Spurious loss is high when RTT is very small and bandwidth very large.

[anrossi]

Describe the bug

The timer-based loss detection seems to fall apart when RTT is 100s of microseconds. The RTT/8 interval for loss might be too short because CPU scheduler and other things can affect traffic significantly at these tiny timescales. Consider using a heuristic to adjust the loss timer when RTT is very very small.

Affected OS

• Windows
• Linux
• macOS
• Other (specify below)

Additional OS information

No response

MsQuic version

main

Steps taken to reproduce bug

Run secnetperf on a high bandwidth ultra-low latency network (like a software loopback-type network, like duonic)

Expected behavior

Connection stats succeed with reasonable numbers of suspected/spurious loss.

Actual outcome

Connection stats spurious loss numbers are high (tens of thousands), but bandwidth doesn't seem to be affected.

Additional details

No response