Hacker News new | past | comments | ask | show | jobs | submit login

Is there an architectural change and/or approach to which the boot performance increase(s) can be attributed?

If not, which is understandable, is there something specific to stable/14 for interested parties to familiarize themselves with?




My impression is that cperciva has been working on FreeBSD/EC2 boot times for the last six years, not just specifically some changes in 14.

The most accessible summary of his work is probably on his Patreon: https://www.patreon.com/c/cperciva/posts. If you go digging there are also some anecdotes on his Twitter too; most recent I can find is https://x.com/cperciva/status/1833735559614988526


I gave a talk at BSDCan 2022 about this ("speeding up the FreeBSD boot") -- I'm on my phone right now so I can't provide a link but it's on YouTube.

There's also a somewhat out of date summary of most of the work on the FreeBSD wiki: https://wiki.freebsd.org/BootTime



The best summary I can provide is "profiling and lots of small wins".




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: