[Gluster-users] Performance for KVM images (qcow)

[Robert Hajime Lanning]

On 04/09/13 01:17, Eyal Marantenboim wrote:
> Hi Bryan,
>
> We have 1G nics on all our servers.
> Do you think that changing our design to distribute-replicate will
> improve the performance?
>
> Anything in the gluster performance settings that you think I should change?

With GlusterFS, almost all the processing is in the client side.  This 
includes replication.  So, when you have "replica 4", the client will be 
duplicating all transactions 4 times, synchronously.  Your 1G ethernet 
just became 256M.

I don't know how much "in production" your environment is.  You might 
want to try the 3.4 beta with the qemu glusterfs driver (using libgfapi.so).

You should get a good speed bump, by bypassing the FUSE interface.

Also look into the write-behind and read caching translators for the 
volume itself.

-- 
Mr. Flibble
King of the Potato People