Hey everyone! We're a group of undergraduate engineering students working on our final year project, which involves hosting our AI backend on AWS. To evaluate our project's scalability, we need to manage around 25 users simultaneously. We're considering creating about 15 g5.xlarge EC2 instances for this purpose over the course of 5 to 8 hours. However, since this is a relatively new AWS account, we're unsure if we can spin up that many instances without hitting any limits. Can anyone share insights on whether we need to request any quota increases, and what the process entails? If you've been in a similar situation, your advice would be greatly appreciated!
1 Answer
Typically, you won't be able to launch that many g5.xlarge instances on a new AWS account since it usually starts with a zero quota for GPU-based EC2 instances. First, check out the vCPU count for the g5.xlarge instances – AWS quotas are based on vCPUs. Head over to your AWS dashboard, navigate to the 'Service Quota' section, and look for 'EC2 Instances' under 'On-Demand Instances'. You might find your quota is set to 0, which means you can't launch any g5 instances. If that's the case, you'll need to request an increase for the number of vCPUs needed. When making the request, it's helpful to explain what you’re doing and why you need that specific increase. Be aware that these requests often go through human review and can take several days to process, so it's best to start this as soon as possible! Good luck!
I submitted my quota increase request a month ago for G-type instances and it was approved in just 30 minutes! I’ve only had one timely bill too, so I'm wondering if I should be okay getting my request through in the next 10 days?