Re: [PATCH v4 2/6] sched_ext: Implement scx_rq_clock_update/stale()

[Changwoo Min <changwoo@igalia.com>]

Hello Andrea,

Thank you for the review.

On 24. 12. 9. 18:40, Andrea Righi wrote:
>> @@ -766,9 +767,11 @@ struct scx_rq {
>>   	unsigned long		ops_qseq;
>>   	u64			extra_enq_flags;	/* see move_task_to_local_dsq() */
>>   	u32			nr_running;
>> -	u32			flags;
>>   	u32			cpuperf_target;		/* [0, SCHED_CAPACITY_SCALE] */
>>   	bool			cpu_released;
>> +	u32			flags;
>> +	u64			clock;			/* current per-rq clock -- see scx_bpf_now_ns() */
>> +	u64			prev_clock;		/* previous per-rq clock -- see scx_bpf_now_ns() */
> 
> Since we're reordering this struct, we may want to move cpu_released all
> the way to the bottom to get rid of the 3-bytes hole (and still have
> flags, clock and prev_clock in the same cacheline).

We'd better keep the layout as it is. That is because moving
cpu_released to the end of the struct creates 4-byte hole between
flags and clock and 7-byte padding at the end after cpu_released.
I double-checked the two layouts using pahole.


> Nit, this is just personal preference (feel free to ignore it):
> 
> 	if (!scx_enabled())
> 		return;
> 	rq->scx.prev_clock = rq->scx.clock;
> 	rq->scx.clock = clock;
> 	rq->scx.flags |= SCX_RQ_CLK_VALID;
> 
That's prettier. I will change it as you suggested.


> I'm wondering if we need to invalidate the clock on all rqs when we call
> scx_ops_enable() to prevent getting stale information from a previous
> scx scheduler.
> 
> Probably it's not an issue, since scx_ops_disable_workfn() should make
> sure that all tasks are going through rq_unpin_lock() before unloading
> the current scheduler, maybe it could be helpful to add comment about
> this scenario in scx_bpf_now_ns() (PATCH 4/6)?

That's a good catch. In theory, there is a possibility that
a scx_rq is not invalidated when unloading the sched_ext. Since
scx_ops_disable_workfn() iterates all the sched_ext tasks, an rq
would not be invalidated if there is no scx task on the rq.
I will add the code which iterates and invalidates all scx_rqs at
scx_ops_disable_workfn() in the next version.

Thank you again!
Changwoo Min