Jumbo frames configured though dell devices will not respond to a mtu size set for more than 8976

  • 0
  • 1
  • Question
  • Updated 1 year ago
  • Answered
Jumbo fames enabled for L2 and L3.

If I ping between two extreme switches with an MTU of 9000 , I get an appropriate response, basically it works as expected.

ping vr "VR-Default" start-size 9000 10.2.7.1

Ping(ICMP) 10.2.7.1: 4 packets, 9000 data bytes, interval 1 second(s).

9008 bytes from 10.2.7.1: icmp_seq=0 ttl=64 time=7.777 ms

9008 bytes from 10.2.7.1: icmp_seq=1 ttl=64 time=3.028 ms

9008 bytes from 10.2.7.1: icmp_seq=2 ttl=64 time=1.771 ms

9008 bytes from 10.2.7.1: icmp_seq=3 ttl=64 time=2.984 ms

If I ping from the switch to a dell server , the max mtu size I can achieve is :

# ping vr "VR-CS-SERVER" start-size 8976 10.2.6.5

Ping(ICMP) 10.2.6.5: 4 packets, 8976 data bytes, interval 1 second(s).

8984 bytes from 10.2.6.5: icmp_seq=0 ttl=64 time=0.487 ms

8984 bytes from 10.2.6.5: icmp_seq=1 ttl=64 time=0.470 ms

8984 bytes from 10.2.6.5: icmp_seq=2 ttl=64 time=2.732 ms

8984 bytes from 10.2.6.5: icmp_seq=3 ttl=64 time=2.656 ms

 FAILS AT :
ping vr "VR-CS-SERVER" start-size 8977 10.2.6.5
Ping(ICMP) 10.2.6.5: 4 packets, 8977 data bytes, interval 1 second(s).

--- 10.2.6.5 ping statistics ---
4 packets transmitted, 0 packets received, 100% loss
round-trip min/avg/max = 0/0/0 ms

IS this a limitation on Jumbo frames ?
Am I missing some overhead that is added to teh ping ?

Any help would be appreciated 
Photo of Rod Robertson

Rod Robertson

  • 2,344 Points 2k badge 2x thumb

Posted 1 year ago

  • 0
  • 1
Photo of David Choi

David Choi, Employee

  • 1,966 Points 1k badge 2x thumb
Hi Rod,

Have you checked the MTU size of the Dell server port?
It looks like the Dell server can support up to 8976 MTU size or it is configured with 8976 MTU size, so it can't reply with 8977 packet size as it exceeds the maximum size.
Photo of Rod Robertson

Rod Robertson

  • 2,344 Points 2k badge 2x thumb


From the customer :

I have change the storage device (10.2.6.6) to 9000 and when we ping –s9000 from the server (10.2.6.8) to the storage it does fail thus:

 

# vmkping -d -I vmk1 -s 9000 10.2.6.6

PING 10.2.6.6 (10.2.6.6): 9000 data bytes

sendto() failed (Message too long)

sendto() failed (Message too long)

sendto() failed (Message too long)

 

However there might be a simple explanation for this.

 

This link http://rickardnobel.se/troubleshoot-jumbo-frames-with-vmkping/ provides the answers. Basically when we do a ping test we should do a test with –s 8972 to allow for the overheads in the  ping command itself.

 

So this works a treat:

# vmkping -d -I vmk1 -s 8972 10.2.6.6

PING 10.2.6.6 (10.2.6.6): 8972 data bytes

8980 bytes from 10.2.6.6: icmp_seq=0 ttl=64 time=0.151 ms

8980 bytes from 10.2.6.6: icmp_seq=1 ttl=64 time=0.133 ms

8980 bytes from 10.2.6.6: icmp_seq=2 ttl=64 time=0.135 ms


This seems to have working in this scenario 


Something to lookout for in the future.