i tried a stab and multicasting a FOG image to 4 machines the other day, and i had experienced odd and strange issues.
here is what i encountered:
100% cpu usage on our core switch
core4507#sh processes cpu hist
9999999999999999999999999999999999999999999999999999999999
7777888888888877777888888888888887777788888888888888888887
100 **********************************************************
90 **********************************************************
80 **********************************************************
70 **********************************************************
60 **********************************************************
50 **********************************************************
40 **********************************************************
30 **********************************************************
20 **********************************************************
10 **********************************************************
0....5....1....1....2....2....3....3....4....4....5....5....
0 5 0 5 0 5 0 5 0 5
CPU% per second (last 60 seconds)
the Vlan is in sparse mode
pinging the SVI on the core and or pinging on the core to other devices resulted in MAJOR latencies, packet loss due to the cpu usage, etc....
no other network operations were affected, i could communicate with the rest of the network, and under 1-2ms latencies.
i noticed it due to my opsview server flagging the core as down (SNMP OID's wouldnt return a value)
it lasted the whole time i was multicasting, i kept a close eye on it. i highly considered canceling my job, but everything ran smooth.
when i looked at the cpu sorted history i saw 2 processes, IP Input, and cat4k mgmnt hipri
is there something that could cause this? nothing that was multicasting was on the core itself.
