating a Server Pool was also unproblematic. Now to my problem, I created a 6 node Server Pool, with each node running 2hdds that have been partitioned to be 2 50%partitions. This leaves me with 3 "export" partitions per node. I set up an 18 brick distributed replicated Volume with a replica 6 setting. The gluster is connected with a cisco gbit switch and cat6 cables. The network setup has been evaluated with iperf and constantly yields 978 mbit/s across the board.</div>
<div>When I benchmarked the system with bonnie++, it took ages and the output showed that "Per Char" writespeed was 9 K/sec and latency around 976ms.</div><div>Overall speed of the hdd's used is fine when simply transferring files between them, but when I try to copy to a mounted gluster volume from a client in the network speed drops to around 24MB/s.</div>
<div>I hope that someone can tell me why gluster is performing so badly.</div><div>If it helps I can attach bonnie++ logs in html format for the different nodes and export directories.</div><div>Thanks in advance,</div><div>
David</div>