Intel Posts Big Linux Patch Set For "Classes of Tasks" On Hybrid CPUs, Thread Director

[arQon]

Linux actually has RLIMIT_NICE which could support this, but most distro just set it to 0...

Thanks, but I'm already painfully aware of this, because I have use cases (especially on Pi-tier HW) where I need renice to, you know, *actually work properly*.

Developers and users have a right to expect their OS to behave in a sane manner. Being unable to reset the priority of a process to the same priority it was started with is unquestionably *not* sane, and it prohibits several key use cases from being possible at all, let alone readily viable. The suggestion that every distro should have to work around it just to arrive at a correctly-functional system is, by definition, an indicator that the behavior is fundamentally broken.

Which it is, though like I say it was for "good" reasons at the time, since the alternative was an exploit. What we ideally need though is for the bug to be fixed properly, so that the exploit stays gone but the rest of the behavior becomes correct. The "cost" of that though is an extra int in the process struct, so instead we got this terrible hack.

[NobodyXu]

Thanks, but I'm already painfully aware of this, because I have use cases (especially on Pi-tier HW) where I need renice to, you know, *actually work properly*.

Developers and users have a right to expect their OS to behave in a sane manner. Being unable to reset the priority of a process to the same priority it was started with is unquestionably *not* sane, and it prohibits several key use cases from being possible at all, let alone readily viable. The suggestion that every distro should have to work around it just to arrive at a correctly-functional system is, by definition, an indicator that the behavior is fundamentally broken.

Which it is, though like I say it was for "good" reasons at the time, since the alternative was an exploit. What we ideally need though is for the bug to be fixed properly, so that the exploit stays gone but the rest of the behavior becomes correct. The "cost" of that though is an extra int in the process struct, so instead we got this terrible hack.

Yes I think having a hard upper limit for nice (default to 0) is probably a good fix, but it seems nobody is motivated to submit a patch for it.

[arQon]

Yes I think having a hard upper limit for nice (default to 0) is probably a good fix, but it seems nobody is motivated to submit a patch for it.

IIRC the idea was shot down for the reason I mentioned, so there was no point to anyone providing one. It was a very long time ago though, and I don't trust my memory for anything that far back - these things tend to blur together as time goes by.

[birdie]

If there's *excessive* pain, find a decent pain specialist and investigate a CRPS diagnosis immediately. The success rate for treatment drops sharply after ~3 months, and continues to plummet after that. Since it's literally the worst pain known to man you very much do not want to end up there, and early intervention is crucial if you develop it.

I've received highly conflicting advice from ten different surgeons/orthopedists, so I've no bloody clue what to do It's been almost a month since the accident and I just try not to walk at all if possible. The pain has subdued but it's extremely painful to walk like a normal person and I often wake up at night because people are rolling all the time when we're sleeping and I guess I do something to my leg in the process.

If you really know the stuff, please email me at aros at gmx dot com. I have MRI scans.

I happen to live in Russia, a country with one of the worst health care systems in the world unless you're very rich in which case you can ... go outside and seek help elsewhere, e.g. in Germany, Israel, USA or even India.