Hi Greg, Am 13.02.21 um 15:50 schrieb Greg Troxel:
- For any network issues, I recommend doing "netstat -s" before and
after a test, and then diffing the results, trying to understand the
origin of all counter changes. For example in your case, there
probably shouldn't be any dropped packets. So if that increments --
or more importantly some other counter none of us have thought
about -- that's interesting.
Seems like my original response did not pass the filter of the mailing list due to attachments.
I have now run the test iperf3 with 128K window size on localhost again with netstat -s (before/after comparison). The system was rebooted before each test run and I ran the tests directly on the VGA console to exclude influences via SSH. When comparing the two diffs, I noticed:
- "packets sent" with Xen is only a third of the value without Xen. Is this an indication that different packet sizes are being used here, i.e. under Xen the packet size is larger by default?
- "correct ACK header predictions" and "correct data packet header predictions" are many times higher without Xen than with Xen. Both parameters don't tell me much, but they sound like a high value would be beneficial here, i.e. another indication that something is wrong in the case with Xen?
Kind regards Matthias