Background: I have a long running API call (.5 to 1 sec) and I created a node app with cluster for each of the CPU cores that I have. It all works fine. I plan on putting the app behind an AWS load-balancer with auto-scale, but this lead to my buffering question:When I do a small load-test, either the OS network stack or the node master process (or both) are queuing network requests, which is good as there are no timeouts or errors (small loadtest, didn't try to overwhelm it). But, I wanted to get an understanding of how this works and what to watch out for, so I can best setup the ELB/load balancer.I am using a mac for development and Linux on AWS for testing.thx!
Submitted December 15, 2016 at 03:01AM by okiloggedin
No comments:
Post a Comment