failed deployment recovery time
The time it takes to recover from a deployment that fails and needs immediate intervention in production.
In more detail
It replaced mean time to restore in 2023 because the old metric counted every outage, including ones no change caused. It needs one fact the pipeline does not know by itself: when the incident began.
Example
failed deployment recovery time 556 minutes (median)Related terms
- DORA metrics — Five measures of software delivery from the DORA research: change lead time, deployment frequency, failed deployment recovery time, change fail rate and deployment rework rate.
- mean time to restore — The older DORA stability metric: the average time to restore service after any production incident.
- incident — An unplanned event that degrades or interrupts a service for its users, or harms the security of systems or data.
- rollback — Returning a system to a previous known-good version after a bad change.
- fix forward — Recovering from a bad change by quickly shipping a new fix, instead of going back to the previous version.
Taught in
- DORA Metrics: Measuring Your Pipeline — Continuous Integration & Continuous Delivery Pipelines
- Feature Flags and DORA Metrics — Continuous Integration & Continuous Delivery Pipelines
- What DevOps Actually Is — DevOps & Site Reliability Engineering
- Throughput: Change Lead Time And Deployment Frequency — DevOps & Site Reliability Engineering
- Restoration: Failed Deployment Recovery Time — DevOps & Site Reliability Engineering
- The Four Keys History And Retiring MTTR — DevOps & Site Reliability Engineering