Packets per Second Limitations in EC2
bluematador.com
Packets per Second Limitations in EC2
1–10 of 44 posts
Re: Packets per Second Limitations in EC2
#2The (undocumented) PPS limitation on EC2 instance types before they added SR-IOV NICs is around 150K PPS. If you had your own full machine — usually the top size of a given instance class, but no guarantee — this would be pretty consistent. But it was a shared resource. This made running memcache clusters really painful on EC2, given that they’d easily get limited by packet throughput before CPU or bandwidth. With modern instance types it’s much better!
Re: Packets per Second Limitations in EC2
#3Amazon also limits DNS queries - probably in a well meaning attempt to prevent DNS amplification attacks from originating within AWS. And I mean DNS queries across their network whether or not they hit Amazon's DNS servers. This is _any_ port 53 UDP traffic.
Re: Packets per Second Limitations in EC2
#4One 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.
Re: Packets per Second Limitations in EC2
#5One 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.
Limits are done on the physical host or the host’s NIC. The TORs are not involved.
Re: Packets per Second Limitations in EC2
#6One 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.
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.
Re: Packets per Second Limitations in EC2
#7One 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.
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.
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.
Re: Packets per Second Limitations in EC2
#8One 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.
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.
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
Re: Packets per Second Limitations in EC2
#9Does anyone know if this applies to the dpdk ENA driver?
Re: Packets per Second Limitations in EC2
#10The (undocumented) PPS limitation on EC2 instance types before they added SR-IOV NICs is around 150K PPS. If you had your own full machine — usually the top size of a given instance class, but no guarantee — this would be pretty consistent. But it was a shared resource. This made running memcache clusters really painful on EC2, given that they’d easily get limited by packet throughput before CPU or bandwidth. With mo…
????
Where are you getting these numbers? For what instance types? For what protocols? This is just wrong.