On Tue, Aug 19, 2025 at 04:50:23PM +0200, Kurt Kanzenbach wrote: > Installed ntpperf on one machine and chrony (v4.6) on the second. In the > chrony config there is 'hwtimestamp enp1s0'. I did run the first example > in ntpperf's README with the following results. 'rate' seems to be > higher with my patch applied. Anyway, your ntpperf output looks > completely different. What parameters are you using? I just want to > reproduce your results first. > > root@cml1:~/ntpperf# ./ntpperf -i enp1s0 -m 6c:b3:11:52:39:15 -d > 192.168.123.1 -s 172.18.0.0/16 -B -H
Interleaved mode needs to be selected by the -I option (instead of -B) in order for the server to enable SW+HW TX timestamps for the responses it sends back to the client. My ntpperf command line also had "-x 1.05" to increase the rate in smaller steps and "-o 0.000000500" to print the offset between the server TX and client RX timestamp instead of the offset between server's TX and RX timestamp (response time), but that requires the NIC PHCs to be synchronized to each other over a different network link and the -o value to be calibrated for the delays in timestamping and cable. It's not important for this issue, no need to bother with that. > * ntpperf with igb patch applied > 129721 12972 0.00% 0.00% 100.00% 0.00% +7934 +49386 +229427 17600 > 194581 16384 0.00% 0.00% 100.00% 0.00% +10760 +54961 +248325 18860 > 291871 16384 0.00% 0.00% 100.00% 0.00% +13207 +57193 +248870 16908 > 437806 16384 25.42% 0.00% 74.58% 0.00% +211479 +275061 +703480 20529 > > * ntpperf without igb patch applied > 129721 12972 0.00% 0.00% 100.00% 0.00% +2670 +14699 +242395 6692 > 194581 16384 0.00% 0.00% 100.00% 0.00% +2520 +19712 +329254 9571 > 291871 16384 1.37% 0.00% 98.63% 0.00% +2818 +77396 +15480693 > 182286 > 437806 16384 24.69% 0.00% 75.31% 0.00% +108662 +246855 +2306431 > 38520 Those results look the same within few percent, as I'd expect with the basic NTP mode (-B option), which doesn't enable server's TX timestamping. Normally, I see larger differences in subsequent runs in the same configuration. -- Miroslav Lichvar
