Keynote: Infrastructure - Introduction
summary
Fabric Cloud moves from AWS to bare metal experiments while scaling metrics and ops: a new database user permission manager adds table and column level access and audit logs, snapshot-based backups cut backup time to 45 seconds backup with a bulk restoration test suite, and logical replication is rolling out to reduce large-site downtime. Machine upgrades to 8th gen cut operational cost ~50%, an automated incident manager runs the first 5 minutes of remediation, builds hit ~23,000/month and error rate falls to 1.37% error rate across 10 regions.
AI-written summary · about
chapters (11)
- 0:00Introduction to Fabric Cloud
- 2:27Growth and scaling challenges
- 3:56Team expansion and metrics focus
- 5:43Global infrastructure and cost reduction
- 7:11Database management improvements
- 12:29Database performance and analytics
- 16:02Machine upgrades and cost savings
- 18:55Storage transparency and control
- 20:41Incident automation and detection
- 22:28Build optimization and reliability
- 24:56Future plans and autoscaling
related talks
56mKeynote on Building the Cloud for You
14mKeynote: The Big Leap: Conquering the Legacy System and Building a Scalable Cloud Infra...
14mKeynote: The Big Leap: Conquering the Legacy System and Building a Scalable Cloud...
18mKeynote: Mind the Gap: Bridging Cloud Native Innovation with Real-World Use
28mKeynote: User Panel
19mKeynote: Operating 600+ Mesos Servers on 7 Datacenters @Criteo
20mKeynote: From Weeks to Minutes
14mKeynote: The Cost of Agility at Scale: It's All Fun and Games Until the Bill Comes
