CODEWITHSUNDEEP
amazon-ec2
SimonSikstrom
SimonSikstrom

Reputation: 93

EC2 Instance, sudden network performance cap

Anyone else experienced a sudden network performance cap recently?

Our instances managed to go up to average 100,000,000 bytes average but all of a sudden we're down to 50,000,000 without warning. This happened two days ago at around Oct 16 11:40 UTC.

I'm using a c3.xlarge type instance with network performance moderate, did they lower the cap of the "moderate" performance?

Would be nice to hear if anyone else have this problem since its pretty weird that they would do that without warning, I cant find any information on this.

I've attached screenshot of proof, the instance-type was not changed at that time.

Its the same problem on both Network In and Network Out.

Graph: https://i.sstatic.net/WQ9Sf.png

Upvotes: 2

Views: 341

Answers (1)

datasage
datasage

Reputation: 19573

This is par for the course with shared tenancy. Most instances except for the largest instance sizes, are all on hardware shared with other instances. This means all resources are shared including network bandwidth.

When no other instances are using the bandwidth available to your host, you can generally take advantage of most, if not all of it. If other hosts are attempting to saturate the host bandwidth, then host will schedule your bandwidth based on your network priority.

Moderate does not mean you are guaranteed a certain amount of bandwidth, instead it gives you a certain priority in comparison with the other instances on the host.

What can you do about this? You could stop/start your instance until you get assigned to a host without any noisy neighbors. You could also scale horizontally to give yourself more available bandwidth.

Upvotes: 2

Related Questions