|
Question : High processor utilisation on Cisco 3750 stack
|
|
Hi Experts,
I have an issue that I could do with some help on. I am working on a stack of 2 3750 switches, connected via their Stackwise interfaces. They in turn connect to 5 2950 switches via dual gigabit Ethernet links, configured as port channels. There are a number of VLANs which are configured such that half of the ports on the 2950s are in each VLAN, and the servers are configured on another VLAN to which the gigabit ports of the 3750s belong. Inter VLAN routing is configured to get the traffic between the VLANs.
I am experiencing high processor utilisation on the 3750s, mostly against the IP Input process. I have done some research and it seems that the switching algorithm may not be the most efficient. Attached is some show ip interface output to show how each VLAN is configured, and some output showing the process usage. I would appreciate any comments on improving the routing performance between VLANs - I am making the sweeping assumption in all this that the 3750s are capable of routing this amount of traffic without breaking a sweat when configured correctly.
CORESW#sh ip int Vlan1 is up, line protocol is up Internet protocol processing disabled Vlan2 is up, line protocol is up Internet address is x.x.x.x/24 Broadcast address is 255.255.255.255 Address determined by setup command MTU is 1500 bytes Helper address is not set Directed broadcast forwarding is disabled Multicast reserved groups joined: 224.0.0.10 Outgoing access list is not set Inbound access list is not set Proxy ARP is enabled Local Proxy ARP is disabled Security level is default Split horizon is enabled ICMP redirects are always sent ICMP unreachables are always sent ICMP mask replies are never sent IP fast switching is enabled IP CEF switching is enabled IP CEF switching turbo vector IP multicast fast switching is disabled IP multicast distributed fast switching is disabled IP route-cache flags are Fast, CEF Router Discovery is disabled IP output packet accounting is disabled IP access violation accounting is disabled TCP/IP header compression is disabled RTP/IP header compression is disabled Probe proxy name replies are disabled Policy routing is disabled Network address translation is enabled, interface in domain outside WCCP Redirect outbound is disabled WCCP Redirect inbound is disabled WCCP Redirect exclude is disabled BGP Policy Mapping is disabled Input features: NAT Outside Output features: Post-routing NAT Outside Vlan3 is up, line protocol is up Internet address is y.y.y.y/24 Broadcast address is 255.255.255.255 Address determined by setup command MTU is 1500 bytes Helper address is x.x.x.1 Directed broadcast forwarding is disabled Multicast reserved groups joined: 224.0.0.10 Outgoing access list is not set Inbound access list is not set Proxy ARP is enabled Local Proxy ARP is disabled Security level is default Split horizon is enabled ICMP redirects are always sent ICMP unreachables are always sent ICMP mask replies are never sent IP fast switching is enabled IP CEF switching is enabled IP CEF switching turbo vector IP multicast fast switching is disabled IP multicast distributed fast switching is disabled IP route-cache flags are Fast, CEF Router Discovery is disabled IP output packet accounting is disabled IP access violation accounting is disabled TCP/IP header compression is disabled RTP/IP header compression is disabled Probe proxy name replies are disabled Policy routing is disabled Network address translation is enabled, interface in domain outside WCCP Redirect outbound is disabled WCCP Redirect inbound is disabled WCCP Redirect exclude is disabled BGP Policy Mapping is disabled Input features: NAT Outside Output features: Post-routing NAT Outside
Process output:
PID Runtime(ms) Invoked uSecs 5Sec 1Min 5Min TTY Process ----------------------------------------------------------------------------------------------------- 159 805309277 1180331872 682 44.65% 55.05% 49.99% 0 IP Input
Thanks in advance.
George
|
Answer : High processor utilisation on Cisco 3750 stack
|
|
Forgot to get back with a result on this one.
The process decided by ourselves and Cisco support was to restart the switches first, then try a bunch of hardware diagnostics and looking at the CPU buffers etc. to see whether switched packets were still being sent via the CPU.
First step, restart the switches. Lo and behold, problem ceased! This was a month ago adn the problem hasn't reoccured. Teh cisco tech found this surprising and suspected a hw fault, but in the absence of a recurrence, it may just have to be accepted as one of those inexplicable faults. Frustrating, but seems to be the case.
|
|
|
|