Replies: 1 comment
-
I have submitted two PRs that may help:
|
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Currently, I see that iperf3 uses the same packet size for all packets - this generally works in most cases, but is there any option I can use that can vary the packet lengths that are being sent by a specific endpoint (e.g. 220-238 bytes) so that it mimics more or less what real-life traffic may look like for a specific application?
Also, it seems like the same value is currently used under bidirectional mode. Many times this is not feasible because the other side may not have a link that allows symmetric throughput (hence forcing you to use the lowest common denominator that can be used for both parties). As an example, my cable link supports up to 600Mbps download, but the uplink is only 20Mbps. If I were to use the bidirectional test, I would not be able to test above 20Mbps without saturating the uplink. It would be great if one can specify the value for the other side separately, e.g. (use 20Mbps for downstream but 2 Mbps for upstream - best if we can use a combination of various lengths and bandwidths for both sides).
Beta Was this translation helpful? Give feedback.
All reactions