[Gluster-users] gluster Performance

[Marcus Bointon]

On 9 May 2012, at 11:35, Arnold Krille wrote:

> So while 
> reading big files from local fuse-mount is fast, reading many small files still 
> has the network-penalty of any distributed and/or replicated system.

That's fair, however network latency shouldn't have *that* big an effect - memcached is all about the network, yet it has no trouble sustaining > 100k requests/sec per node. I even get similar performance using naïvely-replicated sharedance which does hit disk and talks to multiple nodes.

Marcus
-- 
Marcus Bointon
Synchromedia Limited: Creators of http://www.smartmessages.net/
UK info at hand CRM solutions
marcus at synchromedia.co.uk | http://www.synchromedia.co.uk/