26 November 2018

Operational Excellence with Containerized Workloads using AWS Fargate (CON320)

by mo


This session will focus on how leveraging Fargate and its serverless approach to deploying and managing container will help increase operational efficiencies and reduce the time to ramp up your operations to run production containerized workloads. Datree will share their journey to adopt container and the steps they were able to accelerate and avoid by using Fargate as well do a demo.

You can stream application logs to Cloudwatch and then use awslogs to perform grep like operations against the raw logs and filter by specific time periods like:

$ awslogs get /var/log/rails ip-10-1.* --start='2h ago' | grep ERROR

You can run a trace across your services using xray. This allows you to do a distributed trace across services. xray

With Fargate you can run containers without managing servers. You can specify thresholds so that containers are spun up and down automatically based on your workload.

  1. build an image
  2. push image to docker registry
  3. configure aws fargate to pull from registry and configure thresholds
  4. profit!

Spinnaker support is coming soon.

You can also use AWS CodeBuild in place of jenkins or a CI tool. This makes it easier to build a full deployment pipeline using AWS services directly.

Naming scheme:

  • service.region.env.domain

E.g.

shiro.us-east-1.production.example.org

Resources:

devops