[c-nsp] High CPU util on Cat4506

[Jee Kay]

I've got (very) high CPU util on one of my Cat4506s (SupIV running
12.2(20)EW1). I have a strong suspicion that it is being caused by the
switch doing a bit of multicast forwarding (~20-30Mb/s).

I've gone through the Output Interpreter/Performance Tuning tips (ip
mroute-cache was already enabled) but can't find anything that
actually reduces the CPU usage.

The output of sh int switching/ sh int stats for the SVIs are:

#sh int vl410 stats
Vlan410
             Switch path    Pkts In   Chars In   Pkts Out  Chars Out
               Processor          0          0          0          0
             Route cache          0          0          0          0
                Hardware  106282027 22256087017   29334501 1394430880
                   Total  106282027 22256087017   29334501 1394430880

#do sh int vl410 switching
Vlan410
          Throttle count          0
        Drops         RP          0         SP          0
  SPD Flushes       Fast          0        SSE          0
  SPD Aggress       Fast          0
 SPD Priority     Inputs          0      Drops          0

     Protocol       Path    Pkts In   Chars In   Pkts Out  Chars Out
           IP    Process    1415199   88026932    1162606   72449768
            Cache misses          0
                    Fast          0          0          0          0
               Auton/SSE          0          0          0          0
          ARP    Process       2056     123360         27       1620
            Cache misses          0
                    Fast          0          0          0          0
               Auton/SSE          0          0          0          0


interface Vlan410
 ip address 1.1.1.2 255.255.255.240
 ip pim dr-priority 100
 ip pim query-interval 5
 ip pim sparse-mode
 ip igmp query-max-response-time 3
 ip igmp query-interval 10
 standby 1 ip 1.1.1.1
 standby 1 timers msec 300 1


Does anyone have any ideas how to further diagnose this / what to
enable to make the multicast packets go through a fast switching path?
I've had considerably more than 20-30Mb/s of multicast through this
class of switch before without running into any problem this extreme,
but I can't seem to spot what is missing.

Thanks,
Ras