David Bar-On

@AnatoliChe, it is very strange that the RX rate is exactly 10% of the TX rate. Which iperf3 version to you use (`iperf3 -v`)? What is the operating system?

I tried the same test on my machine, using both iperf3 versions 3.7 and 3.12. On both I get about 30Gbps for **both** TX and RX. I also briefly searched...

Thanks for the detailed input. Since when `--bidir` when is not used the throughput in both directions is about the same, I suspect that the issue is related to the...

> So I pretty sure it's problem of architecture of iperf3 which uses only one core I agree this is an issue, and in this case the single CPU performance...

> if you take a look at htop, you can notice server takes 100% of CPU, client only 80%. I now understand why you suggest that the single CPU allocation...

> cpu 5 5[|||||||||||||||||||||||||||||||||||||||| 78.9%] Oops! My mistake. I read the line number as the CPU number .... Thanks for sending the additional results. It shows that the 10% throughput...

> There is maybe an issue in merging this patch as it's removing a previously added option: `--time-skew-threshold` The option is not removed. It is just that this PR was...

> That means this will not allow existing clients to have multiple concurrent sessions with the updated server. This is correct.

> > That means this will not allow existing clients to have multiple concurrent sessions with the updated server. > > This is correct. Sorry, replied to quickly. With this...

>... check the cookie sent when the client is establishing the TCP connections (control or data) instead of redirecting the client to a fork of the server on a another...