CentOS - Jan 2005 - x86_64 timer resolution in ping results

Hi,

There seems to be a problem with the timer resolution on x86_64. This is 
clear in ping results - I don't know if it's just a ping problem or if 
it manifests elsewhere as well. It does also affect mtr and traceroute 
times.

I guess it's more a kernel issue than a CentOS problem, but is anyone 
else seeing the same?

Ping results have a resolution of 10ms - so a ping <10ms shows as 0.000ms...

--- On an Opteron machine running CentOS-3.4 ---

# uname -a
Linux omega.xxx 2.4.21-27.0.2.ELsmp #1 SMP Wed Jan 19 11:28:26 CST 2005 
x86_64 x86_64 x86_64 GNU/Linux

# ping 192.168.1.200
PING 192.168.1.200 (192.168.1.200) 56(84) bytes of data.
64 bytes from 192.168.1.200: icmp_seq=0 ttl=64 time=0.000 ms
64 bytes from 192.168.1.200: icmp_seq=1 ttl=64 time=0.000 ms
64 bytes from 192.168.1.200: icmp_seq=2 ttl=64 time=0.000 ms
64 bytes from 192.168.1.200: icmp_seq=3 ttl=64 time=0.000 ms
64 bytes from 192.168.1.200: icmp_seq=4 ttl=64 time=0.000 ms

--- 192.168.1.200 ping statistics ---
5 packets transmitted, 5 received, 0% packet loss, time 4000ms
rtt min/avg/max/mdev = 0.000/0.000/0.000/0.000 ms, pipe 2

# ping google.com
PING google.com (216.239.39.99) 56(84) bytes of data.
64 bytes from 216.239.39.99: icmp_seq=0 ttl=240 time=230 ms
64 bytes from 216.239.39.99: icmp_seq=1 ttl=240 time=220 ms
64 bytes from 216.239.39.99: icmp_seq=2 ttl=240 time=220 ms
64 bytes from 216.239.39.99: icmp_seq=3 ttl=240 time=230 ms
64 bytes from 216.239.39.99: icmp_seq=4 ttl=240 time=230 ms
64 bytes from 216.239.39.99: icmp_seq=5 ttl=240 time=220 ms

--- google.com ping statistics ---
6 packets transmitted, 6 received, 0% packet loss, time 5050ms
rtt min/avg/max/mdev = 220.006/225.006/230.006/5.000 ms, pipe 2


---- Expected result: On an i686 machine running CentOS-3.3 ----

# ping 192.168.1.202
PING 192.168.1.202 (192.168.1.202) 56(84) bytes of data.
64 bytes from 192.168.1.202: icmp_seq=0 ttl=64 time=0.094 ms
64 bytes from 192.168.1.202: icmp_seq=1 ttl=64 time=0.059 ms
64 bytes from 192.168.1.202: icmp_seq=2 ttl=64 time=0.070 ms
64 bytes from 192.168.1.202: icmp_seq=3 ttl=64 time=0.057 ms
64 bytes from 192.168.1.202: icmp_seq=4 ttl=64 time=0.068 ms

--- 192.168.1.202 ping statistics ---
5 packets transmitted, 5 received, 0% packet loss, time 4016ms
rtt min/avg/max/mdev = 0.057/0.069/0.094/0.016 ms, pipe 2

# ping google.com
PING google.com (216.239.39.99) 56(84) bytes of data.
64 bytes from 216.239.39.99: icmp_seq=0 ttl=240 time=201 ms
64 bytes from 216.239.39.99: icmp_seq=1 ttl=240 time=203 ms
64 bytes from 216.239.39.99: icmp_seq=2 ttl=240 time=201 ms
64 bytes from 216.239.39.99: icmp_seq=3 ttl=240 time=202 ms
64 bytes from 216.239.39.99: icmp_seq=4 ttl=240 time=201 ms
64 bytes from 216.239.39.99: icmp_seq=5 ttl=240 time=201 ms

--- google.com ping statistics ---
6 packets transmitted, 6 received, 0% packet loss, time 5049ms
rtt min/avg/max/mdev = 201.044/201.939/203.012/0.926 ms, pipe 2


Kind regards,

-Simon

On Sun, Jan 30, 2005 at 03:27:23PM +1300, Simon Garner
wrote:
> Hi,
> 
> There seems to be a problem with the timer resolution on x86_64. This is 
> clear in ping results - I don't know if it's just a ping problem or
if
> it manifests elsewhere as well. It does also affect mtr and traceroute 
> times.
> 
> I guess it's more a kernel issue than a CentOS problem, but is anyone 
> else seeing the same?
> 
> Ping results have a resolution of 10ms - so a ping <10ms shows as
0.000ms...
https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=137114

seems like upstream bug

Cheers,

Tru
-- 
http://pgp.mit.edu:11371/pks/lookup?op=get&search=0xBEFA581B
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: not available
URL:
<http://lists.centos.org/pipermail/centos/attachments/20050131/4ba65524/attachment-0002.sig>