It's a complete misunderstanding of what's going on. The way the scheduler switches applications to ensure they all get prioritized equally was built with 8 cores in mind. All cores were always used.
this post was submitted on 14 Nov 2023
1 points (100.0% liked)
Homelab
22 readers
1 users here now
Rules
- Be Civil.
- Post about your homelab, discussion of your homelab, questions you may have, or general discussion about transition your skill from the homelab to the workplace.
- No memes or potato images.
- We love detailed homelab builds, especially network diagrams!
- Report any posts that you feel should be brought to our attention.
- Please no shitposting or blogspam.
- No Referral Linking.
- Keep piracy discussion off of this community
founded 1 year ago
MODERATORS
It's pretty sensible behavior. Things that are desirable on desktop-like multicore systems aren't always desirable on manycore systems.
The ability to thrash on 128 cores is probably not something anyone is missing.
If this had been a real issue, it should have been detected quite a while ago. However as far as I can tell, this limit is reached if one is running very very quick running programs, say if it only takes 5ms to fork and run the program, then one may run into this 8 core issue.
This will basically slow down poorly written shell scripts that constantly runs subprograms - if the subprograms run in parallel (which they are not unless multiple instances of the script are running at the same time). Also it means fork bombs will create processes slower than expected on machines with more then 8 processors. I highly doubt someone would worry about this case.