I cannot seem to ping servers or workstations on my network with a packet size that exceeds anything greater than 20000. Some can go higher than others, and it is not at all consistent. If for instance I use a payload size of 9000, and ping for 10 minutes 80% of the packets go through. If I increase it to 15000, the it goes down to (say) 20% and if I crank it up to 65000 it never goes through.
Even if I stay on the same network segment I cannot go much higher than 30000. If I try to ping my gateway, it has an exact limit size of 17900. I don't know if that is the max a Cisco router will repond to by design or what the deal is there. I am connecting my core server farm switches together via bridge group virtual interfaces, could that have anything to do with it?
I see no interface errors, bandwidth or queue length problems on any of my routers. I see no duplex mismatch problems on the switches. I have tried from numerous stations and get the same thing. I have tried disabling and enabling checksum offloading, updating drivers and forcing duplex and speed on all test stations.
I could really use some help on this one. My wireshark packet captures look pretty much fine, with the expection of occasional big delays (770ms) during a conversation, and packets arriving out of order that are fixed with SACK. No window sizing clamping down to near nothing- nothing that would indicate a massive problem. The only symption is users complaining about long lag periods in their apps.
See example here:
C:\Users\BertnErnie>ping 10.102.1.31 -t -l 19000
Pinging 10.102.1.31 with 19000 bytes of data:
Request timed out.
Request timed out.
Reply from 10.102.1.31: bytes=19000 time=7ms TTL=127
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Reply from 10.102.1.31: bytes=19000 time=8ms TTL=127
Request timed out.
Request timed out.
Request timed out.
Reply from 10.102.1.31: bytes=19000 time=9ms TTL=127
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Request timed out.
Ping statistics for 10.102.1.31:
Packets: Sent = 31, Received = 3, Lost = 28 (90% loss),
Approximate round trip times in milli-seconds:
Minimum = 7ms, Maximum = 9ms, Average = 8ms
It doesn't make any difference if I extend the timeout period.
Can someone please help me understand why this is happening? I have verified all router interfaces between segments
