elijah-roberts opened a new issue, #6794: URL: https://github.com/apache/incubator-devlake/issues/6794
## Question Current state it appears that deployment frequency DORA benchmarks may be outdated. Question: Should we update benchmarks to match 2023 report? The 2023 DevOps report indicates that high performing teams deploy "Between once per day and once per week". Currently dashboards indicate that a high performing team is "Between once per week and once per month" These are the instances I found referencing the outdated benchmark. https://github.com/search?q=repo%3Aapache%2Fincubator-devlake+%22Between+once+per+week+and+once+per+month%22&type=code ## Screenshots 2020 Report: https://cloud.google.com/blog/products/devops-sre/using-the-four-keys-to-measure-your-devops-performance <img width="865" alt="image" src="https://github.com/apache/incubator-devlake/assets/19742213/d8602b37-d2b1-40c8-934f-8b6b0b3094de";> 2023 Report: <img width="577" alt="image" src="https://github.com/apache/incubator-devlake/assets/19742213/a3cc5e68-ccbf-4e42-ba24-81327278534f";> ## Additional context [2023_final_report_sodr.pdf](https://github.com/apache/incubator-devlake/files/13907628/2023_final_report_sodr.pdf) Summary of changes: Certainly! Here's a comparison table highlighting the changes between the 2020 and 2023 DevOps reports: | Performance Level | Deployment Frequency (2020) | Deployment Frequency (2023) | Lead Time for Changes (2020) | Lead Time for Changes (2023) | Change Failure Rate (2020) | Change Failure Rate (2023) | Time to Restore Service (2020) | Time to Restore Service (2023) | |---------------------|-----------------------------|-----------------------------|-----------------------------|-----------------------------|---------------------------|---------------------------|-------------------------------|-------------------------------| | Elite | On-demand | On demand | Less than one day | Less than one day | 0%-15% | 5% | Less than one hour | Less than one hour | | High | Between once per week and per month | Between once per day and per week | Between one day and one week | Between one day and one week | 16%-30% | 10% | Less than one day | Less than one day | | Medium | Between once per month and per 6 months | Between once per week and per month | Between one month and six months | Between one week and one month | 16%-30% | 15% | Between one day and one week | Between one day and one week | | Low | Fewer than once per six months | Between once per week and per month | More than six months | Between one week and one month | 16%-30% | 64% | More than six months | Between one month and six months | Key Changes: 1. **Deployment Frequency:** - High: Shifted from "Between once per week and per month" to "Between once per day and per week." - Medium: Shifted from "Between once per month and per 6 months" to "Between once per week and per month." - Low: Shifted from "Fewer than once per six months" to "Between once per week and per month." 2. **Lead Time for Changes:** - Medium: Shifted from "Between one month and 6 months" to "Between one week and one month" - Low: Shifted from "More than six months" to "Between one week and one month" 3. **Change Failure Rate:** - Elite: Reduced from 0%-15% to 5%. - High: Reduced from 16%-30% to 10%. - Medium: Reduced from 16%-30% to 15%. - Low: Significant increase from 16%-30% to 64%. 4. **Time to Restore Service:** - Low: Decrease from "More than six months" to "Between one month and six months." -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
