12-16-2005 07:09 AM - edited 03-03-2019 01:09 AM
Can somebody please explain to me what overrun errors on an interface are and what may cause them? Thanks.
5 minute input rate 3542000 bits/sec, 714 packets/sec
5 minute output rate 1865000 bits/sec, 694 packets/sec
9077339068 packets input, 9161744841831 bytes, 0 no buffer
Received 48704918 broadcasts (46547259 multicast)
0 runts, 0 giants, 0 throttles
0 input errors, 0 CRC, 0 frame, 139716 overrun, 0 ignored
0 watchdog, 0 multicast, 0 pause input
0 input packets with dribble condition detected
7612190579 packets output, 1859866741694 bytes, 0 underruns
0 output errors, 0 collisions, 0 interface resets
0 babbles, 0 late collision, 0 deferred
0 lost carrier, 0 no carrier, 0 PAUSE output
0 output buffer failures, 0 output buffers swapped out
Solved! Go to Solution.
12-16-2005 07:34 AM
The WS-X6548-GE-TX is what is known as a "blocking" card, meaning that the ports are oversubscribed, for this particular card, at a rate of 8:1. In other words, every block of 8 ports shares 1Gb of bandwidth.
Also, this card shares a 1Mb buffer between groups ports (1-8, 9-16, 17-24, 25-32, 33-40, 41-48) since each block of eight ports is 8:1 oversubscribed. If any port in this range is receiving or transmitting traffic at a rate that exceeds its bandwidth or utilizing a large amount of buffers to handle bursts of traffic, the other ports in the same range of 8 may experience packet loss.
There are a couple of ways to address this.
1)Isolate any ports that may be consistently oversubscribed (SPAN destinations, servers with NFS, slower speed than the other ports in the range, etc.) to their own range of 8 ports to minimize the impact of drops to other interfaces.
2)Disable head of line blocking which will utilize the interface buffers instead of the shared buffers. This will result in only the single over utilized port having drops, but since the interface buffers (32k) are significantly smaller than the 1Mb shared buffer, there may be more lost traffic to individual ports. This is only recommended for extreme cases where slower clients or span ports cannot be moved to other line cards that offer dedicated interface buffers
6500(config)#service internal
6500(config)#interface gigabit 1/1
6500(config-if)#hol-blocking disable
%HOL Blocking is Disabled on: Gi1/1 Gi1/2 Gi1/3 Gi1/4 Gi1/5 Gi1/6 Gi1/7 Gi1/8
6500#show hol-blocking module 1
Interface Hol-Blocking
-------------- ---------------
Gi1/1 Disable
Gi1/2 Disable
Gi1/3 Disable
Gi1/4 Disable
Gi1/5 Disable
Gi1/6 Disable
Gi1/7 Disable
Gi1/8 Disable
Once this is disabled, the drops will move to the interface counters and can be seen with 'show interface gigabit
6500#show interface gigabit 1/1
Input queue: 0/2000/0/0 (size/max/drops/flushes); Total output drops: 25542147 <-----------
Additionally, this document may provide some more insight.
Buffers, Queues & Thresholds on Catalyst 6500 Ethernet Modules
http://www.cisco.com/en/US/products/hw/switches/ps708/products_white_paper09186a0080131086.shtml
HTH,
Bobby
12-16-2005 07:20 AM
Overruns are the number of times the receiver hardware was unable to hand received data to a hardware buffer.
This is generally caused by the input rate of traffic exceeding the receiver's ability to handle the data.
What type of module is this? More than likely this is a blocking card who is receiving more data than can be put into the shared buffer. Depending on the type of card, we may be able to mitigate this by spreading the top talkers among different port groups.
This is documented here:
http://www.cisco.com/warp/public/473/53.shtml#overrun
HTH,
Bobby
12-16-2005 07:30 AM
Thanks Bobby,
I'm surprised a Gigabit interface would ever receive more data than it's buffer can process, however I'm no expert. Wouldn't this mean the input rate would have to exceed 1000Mb/s?
