Re: task_non_contending() for fair_server leads to timer retries

[Bjørn Mork]

Juri Lelli <juri.lelli@xxxxxxxxxx> writes:
> On 15/07/25 16:39, markus.stockhausen@xxxxxx wrote:
>> Hi Peter,
>> 
>> I'm currently investigating issues with the timer-rtl-otto driver in 
>> 6.12 longterm on the Realtek MIPS switch platform (Chris is working
>> hard to upstream this). While doing so I observed that timer retries 
>> continually increase (~6/second) according to /proc/timer_list. The 
>> system is otherwise totally idle. 6.6 longterm does not show that issue.
>> I'm unsure if this is related but documentation reads like "that's bad". 
>> 
>> To be sure about this one I nailed it down to the fair server.
>
> Apologies for interjecting before Peter had a chance to reply, but I had
> a first look and I wonder if this recent patch from Peter (on
> tip/sched/core atm) can already help with the issue, as it should
> reduce the number of dl-server dequeues:
>
> cccb45d7c4295 ("sched/deadline: Less agressive dl_server handling")
>
> Can you please check what you see with it?

Spot on.  Thanks
 
I tested cccb45d7c4295 ("sched/deadline: Less agressive dl_server
handling") on top of the 6.12 longterm we're running and the retries
rate is back to "normal".


Bjørn