This is a VM host for libvirt (kvm) machines and LXC containers. I see dropped packets on the VMs too. Example #1: tompos@lxc01:~$ uptime 10:47:46 up 10:44, 2 users, load average: 0.16, 0.42, 0.48 tompos@lxc01:~$ uname -a Linux lxc01 3.2.0-23-generic #36-Ubuntu SMP Tue Apr 10 20:39:51 UTC 2012 x86_64 x86_64 x86_64 GNU/Linux LXC HOST: br-eth0 Link encap:Ethernet HWaddr 00:25:b3:82:fd:d8 inet addr:10.0.0.54 Bcast:10.0.1.255 Mask:255.255.254.0 inet6 addr: fe80::225:b3ff:fe82:fdd8/64 Scope:Link UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1 RX packets:400371 errors:0 dropped:84828 overruns:0 frame:0 TX packets:94804 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:0 RX bytes:167501161 (167.5 MB) TX bytes:18564022 (18.5 MB) Debian container: eth0 Link encap:Ethernet HWaddr 52:54:00:00:00:00 inet addr:10.0.0.55 Bcast:10.0.1.255 Mask:255.255.254.0 inet6 addr: fe80::5054:ff:fe00:0/64 Scope:Link UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1 RX packets:17213802 errors:0 dropped:84822 overruns:0 frame:0 TX packets:40391225 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:1000 RX bytes:5360613932 (4.9 GiB) TX bytes:12306335047 (11.4 GiB) Debian container: eth0 Link encap:Ethernet HWaddr 36:6d:6a:e4:86:ea inet addr:10.0.0.115 Bcast:10.0.1.255 Mask:255.255.254.0 inet6 addr: fe80::346d:6aff:fee4:86ea/64 Scope:Link UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1 RX packets:324344 errors:0 dropped:84822 overruns:0 frame:0 TX packets:1030 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:1000 RX bytes:143732907 (137.0 MiB) TX bytes:105055 (102.5 KiB) Example #2: LXC+libvirt KVM host: tompos@virt101:~$ uname -a Linux virt101 3.2.0-23-generic #36-Ubuntu SMP Tue Apr 10 20:39:51 UTC 2012 x86_64 x86_64 x86_64 GNU/Linux tompos@virt101:~$ uptime 10:51:28 up 11:05, 1 user, load average: 0.26, 0.22, 0.23 br-eth0 Link encap:Ethernet HWaddr 00:25:90:58:37:7c inet addr:10.0.0.126 Bcast:10.0.1.255 Mask:255.255.254.0 inet6 addr: fe80::225:90ff:fe58:377c/64 Scope:Link UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1 RX packets:502125 errors:0 dropped:87609 overruns:0 frame:0 TX packets:170265 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:0 RX bytes:208178343 (208.1 MB) TX bytes:30995052 (30.9 MB) Debian container: eth0 Link encap:Ethernet HWaddr ae:7f:44:57:9f:0f inet addr:10.0.0.124 Bcast:10.0.1.255 Mask:255.255.254.0 inet6 addr: fe80::ac7f:44ff:fe57:9f0f/64 Scope:Link UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1 RX packets:5638101 errors:0 dropped:87602 overruns:0 frame:0 TX packets:7535345 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:1000 RX bytes:1896436495 (1.7 GiB) TX bytes:1321880127 (1.2 GiB) KVM Lucid VM: dropped packets number does not increasing continuosly: eth0 Link encap:Ethernet HWaddr 52:54:1c:67:24:89 inet addr:10.0.0.178 Bcast:10.0.1.255 Mask:255.255.254.0 inet6 addr: fe80::5054:1cff:fe67:2489/64 Scope:Link UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1 RX packets:2840 errors:0 dropped:4 overruns:0 frame:0 TX packets:62 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:1000 RX bytes:705953 (705.9 KB) TX bytes:8214 (8.2 KB) Centos 6.2 VM works perfectly Linux ldap11.maramaros.chemaxon.local 2.6.32-220.13.1.el6.x86_64 #1 SMP Tue Apr 17 23:56:34 BST 2012 x86_64 x86_64 x86_64 GNU/Linux eth0 Link encap:Ethernet HWaddr 52:54:AB:93:11:E4 inet addr:10.0.0.155 Bcast:10.0.1.255 Mask:255.255.254.0 inet6 addr: fe80::5054:abff:fe93:11e4/64 Scope:Link UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1 RX packets:345362 errors:0 dropped:0 overruns:0 frame:0 TX packets:917 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:1000 RX bytes:150693942 (143.7 MiB) TX bytes:81938 (80.0 KiB) In KVM machines network setup bridge source is br-eth0. I don't know if this helps.