Re: [RFC v2] timers: Don't wake ktimersoftd on every tick

[Haris Okanovic]

On 02/03/2017 10:51 AM, Sebastian Andrzej Siewior wrote:
> On 2016-12-13 15:44:05 [-0600], Haris Okanovic wrote:
> > Changed the way timers are collected per Julia and Thomas'
> > recommendation: Expired timers are now collected in interrupt context
> > and fired in ktimersoftd to avoid double-walk of `pending_map`.
> â
> > Thanks,
> > Haris
>
> I've been staring at it for a while now and now I applied it locally and
> look how it goes.
> I would need that patch signed as per
> 	https://kernel.org/doc/html/latest/process/submitting-patches.html#sign-your-work-the-developer-s-certificate-of-origin
> if you want it applied.

Sent a proper PATCH email with sign-off.

Built and booted with both CONFIG_HZ_PERIODIC=y and CONFIG_NO_HZ_IDLE=y 
configurations (100 HZ). Ran short cyclictest to verify numbers.

> > ---
> >  kernel/time/timer.c | 97 ++++++++++++++++++++++++++++++++++++-----------------
> >  1 file changed, 67 insertions(+), 30 deletions(-)
>
> Sebastian