<html><body>
<p><font size="2" face="sans-serif">I can see both of these options would be set all the time. Users are greedy. They probably want both good latency and good bandwidth.</font><br>
<br>
<font size="2" face="sans-serif">Unless, there is a clear documentation that describes the limitations and drawbacks by enabling these options (however, the limitation and drawbacks is provide specific). Then, users may choose carefully. </font><br>
<br>
<font size="2" face="sans-serif">In general, I think users will set both options since they are ignored if hardware does not support them. Who doesn't want an EP that has both good bandwidth and latency? If both of the options are always set, or set most of the time, it is the same as not having the options.</font><br>
<br>
<font size="2" face="sans-serif">Regards,</font><br>
<font size="2" face="sans-serif"><br>
Alan</font><br>
<br>
<img width="16" height="16" src="cid:1__=0ABBF7CCDFD0D1728f9e8a93df938@us.ibm.com" border="0" alt="Inactive hide details for "Reese Faucette (rfaucett)" ---09/24/2014 11:03:13 PM---> Conceptually, I can see where not all endpo"><font size="2" color="#424282" face="sans-serif">"Reese Faucette (rfaucett)" ---09/24/2014 11:03:13 PM---> Conceptually, I can see where not all endpoints may have dedicated > hardware behind them and may</font><br>
<br>
<font size="1" color="#5F5F5F" face="sans-serif">From: </font><font size="1" face="sans-serif">"Reese Faucette (rfaucett)" <rfaucett@cisco.com></font><br>
<font size="1" color="#5F5F5F" face="sans-serif">To: </font><font size="1" face="sans-serif">"Hefty, Sean" <sean.hefty@intel.com>, "ofiwg@lists.openfabrics.org" <ofiwg@lists.openfabrics.org></font><br>
<font size="1" color="#5F5F5F" face="sans-serif">Date: </font><font size="1" face="sans-serif">09/24/2014 11:03 PM</font><br>
<font size="1" color="#5F5F5F" face="sans-serif">Subject: </font><font size="1" face="sans-serif">Re: [ofiwg] mapping adapter memory</font><br>
<font size="1" color="#5F5F5F" face="sans-serif">Sent by: </font><font size="1" face="sans-serif">ofiwg-bounces@lists.openfabrics.org</font><br>
<hr width="100%" size="2" align="left" noshade style="color:#8091A5; "><br>
<br>
<br>
<tt><font size="2">> Conceptually, I can see where not all endpoints may have dedicated<br>
> hardware behind them and may have to share resources with other<br>
> endpoints, and potentially other processes. Even adapters that can<br>
> dedicate hardware resources to every endpoint may not perform well as a<br>
> result of caching limitations on the HCA. This could require an app to share<br>
> resources (e.g. a kernel allocated QP) for specific communication channels.<br>
> <br>
> Maybe a provider can expose some attributes on the 'optimal' use of any<br>
> the underlying hardware, so that an application or job scheduler doesn't<br>
> oversubscribe the hardware. Reporting maximum values doesn't do that,<br>
> since apps often allocate the max values expecting that there won't be any<br>
> performance loss for doing so.<br>
<br>
How about something like this:<br>
There are hints the app can specify when creating an EP, such as "OPTIMIZE_FOR_LATENCY" or "OPTIMIZE_FOR_BW". If the hardware has nothing special to do for those hints, they are ignored. If there are some special hardware resources that can do one or the other, the provider will make a best-effort to match them with their respective hints. Once these special resources are exhausted, "you get what you get". So, if hardware supports N "low latency" QPs, and the app requests N+1 OPTIMIZE_FOR_LATENCY QPs, the N+1th QP will just be a little slower than the others. Moral: ask for the more important ones first.<br>
<br>
That seems not-to-invasive, and is effective for my needs.<br>
-reese<br>
_______________________________________________<br>
ofiwg mailing list<br>
ofiwg@lists.openfabrics.org<br>
</font></tt><tt><font size="2"><a href="http://lists.openfabrics.org/mailman/listinfo/ofiwg">http://lists.openfabrics.org/mailman/listinfo/ofiwg</a></font></tt><tt><font size="2"><br>
<br>
</font></tt><br>
</body></html>