<div dir="ltr"><br><div class="gmail_extra"><div class="gmail_quote">On Fri, Sep 13, 2013 at 12:05 AM, Mike Spreitzer <span dir="ltr"><<a href="mailto:mspreitz@us.ibm.com" target="_blank">mspreitz@us.ibm.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><tt><font>> From: Nirmal Ranganathan <<a href="mailto:rnirmal@gmail.com" target="_blank">rnirmal@gmail.com</a>></font></tt>
<br><tt><font>> ...<div class="im"><br>
> Not host capacity, just a opaque reference to distinguish a host is
<br>
> enough. Hadoop can use that information to appropriately place block<br>
> replicas. For example if the replication count is 3, and if a host/<br>
> rack topology is provided to Hadoop, it will place each replica on
a<br>
> different host/rack granted one is available.</div></font></tt>
<br><tt><font><br>
What if there are more than three racks, but some are better choices than
others (perhaps even some are ruled out) due to considerations of various
sorts of capacity and usage?</font></tt>
<br></blockquote><div><br></div><div>Well that's left upto the specific block placement policies in hdfs, all we are providing with the topology information is a hint on node/rack placement.</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<br><tt><font>Thanks,</font></tt>
<br><tt><font>Mike</font></tt><br>_______________________________________________<br>
OpenStack-dev mailing list<br>
<a href="mailto:OpenStack-dev@lists.openstack.org">OpenStack-dev@lists.openstack.org</a><br>
<a href="http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-dev" target="_blank">http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-dev</a><br></blockquote></div></div></div>