<p dir="ltr">Il 21 giu 2016 19:02, "Luciano Giacchetta" <<a href="mailto:ldgiacchetta@gmail.com">ldgiacchetta@gmail.com</a>> ha scritto:<br>
><br>
> Hi,<br>
><br>
> I have similar scenario, for a cars classified with millions of small files, mounted with gluster native client in a replica config.<br>
> The gluster server has 16gb RAM and 4 cores and mount the glusterfs with direct-io-mode=enable. Then i export to all servers ( windows included with CIFS )<br>
><br>
> performance.cache-refresh-timeout: 60<br>
> performance.read-ahead: enable<br>
> performance.write-behind-window-size: 4MB<br>
> performance.io-thread-count: 64<br>
> performance.cache-size: 12GB<br>
> performance.quick-read: on<br>
> performance.flush-behind: on<br>
> performance.write-behind: on<br>
> nfs.disable: on</p>
<p dir="ltr">Which performance are you getting? </p>