[Gluster-users] MTU 9000 question

[Dmitry Melekhov]

06.05.2020 19:15, Erik Jacobson пишет:
>> It's been working pretty
>> well at 1500 MTU so far. If the only issue is less throughput, that may
>> be a price we can pay since we're not bandwidth bound right now.
>>

I think that fragmentation offload on nics makes jumbo frames not very 
useful.

As I said we see no difference in our workload, we switched nics to mtu 
9000 just because we can, but not from start,

and we did not see any improvements.

Gluster never saturates our teamed in two 10Gb connections nor with mtu 
9000 nor with 1500 and there is no visible latency difference.