Re: CPU affinity behavior of liburcu call-rcu per-cpu worker threads

On 2026-07-10 14:57, Paul E. McKenney wrote:
> On Fri, Jul 10, 2026 at 12:17:39AM -0400, Mathieu Desnoyers wrote:

[...]

>> The "simpler" option would be to implement the rseq extension tcmalloc
>> need, so they can finally stop doing their odd games and become
>> compatible with the rest of the world. But the last time I offered to
>> help them on this front I've been told that they would not even have
>> time to try my patches.
>>
>> Oh well.
> 
> I bet that there is a way, but thus far I at least add a load and a branch
> to those fastpaths.  Maybe convince someone to submit the needed patches
> to tcmalloc() and then browbeat the tcmalloc() folks into accepting them?
> You would need someone young, energetic, and obnoxious, which lets me
> off on two of the three.  ;-)

Olivier !

Can I interest you in a rseq system call extension and tcmalloc
contribution ? ;-)

Thanks,

Mathieu

-- 
Mathieu Desnoyers
EfficiOS Inc.
https://www.efficios.com