<div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr">You can experiment with FUSE mount options: halo-latency & halo-min-replicas</div><div dir="ltr"> halo-latency: The threshold below which all other clients will<br> consider children (bricks) connected.<br> halo-min-replicas: The minimum number of replicas which are to<br> be enforced regardless of latency specified in the above 3 options.<br> If the number of children falls below this threshold the next<br> best (chosen by latency) shall be swapped in.<br></div></div><div><br></div><div>If you have one brick per site set halo-min-replicas to 1 and halo-latency very low so it will write to the local brick (watch that fuse connects to local gluster - it tends to mount to remote on boot);</div><div> then files written will "heal" to the other bricks on a background. Heal performance is pretty solid.<br></div><div>I wouldn't do it for VMs</div><div><br></div><div>With my clusters around 10ms max latency I dont mind slow writes to cluster.</div><div>Real problem are reads from cluster as it does all attr queries 20 times each file,</div><div>and if you have maildir 100k emails in a folder ...</div><div><br></div><div>I had to write overlay fuse file system to direct reads directly to the brick through the kernel, bypassing all gluster fuse stuff:</div><div>all reads fly, and writes go regular way <a href="https://github.com/lavdnone/unionfs-fuse">https://github.com/lavdnone/unionfs-fuse</a></div><div><br></div><div><br></div><div>You can also look in to Syncthing - surprisingly made on Go it is pretty solid. Especially for 2 replicas you want.</div><div>Shoot own discovery server on each node or on some cloud and have your sites sync with file change monitoring 0 delay.<br></div><div><br></div><div>v<br></div><div><br></div><div><br></div><div class="gmail_quote"><div dir="ltr">On Wed, Oct 17, 2018 at 1:42 AM Oğuz Yarımtepe <<a href="mailto:oguzyarimtepe@gmail.com">oguzyarimtepe@gmail.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">Any idea about the Halo configuration? Didn't find any documentation about it.</div><br><div class="gmail_quote"><div dir="ltr">On Wed, Oct 17, 2018 at 1:10 AM Vlad Kopylov <<a href="mailto:vladkopy@gmail.com" target="_blank">vladkopy@gmail.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"><div>if you going for redundancy go for 3 full nodes, arbiter setup seen bugs</div><div>doubt anything good will come out of using NFS<br></div><div>if you doing websites use VMs as hypervisors are using libgfapi</div><div> or implement libgfapi in your app directly</div><div><br></div><div>v<br></div></div></div></div><br><div class="gmail_quote"><div dir="ltr">On Sun, Oct 14, 2018 at 2:13 PM Oğuz Yarımtepe <<a href="mailto:oguzyarimtepe@gmail.com" target="_blank">oguzyarimtepe@gmail.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">Hi,<div><br></div><div>I am trying to replicate nfs mount areas between to sites that will work active active. I was checking the methods that i can use via GlusterFS and it seems replication should be the way. I am not sure how many nodes should i use fo replication. I may need to make maintenance on the GlusterFS servers and i don't want to cause server 500 failures because of inexistance of mount areas. Any tips? Should i use arbiter?</div><div><br></div><div>Regards.<br clear="all"><div><br></div>-- <br><div dir="ltr" class="gmail-m_8892658846621688388m_-2197194273363412029m_1059550660282596298gmail_signature">Oğuz Yarımtepe<br><a href="http://about.me/oguzy" target="_blank">http://about.me/oguzy</a></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>
</blockquote></div><br clear="all"><div><br></div>-- <br><div dir="ltr" class="gmail-m_8892658846621688388gmail_signature">Oğuz Yarımtepe<br><a href="http://about.me/oguzy" target="_blank">http://about.me/oguzy</a></div>
</blockquote></div></div></div>