On Wed, Apr 05, 2006 at 10:12:33AM +0200, Toni Mueller wrote: > Hello, re
> I have just experienced the weird situation that I see a number of > pings show negative times: smp has issues wrt gettimeofday()... > $ ping 172.20.10.1 > PING 172.20.10.1 (172.20.10.1): 56 data bytes > 64 bytes from 172.20.10.1: icmp_seq=0 ttl=64 time=162.004 ms > 64 bytes from 172.20.10.1: icmp_seq=1 ttl=64 time=-3.-995 ms > 64 bytes from 172.20.10.1: icmp_seq=2 ttl=64 time=0.-603 ms > 64 bytes from 172.20.10.1: icmp_seq=3 ttl=64 time=-8.-716 ms > 64 bytes from 172.20.10.1: icmp_seq=4 ttl=64 time=-7.-468 ms > 64 bytes from 172.20.10.1: icmp_seq=5 ttl=64 time=-7.-623 ms > 64 bytes from 172.20.10.1: icmp_seq=6 ttl=64 time=-7.-935 ms > 64 bytes from 172.20.10.1: icmp_seq=7 ttl=64 time=-4.-349 ms > 64 bytes from 172.20.10.1: icmp_seq=8 ttl=64 time=-5.-440 ms > 64 bytes from 172.20.10.1: icmp_seq=9 ttl=64 time=-2.-321 ms > 64 bytes from 172.20.10.1: icmp_seq=10 ttl=64 time=-2.-943 ms > 64 bytes from 172.20.10.1: icmp_seq=11 ttl=64 time=0.643 ms > 64 bytes from 172.20.10.1: icmp_seq=12 ttl=64 time=-7.-311 ms > 64 bytes from 172.20.10.1: icmp_seq=13 ttl=64 time=-1.-384 ms > 64 bytes from 172.20.10.1: icmp_seq=14 ttl=64 time=-4.-817 ms > 64 bytes from 172.20.10.1: icmp_seq=15 ttl=64 time=-1.-382 ms > 64 bytes from 172.20.10.1: icmp_seq=16 ttl=64 time=0.-450 ms > 64 bytes from 172.20.10.1: icmp_seq=17 ttl=64 time=-2.-319 ms > > > This is weird. I saw a similar thread last year in the context of 3.6, > but this is 3.8. Also, the number of negative pings should rule out any > rdate or ntp related questions. > > $ uname -a > OpenBSD lyon.as-creation.de 3.8 GENERIC.MPR#0 amd64 > > (amd64 MP + RAIDFRAME) > > After interrupting this ping and starting over a minute or so later, > this phenomenon showed up only a while later: > > > 64 bytes from 172.20.10.1: icmp_seq=107 ttl=64 time=5.962 ms > 64 bytes from 172.20.10.1: icmp_seq=108 ttl=64 time=3.311 ms > 64 bytes from 172.20.10.1: icmp_seq=109 ttl=64 time=1.130 ms > 64 bytes from 172.20.10.1: icmp_seq=110 ttl=64 time=8.616 ms > 64 bytes from 172.20.10.1: icmp_seq=111 ttl=64 time=2.844 ms > 64 bytes from 172.20.10.1: icmp_seq=112 ttl=64 time=7.525 ms > 64 bytes from 172.20.10.1: icmp_seq=113 ttl=64 time=-8.-246 ms > 64 bytes from 172.20.10.1: icmp_seq=114 ttl=64 time=-6.-845 ms > 64 bytes from 172.20.10.1: icmp_seq=115 ttl=64 time=-4.-35 ms > 64 bytes from 172.20.10.1: icmp_seq=116 ttl=64 time=-1.-540 ms > 64 bytes from 172.20.10.1: icmp_seq=117 ttl=64 time=-5.-441 ms > 64 bytes from 172.20.10.1: icmp_seq=118 ttl=64 time=-2.-789 ms > 64 bytes from 172.20.10.1: icmp_seq=119 ttl=64 time=-3.-568 ms > 64 bytes from 172.20.10.1: icmp_seq=120 ttl=64 time=-4.-971 ms > 64 bytes from 172.20.10.1: icmp_seq=121 ttl=64 time=-5.-751 ms > 64 bytes from 172.20.10.1: icmp_seq=122 ttl=64 time=-2.