Great diagram about the Microservices application architecture at https://blog.bytebytego.com/i/146792961/essential-components-of-a-production-microservice-application
In my opinion, this architecture is also valid for most software these days. Not just microservices but also web applications, distributed monolith and so on. Think Spotify, Netflix, Your bank web application and pretty much everything.
I believe it also deserves some extra discussion about the logs and metric collection.
Pushing logs to Logstash (which seems to be suggested by the direction of the arrows) was the recommended way until a combination of Kubernetes cluster monitoring and Elastic Agent changed the paradigm for good few years ago. Logs are now written by the application running on K8s to local files on the k8s nodes and can be easily collected by Elastic Agents running on each K8s node and pushed directly to Elasticsearch. Logstash has almost become obsolete, except for some very specific use cases. Log aggregation in this way has tremendous benefits for the application since it doesn't need to deal with pushing logs directly to Logstash, retries, or other Logstash failures.
Similar to the point above. Applications expose Prometheus-format metrics at an HTTP endpoint, Prometheus collects those metrics (aka it pulls from that endpoint) and pushes them to its storage.
Actually, Prometheus can be taken out of the picture, as can Logstash, since Elastic Agent can collect Prometheus-format metrics directly from the applications and push them to Elasticsearch.
Why should you trust me on what I said above?
I have worked for 2 years at Elastic in the cloud-native monitoring team,and I have seen countless customers implement that exact pattern.
I'm still at Elastic but in a different department.
In this week's article in my newsletter, Cloud Native Engineer will discuss in detail the log collection in Kubernetes with the Elastic Agent.
Top comments (0)