<div dir="auto"><div><div class="gmail_extra"><div class="gmail_quote">Il 05 gen 2017 2:00 PM, "Jeff Darcy" <<a href="mailto:jdarcy@redhat.com">jdarcy@redhat.com</a>> ha scritto:<blockquote class="quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">There used to be an idea called "data classification" to cover this<br>
kind of case. You're right that setting arbitrary goals for arbitrary<br>
objects would be too difficult. However, we could have multiple pools<br>
with different replication/EC strategies, then use a translator like<br>
the one for tiering to control which objects go into which pools based<br>
on some kind of policy. To support that with a relatively small<br>
number of nodes/bricks we'd also need to be able to split bricks into<br>
smaller units, but that's not really all that hard<br></blockquote></div></div></div><div dir="auto"><br></div><div dir="auto">IMHO one of the biggest drawback in gluster is the way it manage bricks</div><div dir="auto">Adding the ability to add one server per time without having to manually rebalance or similiar would be usefully</div><div dir="auto"><br></div><div dir="auto">Both ceph and lizard manage this automatically.</div><div dir="auto">If you want, you can add a single disk to a working cluster and automatically the whole cluster is rebalanced transparently with no user intervention</div><div dir="auto"><br></div><div dir="auto">This is really usefully an much less error prone that having to manually rebalance all the things </div><div dir="auto"><div class="gmail_extra"><div class="gmail_quote"><blockquote class="quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"></blockquote></div></div></div></div>