Here are my module details:
auto-neg to Full-duplex, 1000Mb/s
!
interface GigabitEthernet4/29
logging event link-status
switchport
switchport access vlan 101
switchport mode access
no cdp enable
spanning-tree portfast
end
Mod Ports Card Type Model Serial No.
--- ----- -------------------------------------- ------------------ -----------
4 48 SFM-capable 48 port 10/100/1000mb RJ45 WS-X6548-GE-TX SAD0835026Z
Mod MAC addresses Hw Fw Sw Status
--- ---------------------------------- ------ ------------ ------------ -------
4 0001.c9df.b802 to 0001.c9df.b831 10.1 7.2(1) 8.3(2.10)TFW Ok
Mod Online Diag Status
--- -------------------
4 Pass
12-16-2005 07:34 AM
The WS-X6548-GE-TX is what is known as a "blocking" card, meaning that the ports are oversubscribed, for this particular card, at a rate of 8:1. In other words, every block of 8 ports shares 1Gb of bandwidth.
Also, this card shares a 1Mb buffer between groups ports (1-8, 9-16, 17-24, 25-32, 33-40, 41-48) since each block of eight ports is 8:1 oversubscribed. If any port in this range is receiving or transmitting traffic at a rate that exceeds its bandwidth or utilizing a large amount of buffers to handle bursts of traffic, the other ports in the same range of 8 may experience packet loss.
There are a couple of ways to address this.
1)Isolate any ports that may be consistently oversubscribed (SPAN destinations, servers with NFS, slower speed than the other ports in the range, etc.) to their own range of 8 ports to minimize the impact of drops to other interfaces.
2)Disable head of line blocking which will utilize the interface buffers instead of the shared buffers. This will result in only the single over utilized port having drops, but since the interface buffers (32k) are significantly smaller than the 1Mb shared buffer, there may be more lost traffic to individual ports. This is only recommended for extreme cases where slower clients or span ports cannot be moved to other line cards that offer dedicated interface buffers
6500(config)#service internal
6500(config)#interface gigabit 1/1
6500(config-if)#hol-blocking disable
%HOL Blocking is Disabled on: Gi1/1 Gi1/2 Gi1/3 Gi1/4 Gi1/5 Gi1/6 Gi1/7 Gi1/8
6500#show hol-blocking module 1
Interface Hol-Blocking
-------------- ---------------
Gi1/1 Disable
Gi1/2 Disable
Gi1/3 Disable
Gi1/4 Disable
Gi1/5 Disable
Gi1/6 Disable
Gi1/7 Disable
Gi1/8 Disable
Once this is disabled, the drops will move to the interface counters and can be seen with 'show interface gigabit
6500#show interface gigabit 1/1
Input queue: 0/2000/0/0 (size/max/drops/flushes); Total output drops: 25542147 <-----------
Additionally, this document may provide some more insight.
Buffers, Queues & Thresholds on Catalyst 6500 Ethernet Modules
http://www.cisco.com/en/US/products/hw/switches/ps708/products_white_paper09186a0080131086.shtml
HTH,
Bobby
12-16-2005 09:07 AM
bobby,
Thanks very much for your extremely informative response.
I do have 1 more question. How would overruns manifest themselves on the application layer? Would users experience slowness? TCP Re-transmissions?
12-16-2005 09:12 AM
Slowness and TCP retransmissions are very likely scenarios that would correlate on the upper layers as a result of this, depending of course, on what type of traffic is being dropped.
12-16-2005 10:18 AM
Thanks again Bobby. Wow you are a wealth of knowledge :)
Wouldn't I see output drops on my interface is packets were in fact being dropped as a result of the overruns? Or do I assume that because I'm seeing overruns there is packet loss?
12-16-2005 10:44 AM
If head-of-line blocking is disabled, you'll use the port level buffers, and then you would see the drops on the interface (example in my longer post above).
However, you can assume that there is packet loss if you are seeing overruns to begin with.
-Bobby
Discover and save your favorite ideas. Come back to expert answers, step-by-step guides, recent topics, and more.
New here? Get started with these tips. How to use Community New member guide