<div dir="auto">I actually have 4 bricks with no arbiters. Fixed quorum count of 1 assures the files will be accessible even if all but 1 brick go down. Performance is good enough, though it can always be better, of course. </div><br><div class="gmail_quote"><div dir="ltr">On Fri, Jan 18, 2019, 5:37 AM Andreas Davour <<a href="mailto:ante@update.uu.se">ante@update.uu.se</a> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">On Fri, 18 Jan 2019, Diego Remolina wrote:<br>
<br>
> The OP (me) has a two node setup. I am not sure how many nodes in Artem's<br>
> configuration (he is running 4.0.2).<br>
><br>
> It can make sense that the more bricks you have, the higher the performance<br>
> hit in certain conditions, given that supposedly one of the issues of<br>
> gluster with many small files is that gluster has to stat the files in all<br>
> the bricks (I would assume where they reside), so this is what creates the<br>
> high latencies which lead to bad performance with many small files.<br>
><br>
> I am no expert on the internals of how it works, so I am not 100% sure<br>
> though.<br>
<br>
Ah! Look at that. I mixed up you and Artem. Sorry about that!<br>
<br>
/andreas<br>
<br>
--<br>
"economics is a pseudoscience; the astrology of our time"<br>
Kim Stanley Robinson<br>
</blockquote></div>