Performance drop on AWS T3 instances - Linux

Question

The issue with performance drop when having just a couple of hundreds of connections might be typical to AWS T3 instances.  Our server-side Apache modules maintain "sleeping" connections to clients, which is not quite typical for regular web applications. Any time a new request come for a host PC, the client's server-side Apache instance wakes up and puts the request's data into a queue for the host PC and signals its server-side Apache instance, which wakes up and sends the data to the host PC. Hence, every data exchange through the server involves quite a few of server processes scheduling. It appears that our T3 starts experiencing lagging of the AWS scheduling at some point, which is not reflected in CPU usage.

Answer

Hello,

The data provided is insufficient to determine the cause. There could be lots of factors to check while dealing with issues with respect to LAG.

When you say LAG, what exactly is observed ? How do you determine that ? How is the connectivity from your Host-PC to the AWS instance ? What tools have you used to determine whether it is latency/compute related ? Have you checked the top, vmstat, iostat, df-kh output to eliminate all the factors that could cause potential issues ? Also, what is the output of netstat - anp ? Have you also tried to upgrade the instance from t3 medium to a higher one ?

Do you have an AWS Support plan ? I believe the AWS engineers would be the best to determine on how to move forward with the same. Hope this helps.

Performance drop on AWS T3 instances - Linux

Contenido relevante