What is the smallest AWS EC2 instance I can run a postgres db on?

Question

There is the free tier on AWS and I can get a micro EC2 instance for free essentially.. or close to.. I'm sure setting up elastic ips - loads balancers etc is extra.

Would it effectively be possible for me to run a postgres DB - for a small api. Roughly about 50 inserts + 50 reads per second... say about 6000 operations per min at the most.

I can't seem to find anything online - which makes me think that this might be a silly idea.

For this not to be an "open question" - it's simply: Is it possible and realistic to expect usable performance on an EC2 instance running my postgres DB.

Answer 1

The best way to determine whether the database can handle a particular workload is to test it at that capacity. Launch the database, simulate traffic and monitor its performance. Please note that every application uses a database differently, so nobody can provide "general advice" as to whether a particular-sized database would meet the needs of your particular application.

If you are going to run 'production' workloads, try to avoid using the Burstable performance instances (T2, T3) since they can hit limits under heavy workloads unless the 'Unlimited' option is selected. T2/T3 is great for bursty workloads, but not for sustained workloads.

Comparing m5.xlarge between EC2 and RDS:

• Amazon EC2: 19.2c/hr ($4.61/day)
• Amazon RDS: 35.6c/hr ($8.54/day)

For the additional price, Amazon RDS provides a fully-managed database, automated backups, CloudWatch metrics, etc. This is probably worth much more than $4 of your time every day.

Alternatively, if you can modify your application to use NoSQL instead of SQL, you could use Amazon DynamoDB where the capacity you mention would cost 4c/hour ($1/day) plus request and storage costs.

Don't underspend on your database — it powers everything you do. Instead, try to save money by turning off non-production systems when they aren't being used (eg weekends and evenings). That will hopefully give you enough savings to afford an appropriately-powered database.