<div dir="ltr"><div>Thanks Bodireddy.</div><div><br></div>Sorry I am a bit confused about the EMC occupied size per PMD, here[1] has a different story.<div><br><div>Do you mean in real scenarios OVS-DPDK can be memory bound on EMC? I thought EMC should be totally fit in LLC.</div><div><br></div><div>If the megaflows just part in LLC, then the cost of copy between memory and LLC should be large, isn't it not like what defined as 'fast path' in userspace compared with kernel datapath? And if most of megaflows are in memory, the reason of every PMD has one dpcls instance is to follow the rule PMD thread should has local data as most as it can, but not every PMD put it in its local cache, if that is true, I can't see why 64k is the limit num, unless this is an experience best value calculated from vtune/perf resutls.</div><div><br></div><div>You are probably enabled hyper-thread with 35MB and got 28 cores.</div><div><br></div><div>[1] <a href="https://mail.openvswitch.org/pipermail/ovs-dev/2015-May/298999.html">https://mail.openvswitch.org/pipermail/ovs-dev/2015-May/298999.html</a></div><div><br></div><div> </div></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Thu, Jun 29, 2017 at 10:23 PM, Bodireddy, Bhanuprakash <span dir="ltr"><<a href="mailto:bhanuprakash.bodireddy@intel.com" target="_blank">bhanuprakash.bodireddy@intel.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">><br>
>I guess the answer is now the general LLC is 2.5M per core so that there is 64k<br>
>flows per thread.<br>
<br>
</span>AFAIK, the no. of flows here may not have to do anything with LLC. Also there is EMC cache(8k entries) of ~4MB per PMD thread.<br>
Yes the performance will be nice with simple test cases (P2P with 1 PMD thread) as most of this fits in to LLC. But in real scenarios OvS-DPDK can be memory bound.<br>
<br>
BTW, on my DUT the LLC is 35MB and has 28 cores and so the assumption of 2.5M/core isn't right.<br>
<span class="HOEnZb"><font color="#888888"><br>
- Bhanuprakash.<br>
</font></span><div class="HOEnZb"><div class="h5"><br>
><br>
>On Fri, Jun 23, 2017 at 11:15 AM, Hui Xiang <<a href="mailto:xianghuir@gmail.com">xianghuir@gmail.com</a>> wrote:<br>
>Thanks Darrell,<br>
><br>
>More questions:<br>
>Why not allocating 64k for each dpcls? does the 64k just fit in L3 cache or<br>
>anywhere? how it is calculated in such an exact number? If there are more<br>
>ports added for polling, for avoid competing can I increase the 64k size into a<br>
>bigger one? Thanks.<br>
><br>
>Hui.<br>
><br>
><br>
<br>
</div></div></blockquote></div><br></div>