Hello,
I have tests that seem to show that if many lxc machines emit icmp
messages at the same time, the rate is globaly measured and some get
dropped.
The following setting in each of the lxc:
echo 0 > /proc/sys/net/ipv4/icmp_ratemask
permits to have lots of icmp at the same time and permits to use
traceroute in a virtual network of lxc.
Now I have problems with the multicasts that ospf produces for the hellos
between lxc machines, do you think that it could be the same kind of
problem: a rate limit for multicasting and if so how do we deactivate it ?
Regards
Vincent Perrier
------------------------------------------------------------------------------
All the data continuously generated in your IT infrastructure contains a
definitive record of customers, application performance, security
threats, fraudulent activity and more. Splunk takes this data and makes
sense of it. Business sense. IT sense. Common sense.
http://p.sf.net/sfu/splunk-d2dcopy1
_______________________________________________
Lxc-devel mailing list
Lxc-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/lxc-devel
