[c-nsp] cisco buffer misses

Matthew Huff mhuff at ox.com
Thu Apr 18 15:31:22 EDT 2013


Output drops are usually cause by microburst or by larger->smaller aggregation bursts. The drop is a tail-drop caused by buffer overflows during output serialization resulting in tail drops. 

Microburst happen when data is very irregular especially udp based (multicast, ipvtv, etc..) and traffic hits an interface faster it can queue it outbound. Also, when you have larger pipes sending data your way the bandwidth will cause the traffic to "bunch-up" when it hits the lower speed interfaces causing the same thing.

The only solution is to either shape the traffic heading to the device or replace the device/linecard with something that has larger buffers like a Cisco 49xx or Nexus3/4/5k.


----
Matthew Huff             | 1 Manhattanville Rd
Director of Operations   | Purchase, NY 10577
OTA Management LLC       | Phone: 914-460-4039

> -----Original Message-----
> From: cisco-nsp [mailto:cisco-nsp-bounces at puck.nether.net] On Behalf Of Michael Sprouffske
> Sent: Thursday, April 18, 2013 12:40 PM
> To: cisco-nsp at puck.nether.net
> Subject: [c-nsp] cisco buffer misses
> 
> Could someone give me some insight as to what is causing the misses?  I'm currently researching this
> on the inter webs.  I also notice an interface with several drops as well.
> 
> 
> 
> 
> model: WS-C3750X-24T-S
> 
> 
> 
> Buffer elements:
>      1061 in free list (500 max allowed)
>      3479036431 hits, 0 misses, 1024 created
> 
> Public buffer pools:
> Small buffers, 104 bytes (total 50, permanent 50, peak 119 @ 7w0d):
>      49 in free list (20 min, 150 max allowed)
>      1712506149 hits, 23 misses, 69 trims, 69 created
>      0 failures (0 no memory)
> Middle buffers, 600 bytes (total 25, permanent 25, peak 85 @ 7w0d):
>      23 in free list (10 min, 150 max allowed)
>      167702 hits, 58 misses, 174 trims, 174 created
>      0 failures (0 no memory)
> Big buffers, 1536 bytes (total 50, permanent 50, peak 119 @ 7w0d):
>      50 in free list (5 min, 150 max allowed)
>      244703400 hits, 39 misses, 117 trims, 117 created
>      0 failures (0 no memory)
> VeryBig buffers, 4520 bytes (total 16, permanent 10, peak 16 @ 7w0d):
>      0 in free list (0 min, 100 max allowed)
>      59 hits, 3 misses, 1429 trims, 1435 created
>      0 failures (0 no memory)
> Large buffers, 5024 bytes (total 0, permanent 0):
>      0 in free list (0 min, 10 max allowed)
>      0 hits, 0 misses, 0 trims, 0 created
>      0 failures (0 no memory)
> Huge buffers, 18024 bytes (total 4, permanent 0, peak 7 @ 7w0d):
>      4 in free list (0 min, 4 max allowed)
>      145363512 hits, 412449 misses, 822729 trims, 822733 created
>      0 failures (0 no memory)
> 
> 
> 
> 
> GigabitEthernet1/0/11 is up, line protocol is up (connected)
>   Hardware is Gigabit Ethernet, address is 649e.f3e2.7b8b (bia 649e.f3e2.7b8b)
>   Description: server ports
>   MTU 9000 bytes, BW 100000 Kbit, DLY 100 usec,
>      reliability 255/255, txload 1/255, rxload 1/255
>   Encapsulation ARPA, loopback not set
>   Keepalive set (10 sec)
>   Full-duplex, 100Mb/s, media type is 10/100/1000BaseTX
>   input flow-control is off, output flow-control is unsupported
>   ARP type: ARPA, ARP Timeout 04:00:00
>   Last input 00:00:16, output 00:00:01, output hang never
>   Last clearing of "show interface" counters never
>   Input queue: 0/75/0/0 (size/max/drops/flushes); Total output drops: 54011
>   Queueing strategy: fifo
>   Output queue: 0/40 (size/max)
>   5 minute input rate 0 bits/sec, 0 packets/sec
>   5 minute output rate 49000 bits/sec, 28 packets/sec
>      837676 packets input, 118543994 bytes, 0 no buffer
>      Received 492811 broadcasts (481207 multicasts)
>      0 runts, 0 giants, 0 throttles
>      0 input errors, 0 CRC, 0 frame, 0 overrun, 0 ignored
>      0 watchdog, 481207 multicast, 0 pause input
>      0 input packets with dribble condition detected
>      670450255 packets output, 115399962776 bytes, 0 underruns
>      0 output errors, 0 collisions, 1 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
> _______________________________________________
> cisco-nsp mailing list  cisco-nsp at puck.nether.net
> https://puck.nether.net/mailman/listinfo/cisco-nsp
> archive at http://puck.nether.net/pipermail/cisco-nsp/



More information about the cisco-nsp mailing list