- Newest
- Most votes
- Most comments
What instance size are you using? If you are using Instances which have more than 4 cores - this comes with a feature called Enhanced IO enabled by default - which improves throughput by upto 83% and upto 47% reduction in latency with no application code changes required.
Additional details can be found in this Blog - https://aws.amazon.com/blogs/database/boosting-application-performance-and-reducing-costs-with-amazon-elasticache-for-redis/
There are a few other changes that can improve overall latencies but that could involve looking at the metrics.
Unfortunately, there's no beating the speed of light. As you've seen, using Global Accelerator can make a difference but it isn't going to reduce latency enough for some users - because they are just further away.
Adding a read-only replica in a region closer to the users is a good idea; but that does mean that writes have to go back to the read/write replica (assuming you want synchronous writes) or you could have some process in the region local to the users that accept asynchronous write requests. Either way means a change in your application architecture.
Relevant content
- Accepted Answerasked a year ago
- asked 4 months ago
- asked a year ago
- AWS OFFICIALUpdated 2 years ago
- AWS OFFICIALUpdated 7 months ago
- AWS OFFICIALUpdated 10 months ago
- AWS OFFICIALUpdated a year ago
At the moment it's a r6a.xlarge. You do have a point. I did see that in the docs. I will spin up a new server and do some testing and return with my findings.