amd64 opteron, scheduler nebudi procesy vcas

[Martin Kraus]

Zdravim.
Mame HP proliant s amd opteron 6212. nic na nem nebezi takze neni vytizeny.

kdyz pustim ping na 127.0.0.1 s vterinovym intervalem tak misto aby bezel cca
5 vterin, tak bezi mnohem dele.

# time ping 127.0.0.1 -n -c 5
PING 127.0.0.1 (127.0.0.1) 56(84) bytes of data.
64 bytes from 127.0.0.1: icmp_req=1 ttl=64 time=0.028 ms
64 bytes from 127.0.0.1: icmp_req=2 ttl=64 time=0.029 ms
64 bytes from 127.0.0.1: icmp_req=3 ttl=64 time=0.030 ms
64 bytes from 127.0.0.1: icmp_req=4 ttl=64 time=0.029 ms
64 bytes from 127.0.0.1: icmp_req=5 ttl=64 time=0.029 ms

--- 127.0.0.1 ping statistics ---
5 packets transmitted, 5 received, 0% packet loss, time 14691ms
rtt min/avg/max/mdev = 0.028/0.029/0.030/0.000 ms

real    0m14.693s
user    0m0.000s
sys 0m0.004s

kdyz to stracenu tak vidim, ze se process nebudi vcas, napriklad:

3831       0.000272 write(1, "64 bytes from 127.0.0.1: icmp_req=9 ttl=64 time=0.157 ms\n", 57) = 57
3831       0.000152 recvmsg(3, 0x7fff47abc840, 0) = -1 EAGAIN (Resource temporarily unavailable)
3831      10.145633 sendmsg(3, {msg_name(16)={sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("127.0.0.1")}, ms

misto aby se vzbudil za vterinu, tak se vzbudi v extremnim pripade az za 10
vterin.

Pokud zacneme generovat interrupty napriklad sitovym provozem, tak se vse
vrati na danou dobu do normalu.

Setkal se nekdo s necim podobnym?

diky
mk