To s tím HT jen pro stejný proces taky není tak úplně jednoduché, přímo od Raadt:
"Let's say you just run threads of the same program, so they have the same address space. One of the threads does a system call, so it is now running in the kernel. In a subtle way, the rule has just been broken."
To sa síce dá jednoducho a elegantne riešiť, ale bude to stáť kopu výkonu.
V RTLinuxPro delili CPU/jadrá na jadrá pre Realtime a non=reltime úlohy., Tu by mohli byť jadrá na ktorých beží len kernel a jadrá na ktorých beží len userspace. A teda pri prepínaní ringu by sa vlákno presunulo na iné jadro, Aj keď si uvedomujem cenu na výkone, bezpečnosť by to zvýšilo...
RTLinuxPro CPU reservation technology
May 7, 2004
http://linuxdevices.io/rtlinuxpro-cpu-reservation-technology/
Aby nedošlo k nedorozumeniu
Uvedomujem si, že v mojom riešení bude "skákať krava"
4 March 2013
There's also a scheduler patch to fix a "bouncing cow" problem by when running fewer processes on the system than number of processor cores, the process could be bounced around between cores and yield poor performance. This bouncing cow fix for the scheduler yields a performance boost by 15x in a worst-case scenario. More work will come to future Linux kernel releases.
https://www.phoronix.com/scan.php?page=news_item&px=MTMxNzA
February 20, 2013
https://lwn.net/Articles/538101/
Aneb neco co ma treba NetBSD a mel to davno Solaris nebo HP-UX? http://netbsd.gw.com/cgi-bin/man-cgi?psrset+8