David Bar-On

> Can anyone help me locate where the problem is? I don't have an answer, but some points that can help evaluation: 1. From the `-w 64k` test, the link...

> is fixed in 3.15? @asy972, I believe that the issue was fixed by PR #1282, using socket's `TCP_USER_TIMEOUT` option. Timeout is set using `--snd-timeout` and `--rcv-timeout`.

> No. I tested it now. --snd-timeout isn't help. Version 3.14 remained susceptible for this DoS but 3.15 canceled arbitrary connection without my patch. Sorry for wrong answer. PR #1282...

Maybe try using different server port numbers (`--port`), in case 5201 and some other ports are blocked for some reason.

> Using the -w parameter will result in a smaller bandwidth, which is set to a maximum of 416K, and cannot reach the bandwidth when the-w parameter is not used....

@bmah888 I have change the PR to use `-Z` option for using `sendmmsg` for UDP, instead of adding a new option (I also rewrote the PR description). I also enhanced...

@bmah888, I believe this PR should be merged into the mainline, as it seems to be important for Windows users. It fixes issue #1314 and probably also #1201. Although I...

@swg0101, I built and run my original code (more than a 1.5 years old) and it runs o.k. in both direction. I didn't have time yet to evaluate your code,...

Hi @swg0101, the problem seem to be in [this line](https://github.com/swg0101/iperf/blob/962e4a9224820e27ca03fb41b50430a4232cedda/src/iperf_udp.c#L76): `sp->settings->blksize_max` should be `sp->settings->blksize` (the error causes calling `Nread` instead of `Pread`).

> I'm also not 100% sure if this doesn't potentially have side effects for the test initialization state transition on the slave side in case the connect datagram is not...