# ConnectX-5 RX RSS has no impact even allocating more rx queues

**URL:** <https://forums.developer.nvidia.com/t/connectx-5-rx-rss-has-no-impact-even-allocating-more-rx-queues/206157>\
**Category:** Uncategorized\
**Tags:** rx\
**Created:** [March 25, 2021, 8:46am UTC](https://forums.developer.nvidia.com/t/connectx-5-rx-rss-has-no-impact-even-allocating-more-rx-queues/206157 "2021-03-25T08:46:27Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![setprem](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@setprem](https://forums.developer.nvidia.com/u/setprem)\
**Post date:** [March 25, 2021, 8:46am UTC](https://forums.developer.nvidia.com/t/connectx-5-rx-rss-has-no-impact-even-allocating-more-rx-queues/206157/1 "2021-03-25T08:46:27Z")

</div>

I am running pktgen in another server, connected to RX server via 100G DAC (only one 100G port is used for testing). pktgen is generating 25 Mpps.

But at RX server, it is receiving at a rate of 12-14 Mpps. I tried RSS and spread it to 4 RX Queues and dedicated lcore for reading from each RX Queue. But the collective RX capability still remains 12-14 Mpps. No matter how many more Queues i inrease, total RX rate remains the same as 12-14 Mpps.

Any help would be highly appreciated. RSS conf I used at receiver side is given below

_.rx\_adv\_conf = {_

_.rss\_conf = {_

_.rss\_hf = ETH\_RSS\_IP | ETH\_RSS\_UDP |_

_ETH\_RSS\_TCP | ETH\_RSS\_SCTP,_

_}_

_},_

Here is a sample output where I am priting no:of pkts received from each RX queue read within a second. Total 4 Queues

_Instance: 0 . Pkts: 3104552_

_Instance: 1 . Pkts: 3015873_

_Instance: 2 . Pkts: 3798675_

_Instance: 3 . Pkts: 2729060_

_IN\_PKTS Total: 12648174_

---

<div class="post-metadata">

**Author:** ![MvB](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/mvb/32/367020_2.png) [@MvB](https://forums.developer.nvidia.com/u/MvB)\
**Post date:** [March 28, 2021, 7:13pm UTC](https://forums.developer.nvidia.com/t/connectx-5-rx-rss-has-no-impact-even-allocating-more-rx-queues/206157/2 "2021-03-28T19:13:22Z")

</div>

Hello Prem,

Thank you for posting your inquiry on the NVIDIA Networking Community.

Based on the information provided, the issue is not related to a malfunction of the adapter or the mlx5 PMD driver.

Please review the latest DPDK performance reports related to tuning and testing DPDK to achieving full performance on our adapters.

Thank you and regards,

~NVIDIA Networking Technical Support

---

<div class="post-metadata">

**Author:** ![setprem](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@setprem](https://forums.developer.nvidia.com/u/setprem)\
**Post date:** [March 29, 2021, 1:56pm UTC](https://forums.developer.nvidia.com/t/connectx-5-rx-rss-has-no-impact-even-allocating-more-rx-queues/206157/3 "2021-03-29T13:56:11Z")

</div>

Hello Martijn,

Thank you for the reply. I will go through the performance optimizations for dpdk with mellanox card.

Since i have not tried any cards other than connect-x-5 , just need confirmation for below two points.

1. Can Mellanox card will be able to intake more packets (pps) if we increase the RX queues using RSS capability.
2. I am using AMD Epyc 7702 processor (64 cores). Does using AMD proc can impact the performance with mellanox card? Should I consider intel xeon processor ?

Thanks & Regards,

Prem Sankar