<html>
<head>
<meta content="text/html; charset=utf-8" http-equiv="Content-Type">
</head>
<body text="#000000" bgcolor="#FFFFFF">
We do not using centralized storages (all instances running with
local drives). And I just can't express my happiness about this.
Every time monitoring send me '** PROBLEM ALERT bla-bla-bla', I know
it not a big deal. Just one server.<br>
<br>
I do not want <span id="result_box" class="short_text" lang="en"><span
class="hps">to turn gray</span> <span class="hps">prematurely.
Just light glance on
<a class="moz-txt-link-freetext" href="https://www.google.com/search?q=ceph+crash+corruption">https://www.google.com/search?q=ceph+crash+corruption</a></span></span>
give me strong feeling I don't want to centralize points of
failures.<br>
<br>
Btw: If I sold nodes designated for Ceph as normal compute nodes, it
will be more effective than sell only space from them (and buy more
compute nodes for actual work).<br>
<br>
<div class="moz-cite-prefix">On 01/16/2015 12:31 AM, Abel Lopez
wrote:<br>
</div>
<blockquote
cite="mid:CALtO1ZLB7_odFz2chwLmsGx5WrZV5-rKJSgeVVEK4azp2Df-MA@mail.gmail.com"
type="cite">That specific bottleneck can be solved by running
glance on ceph, and running ephemeral instances also on ceph.
Snapshots are a quick backend operation then. But you've made your
installation on a house of cards. <br>
<br>
On Thursday, January 15, 2015, George Shuklin <<a
moz-do-not-send="true" href="mailto:george.shuklin@gmail.com">george.shuklin@gmail.com</a>>
wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0
.8ex;border-left:1px #ccc solid;padding-left:1ex">Hello
everyone.<br>
<br>
One more thing in the light of small openstack.<br>
<br>
I really dislike tripple network load caused by current glance
snapshot operations. When compute do snapshot, it playing with
files locally, than it sends them to glance-api, and (if glance
API is linked to swift), glance sends them to swift. Basically,
for each 100Gb disk there is 300Gb on network operations. It is
specially painful for glance-api, which need to get more CPU and
network bandwidth than we want to spend on it.<br>
<br>
So idea: put glance-api on each compute node without cache.<br>
<br>
To help compute to go to the proper glance, endpoint points to
fqdn, and on each compute that fqdn is pointing to localhost
(where glance-api is live). Plus normal glance-api on
API/controller node to serve dashboard/api clients.<br>
<br>
I didn't test it yet.<br>
<br>
Any ideas on possible problems/bottlenecks? And how many
glance-registry I need for this?<br>
<br>
_______________________________________________<br>
OpenStack-operators mailing list<br>
<a moz-do-not-send="true">OpenStack-operators@lists.openstack.org</a><br>
<a moz-do-not-send="true"
href="http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-operators"
target="_blank">http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-operators</a><br>
</blockquote>
</blockquote>
<br>
</body>
</html>