On 8/6/26 9:27 AM, Patrice CHOTARD wrote:
On 8/6/26 02:33, Marek Vasut wrote:
On 8/5/26 9:30 AM, Patrice CHOTARD wrote:
Hello Patrice,
Agree with your analysis, i will send a fix to exit from cyclic_run() in case
the next cyclic timestamp is not reached.
But, in parallel, to gain more reactivity, schedule() can also be moved at the
same level of ctrcl() as this patch is proposing.
Thanks
Patrice
Hi Marek
Is it OK for you to merge this patch ?
Is this series still necessary with the cyclic fixes in place ?
Yes it allows to get an additional reactivity gain.
With the cyclic fixes 9c1b13b3fd27 ("cyclic: reduce get_timer_us() calls inside
hlist_for_each_entry_safe()")
ctrlc() is called every ~280ms
With this patch, ctrlc() is called every ~70ms.
Is there any chance we can optimize the schedule() call further instead?