-161 ms > 64 bytes from 172.20.10.1: icmp_seq=123 ttl=64 time=2.827 ms > 64 bytes from 172.20.10.1: icmp_seq=124 ttl=64 time=-1.-384 ms > 64 bytes from 172.20.10.1: icmp_seq=125 ttl=64 time=0.-761 ms > 64 bytes from 172.20.10.1: icmp_seq=126 ttl=64 time=-7.000 ms > 64 bytes from 172.20.10.1: icmp_seq=128 ttl=64 time=0.956 ms > 64 bytes from 172.20.10.1: icmp_seq=129 ttl=64 time=-2.-08 ms > 64 bytes from 172.20.10.1: icmp_seq=130 ttl=64 time=0.487 ms > 64 bytes from 172.20.10.1: icmp_seq=107 ttl=64 time=5.962 ms > 64 bytes from 172.20.10.1: icmp_seq=108 ttl=64 time=3.311 ms > 64 bytes from 172.20.10.1: icmp_seq=109 ttl=64 time=1.130 ms > 64 bytes from 172.20.10.1: icmp_seq=110 ttl=64 time=8.616 ms > 64 bytes from 172.20.10.1: icmp_seq=111 ttl=64 time=2.844 ms > 64 bytes from 172.20.10.1: icmp_seq=112 ttl=64 time=7.525 ms > 64 bytes from 172.20.10.1: icmp_seq=113 ttl=64 time=-8.-246 ms > 64 bytes from 172.20.10.1: icmp_seq=114 ttl=64 time=-6.-845 ms > 64 bytes from 172.20.10.1: icmp_seq=115 ttl=64 time=-4.-35 ms > 64 bytes from 172.20.10.1: icmp_seq=116 ttl=64 time=-1.-540 ms > 64 bytes from 172.20.10.1: icmp_seq=117 ttl=64 time=-5.-441 ms > 64 bytes from 172.20.10.1: icmp_seq=118 ttl=64 time=-2.-789 ms > 64 bytes from 172.20.10.1: icmp_seq=119 ttl=64 time=-3.-568 ms > 64 bytes from 172.20.10.1: icmp_seq=120 ttl=64 time=-4.-971 ms > 64 bytes from 172.20.10.1: icmp_seq=121 ttl=64 time=-5.-751 ms > 64 bytes from 172.20.10.1: icmp_seq=122 ttl=64 time=-2.-161 ms > 64 bytes from 172.20.10.1: icmp_seq=123 ttl=64 time=2.827 ms > 64 bytes from 172.20.10.1: icmp_seq=124 ttl=64 time=-1.-384 ms > 64 bytes from 172.20.10.1: icmp_seq=125 ttl=64 time=0.-761 ms > 64 bytes from 172.20.10.1: icmp_seq=126 ttl=64 time=-7.000 ms > 64 bytes from 172.20.10.1: icmp_seq=128 ttl=64 time=0.956 ms > 64 bytes from 172.20.10.1: icmp_seq=129 ttl=64 time=-2.-08 ms > 64 bytes from 172.20.10.1: icmp_seq=130 ttl=64 time=0.487 ms > 64 bytes from 172.20.10.1: icmp_seq=131 ttl=64 time=-8.-873 ms > 64 bytes from 172.20.10.1: icmp_seq=132 ttl=64 time=-5.-751 ms > 64 bytes from 172.20.10.1: icmp_seq=133 ttl=64 time=-2.-478 ms > 64 bytes from 172.20.10.1: icmp_seq=134 ttl=64 time=-7.-623 ms > 64 bytes from 172.20.10.1: icmp_seq=135 ttl=64 time=-8.-560 ms > 64 bytes from 172.20.10.1: icmp_seq=136 ttl=64 time=-4.-348 ms > 64 bytes from 172.20.10.1: icmp_seq=137 ttl=64 time=-4.-662 ms > 64 bytes from 172.20.10.1: icmp_seq=138 ttl=64 time=10.020 ms > 64 bytes from 172.20.10.1: icmp_seq=139 ttl=64 time=-5.-442 ms > 64 bytes from 172.20.10.1: icmp_seq=140 ttl=64 time=-5.-130 ms > 64 bytes from 172.20.10.1: icmp_seq=141 ttl=64 time=-6.-843 ms > > Other machines on that same 100MBit/s Ethernet respond within more or > less consistent times of some 0.3-0.5 ms. > > Any suggestions are most welcome! > > > Best, > --Toni++ > -- paranoic mickey (my employers have changed but, the name has remained)