Velocity Culture
summary
Amazon moves all amazon.com traffic onto EC2 and turned off the last physical web server Nov 10 2010, allowing fleet size to scale in single-server increments and cutting typical-week capacity waste from about 40% and enabling a November capacity optimization that claims up to 75% savings. An internal system Apollo launches continuous production deploys every 11.6 seconds on average, with ~10,000 hosts receiving deployments simultaneously and peaks near 30,000, driving a 75% drop in deployment-caused outages and 90% fewer outage minutes.
AI-written summary · about
chapters (4)
- 0:00The state of operations
- 3:02Scaling down for efficiency
- 8:39Scaling up for deployment
- 14:16Call to action for Ops
related talks
17mDeployments We Can Believe In
31mDevOps in the Cloud: Case Studies of Amazon.com teams and their resilient architectures
44mThe Amazon Software Development Process
28mHarness cloud elasticity by bursting to Amazon EC2 Spot
21mHow you can scale up with Amazon EC2 for up to 90% less
36mPractical Cloud Native: What Works, What Doesn't
21mDevOps Culture at Amazon
30mLeaping from Mainframes to AWS: Technology Time Travel in the Government