[External] : Re: [PATCH v14 4/6] locking/qspinlock: Introduce starvation avoidance into CNA

Alex Kogan alex.kogan at oracle.com
Wed Apr 14 03:30:41 BST 2021



> On Apr 13, 2021, at 5:22 PM, Andi Kleen <ak at linux.intel.com> wrote:
> 
>>> ms granularity seems very coarse grained for this. Surely
>>> at some point of spinning you can afford a ktime_get? But ok.
>> We are reading time when we are at the head of the (main) queue, but
>> don’t have the lock yet. Not sure about the latency of ktime_get(), but
>> anything reasonably fast but not necessarily precise should work.
> 
> Actually cpu_clock / sched_clock (see my other email). These should
> be fast without corner cases and also monotonic.
I see, thanks.

> 
>> 
>>> Could you turn that into a moduleparm which can be changed at runtime?
>>> Would be strange to have to reboot just to play with this parameter
>> Yes, good suggestion, thanks.
>> 
>>> This would also make the code a lot shorter I guess.
>> So you don’t think we need the command-line parameter, just the module_param?
> 
> module_params can be changed at the command line too, so yes.
Got it, thanks again.

— Alex




More information about the linux-arm-kernel mailing list