<div dir="ltr">Thiago,<div><br></div><div style>Although nova is not explicitly aware of KSM, it is aware that deployers want to over commit their memory and cpu. Check out: <a href="http://docs.openstack.org/trunk/openstack-ops/content/compute_nodes.html">http://docs.openstack.org/trunk/openstack-ops/content/compute_nodes.html</a> there's a section on overcommiting.</div>
<div style><br></div><div style>-MIke</div></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Mon, Nov 4, 2013 at 3:35 PM, Martinx - $B%8%'!<%`%:(B <span dir="ltr"><<a href="mailto:thiagocmartinsc@gmail.com" target="_blank">thiagocmartinsc@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Stackers!<div><br></div><div>I'm thinking about something here... Linux have a very useful resource, called KSM (Kernel SamePage Merging), which reduces (apparently a lot), the amount of RAM memory used by KVM Virtual machines "of the same kind".</div>
<div><br></div><div>This means that equal virtual machines "shares" portions of physical RAM memory using CoW technique (right?).</div><div><br></div><div>So, I think that would be cool for OpenStack scheduler (?), to "have Linux KSM in mind" when launching a Instance, to try to get more from it, opening a window to safely increase RAM overcommit allocation ratio.</div>
<div><br></div><div>What do you guys think?!</div><div><br></div><div>Best!</div><div>Thiago</div></div>
<br>_______________________________________________<br>
Mailing list: <a href="http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack" target="_blank">http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack</a><br>
Post to : <a href="mailto:openstack@lists.openstack.org">openstack@lists.openstack.org</a><br>
Unsubscribe : <a href="http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack" target="_blank">http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack</a><br>
<br></blockquote></div><br></div>