[ramshanker]

One thing I was looking for the entire article weather these limitations are imposed by the Instance or the TOR networking gear.

Maybe random reallocation to a rack with newer switches will guarantee better baseline PPS.

[rbranson]

It has to do with hardware support for virtualized networking. Instances capable of SR-IOV or with the ENA can sustain millions of PPS. It makes a huge difference.

[ra1n85]

Not correct. Instances are rate limited based on their type and protocol. Enhanced networking support increases total potential performance, but there are artificial limitations put in place.

[dkhenry]

They can sustain millions of PPS, but they still get artificially limited, no matter how many ENI's you seem to attach a given instance will top out at around the same amount of PPS

[ra1n85]

Limits are done on the physical host or the host’s NIC. The TORs are not involved.