eg

13 sntcca4lce1-hurricane-gige.wcg.net (64.200.150.106) 82.529 ms 83.709 ms 8
4.842 ms
14 pos2-3.gsr12416.pao.he.net (66.220.13.42) 90.922 ms 89.219 ms 95.109 ms
15 pos2-0.gsr12012.fmt.he.net (64.62.249.121) 99.901 ms 98.398 ms 89.797 ms
16 linode.spuddy.org (66.160.141.105) 170.146 ms 171.590 ms 169.353 ms

That extra 70->80ms between the previous hop and my linode is quite massive. I know the structure of UML could mean data passing an additional network stack (on my home network pings between one machine and a host server, and between the machine and a UML instance show the UML instance takes almost twice as long... but we're still talking usec's on my local LAN) whereas we're now talking almost doubling of round trip delays.

Could I just be testing at a bad time (00:20 Sunday morning) where the host is overloaded with weekly processing, or what?

This latency is causing some of my connections to take a long time

_________________
Rgds
Stephen
(Linux user since kernel version 0.11)

Hi,

One way to see if it is your linode that is causing the delay or a general problem is to try tracing to the host.

hostxx.linode.com

It is also worth tracing to hosts around yours as well.

Adam