Afternoon all. Trying to figure out an issue I am having with a specific server group. These are all part of a target group, running docker and a micro python service. These are all running Amazon EC2 AMI instances, and there is nothing scheduled on the cron except 2 jobs around 11:45pm only.
The issue is we have a lot of traffic on these and every hour for about 5-10 seconds there is a huge spike in latency on the requests. When these were running on the t3.small series (in testing), the spike was very noticeable, I thought I saw a process 'aws' while watching TOP, but we have moved into production, now running on m6a.xlarges and where the spike/latency is still there and seen in the response time logs, I don't really see anything in TOP (I am assuming with the extra horsepower it goes too quickly).
So if anyone has thoughts or ideas on how to see what this is, it would be appreciated as we may not be able to fix it but if we at least know the issue it will be better, we just know the more and bigger CPU's, the less impact it has.
Thanks all.
AWS OFICIALAtualizada há 10 meses