<div dir="ltr"><div dir="ltr"><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Tue, 22 Jan 2019 at 11:42, Amar Tumballi Suryanarayan <<a href="mailto:atumball@redhat.com">atumball@redhat.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div dir="ltr"><div dir="ltr"><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail-m_7525886443949779843gmail_attr">On Thu, Jan 10, 2019 at 1:56 PM Hu Bert <<a href="mailto:revirii@googlemail.com" target="_blank">revirii@googlemail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Hi,<br>
<br>
> > We ara also using 10TB disks, heal takes 7-8 days.<br>
> > You can play with "cluster.shd-max-threads" setting. It is default 1 I<br>
> > think. I am using it with 4.<br>
> > Below you can find more info:<br>
> > <a href="https://access.redhat.com/solutions/882233" rel="noreferrer" target="_blank">https://access.redhat.com/solutions/882233</a><br>
> cluster.shd-max-threads: 8<br>
> cluster.shd-wait-qlength: 10000<br>
<br>
Our setup:<br>
cluster.shd-max-threads: 2<br>
cluster.shd-wait-qlength: 10000<br>
<br>
> >> Volume Name: shared<br>
> >> Type: Distributed-Replicate<br>
> A, you have distributed-replicated volume, but I choose only replicated<br>
> (for beginning simplicity :)<br>
> May be replicated volume are healing faster?<br>
<br>
Well, maybe our setup with 3 servers and 4 disks=bricks == 12 bricks,<br>
resulting in a distributed-replicate volume (all /dev/sd{a,b,c,d}<br>
identical) , isn't optimal? And it would be better to create a<br>
replicate 3 volume with only 1 (big) brick per server (with 4 disks:<br>
either a logical volume or sw/hw raid)?<br>
<br>
But it would be interesting to know if a replicate volume is healing<br>
faster than a distributed-replicate volume - even if there was only 1<br>
faulty brick.<br>
<br></blockquote><div><br></div><div>We don't have any data point to agree to this, but it may be true. Specially, as the crawling when DHT (ie, distribute) is involved can get little slower, which means, the healing would get slower too.</div></div></div></div></blockquote><div><br></div><div>If the healing is being done by the Self heal daemon, the slowdown is not due to dht (shd does not load dht).</div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div dir="ltr"><div class="gmail_quote"><div><br></div><div>We are trying to experiment few performance enhancement patches (like <a href="https://review.gluster.org/20636" target="_blank">https://review.gluster.org/20636</a>), would be great to see how things work with newer base. Will keep the list updated about performance numbers once we have some more data on them.</div><div><br></div><div>-Amar</div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<br>
Thx<br>
Hubert<br>
_______________________________________________<br>
Gluster-users mailing list<br>
<a href="mailto:Gluster-users@gluster.org" target="_blank">Gluster-users@gluster.org</a><br>
<a href="https://lists.gluster.org/mailman/listinfo/gluster-users" rel="noreferrer" target="_blank">https://lists.gluster.org/mailman/listinfo/gluster-users</a><br>
<br>
<br>
</blockquote></div><br clear="all"><div><br></div>-- <br><div dir="ltr" class="gmail-m_7525886443949779843gmail_signature"><div dir="ltr"><div><div dir="ltr"><div>Amar Tumballi (amarts)<br></div></div></div></div></div></div></div>
_______________________________________________<br>
Gluster-users mailing list<br>
<a href="mailto:Gluster-users@gluster.org" target="_blank">Gluster-users@gluster.org</a><br>
<a href="https://lists.gluster.org/mailman/listinfo/gluster-users" rel="noreferrer" target="_blank">https://lists.gluster.org/mailman/listinfo/gluster-users</a></blockquote></div></div>