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

Yes, we know that OpenBSD is famous for ignoring performance. A syscall for every tiny malloc, where in normal systems the threshold is 128K.



Except it doesn't use a syscall for every malloc. That would be crazy. It's a conventional block allocator.


Not sure why you are getting downvoted.

IIRC, OpenBSD is slightly more sophisticated than issuing one syscall per call to malloc(3) and friends. Just slightly, but still. ;-)

Still, I do not like expressing disagreement by downvoting. Sorry about that.


Yeah, I was a bit wrong. It does a syscall for every 4K. Normal systems use a slow syscall only for malloc > 128K. I see no other advantage than extremism in security, and giving a damn about performance.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

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

Search: