Re: [PATCH v2] sched/core: Introduce SM_IDLE and an idle re-entry fast-path in __schedule()

[K Prateek Nayak <kprateek.nayak@amd.com>]

Hello Vincent,

On 9/4/2024 12:54 PM, Vincent Guittot wrote:
> On Fri, 9 Aug 2024 at 11:22, K Prateek Nayak <kprateek.nayak@amd.com> wrote:
>>
>> From: Peter Zijlstra <peterz@infradead.org>
>>
>> Since commit b2a02fc43a1f ("smp: Optimize
>> send_call_function_single_ipi()") an idle CPU in TIF_POLLING_NRFLAG mode
>> can be pulled out of idle by setting TIF_NEED_RESCHED flag to service an
>> IPI without actually sending an interrupt. Even in cases where the IPI
>> handler does not queue a task on the idle CPU, do_idle() will call
>> __schedule() since need_resched() returns true in these cases.
>>
>> Introduce and use SM_IDLE to identify call to __schedule() from
>> schedule_idle() and shorten the idle re-entry time by skipping
>> pick_next_task() when nr_running is 0 and the previous task is the idle
>> task.
>>
>> With the SM_IDLE fast-path, the time taken to complete a fixed set of
>> IPIs using ipistorm improves noticeably. Following are the numbers
>> from a dual socket Intel Ice Lake Xeon server (2 x 32C/64T) and
>> 3rd Generation AMD EPYC system (2 x 64C/128T) (boost on, C2 disabled)
>> running ipistorm between CPU8 and CPU16:
>>
>> cmdline: insmod ipistorm.ko numipi=100000 single=1 offset=8 cpulist=8 wait=1
>>
>>     ==================================================================
>>     Test          : ipistorm (modified)
>>     Units         : Normalized runtime
>>     Interpretation: Lower is better
>>     Statistic     : AMean
>>     ======================= Intel Ice Lake Xeon ======================
>>     kernel:                              time [pct imp]
>>     tip:sched/core                       1.00 [baseline]
>>     tip:sched/core + SM_IDLE             0.80 [20.51%]
>>     ==================== 3rd Generation AMD EPYC =====================
>>     kernel:                              time [pct imp]
>>     tip:sched/core                       1.00 [baseline]
>>     tip:sched/core + SM_IDLE             0.90 [10.17%]
>>     ==================================================================
>>
>>
>> [ kprateek: Commit message, SM_RTLOCK_WAIT fix ]
>>
>> Link: https://lore.kernel.org/lkml/20240615012814.GP8774@noisy.programming.kicks-ass.net/
>> Not-yet-signed-off-by: Peter Zijlstra <peterz@infradead.org>
>> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
> 
> Acked-by: Vincent Guittot <vincent.guittot@linaro.org>

Thank you for the ack.

> 
>> ---
>> v1..v2:
>>
>> - Fixed SM_RTLOCK_WAIT being considered as preemption for task state
>>    change on PREEMPT_RT kernels. Since (sched_mode & SM_MASK_PREEMPT) was
>>    used in a couple of places, I decided to reuse the preempt variable.
>>    (Vincent, Peter)
>>
>> - Seperated this patch from the newidle_balance() fixes series since
>>    there are PREEMPT_RT bits that requires deeper review whereas this is
>>    an independent enhancement on its own.
> 
> What is the status of the other part of v1 patchset to run idle load
> balance instead of newly idle load balance ?

Just posted the series out to LKML. You can find it here
https://lore.kernel.org/lkml/20240904111223.1035-1-kprateek.nayak@amd.com/

Sorry for the delay and thank you again for the review.

-- 
Thanks and Regards,
Prateek

> 
>>
>> [..snip..]
>>