mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Dan Schatzberg <schatzberg.dan@gmail.com>
To: Tejun Heo <tj@kernel.org>
Cc: David Vernet <void@manifault.com>,
	Andrea Righi <andrea.righi@linux.dev>,
	Changwoo Min <changwoo@igalia.com>,
	Emil Tsalapatis <etsal@meta.com>,
	sched-ext@lists.linux.dev, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 02/13] sched_ext: Make slice values tunable and use shorter slice in bypass mode
Date: Tue, 11 Nov 2025 09:57:46 -0500	[thread overview]
Message-ID: <aRNO6j5B4RDugKfJ@dschatzberg-fedora-PF3DHTBV> (raw)
In-Reply-To: <20251109183112.2412147-3-tj@kernel.org>

On Sun, Nov 09, 2025 at 08:31:01AM -1000, Tejun Heo wrote:
> @@ -919,7 +948,7 @@ static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta)
>  
>  static void refill_task_slice_dfl(struct scx_sched *sch, struct task_struct *p)
>  {
> -	p->scx.slice = SCX_SLICE_DFL;
> +	p->scx.slice = scx_slice_dfl;

Do you need to use READ_ONCE here given that this can be modified concurrently?

>  	__scx_add_event(sch, SCX_EV_REFILL_SLICE_DFL, 1);
>  }
>  
> @@ -2892,7 +2921,7 @@ void init_scx_entity(struct sched_ext_entity *scx)
>  	INIT_LIST_HEAD(&scx->runnable_node);
>  	scx->runnable_at = jiffies;
>  	scx->ddsp_dsq_id = SCX_DSQ_INVALID;
> -	scx->slice = SCX_SLICE_DFL;
> +	scx->slice = scx_slice_dfl;
>  }
>  
>  void scx_pre_fork(struct task_struct *p)
> @@ -3770,6 +3799,7 @@ static void scx_bypass(bool bypass)
>  		WARN_ON_ONCE(scx_bypass_depth <= 0);
>  		if (scx_bypass_depth != 1)
>  			goto unlock;
> +		scx_slice_dfl = scx_slice_bypass_us * NSEC_PER_USEC;

Similarly WRITE_ONCE here

>  		bypass_timestamp = ktime_get_ns();
>  		if (sch)
>  			scx_add_event(sch, SCX_EV_BYPASS_ACTIVATE, 1);
> @@ -3778,6 +3808,7 @@ static void scx_bypass(bool bypass)
>  		WARN_ON_ONCE(scx_bypass_depth < 0);
>  		if (scx_bypass_depth != 0)
>  			goto unlock;
> +		scx_slice_dfl = scx_slice_dfl_us * NSEC_PER_USEC;

And here

>  		if (sch)
>  			scx_add_event(sch, SCX_EV_BYPASS_DURATION,
>  				      ktime_get_ns() - bypass_timestamp);
> @@ -4776,7 +4807,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
>  			queue_flags |= DEQUEUE_CLASS;
>  
>  		scoped_guard (sched_change, p, queue_flags) {
> -			p->scx.slice = SCX_SLICE_DFL;
> +			p->scx.slice = scx_slice_dfl;

And here
>  			p->sched_class = new_class;
>  		}
>  	}
> -- 
> 2.51.1
> 

  parent reply	other threads:[~2025-11-11 14:57 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-09 18:30 [PATCHSET sched_ext/for-6.19] sched_ext: Improve bypass mode scalability Tejun Heo
2025-11-09 18:31 ` [PATCH 01/13] sched_ext: Don't set ddsp_dsq_id during select_cpu in bypass mode Tejun Heo
2025-11-10  6:57   ` Andrea Righi
2025-11-10 16:08     ` Tejun Heo
2025-11-09 18:31 ` [PATCH 02/13] sched_ext: Make slice values tunable and use shorter slice " Tejun Heo
2025-11-10  7:03   ` Andrea Righi
2025-11-10  7:59     ` Andrea Righi
2025-11-10 16:21     ` Tejun Heo
2025-11-10 16:22       ` Tejun Heo
2025-11-10  8:22   ` Andrea Righi
2025-11-11 14:57   ` Dan Schatzberg [this message]
2025-11-09 18:31 ` [PATCH 03/13] sched_ext: Refactor do_enqueue_task() local and global DSQ paths Tejun Heo
2025-11-10  7:21   ` Andrea Righi
2025-11-09 18:31 ` [PATCH 04/13] sched_ext: Use per-CPU DSQs instead of per-node global DSQs in bypass mode Tejun Heo
2025-11-10  7:42   ` Andrea Righi
2025-11-10 16:42     ` Tejun Heo
2025-11-10 17:30       ` Andrea Righi
2025-11-11 15:31   ` Dan Schatzberg
2025-11-09 18:31 ` [PATCH 05/13] sched_ext: Simplify breather mechanism with scx_aborting flag Tejun Heo
2025-11-10  7:45   ` Andrea Righi
2025-11-11 15:34   ` Dan Schatzberg
2025-11-09 18:31 ` [PATCH 06/13] sched_ext: Exit dispatch and move operations immediately when aborting Tejun Heo
2025-11-10  8:20   ` Andrea Righi
2025-11-10 18:51     ` Tejun Heo
2025-11-11 15:46   ` Dan Schatzberg
2025-11-09 18:31 ` [PATCH 07/13] sched_ext: Make scx_exit() and scx_vexit() return bool Tejun Heo
2025-11-10  8:28   ` Andrea Righi
2025-11-11 15:48   ` Dan Schatzberg
2025-11-09 18:31 ` [PATCH 08/13] sched_ext: Refactor lockup handlers into handle_lockup() Tejun Heo
2025-11-10  8:29   ` Andrea Righi
2025-11-11 15:49   ` Dan Schatzberg
2025-11-09 18:31 ` [PATCH 09/13] sched_ext: Make handle_lockup() propagate scx_verror() result Tejun Heo
2025-11-10  8:29   ` Andrea Righi
2025-11-09 18:31 ` [PATCH 10/13] sched_ext: Hook up hardlockup detector Tejun Heo
2025-11-10  8:31   ` Andrea Righi
2025-11-09 18:31 ` [PATCH 11/13] sched_ext: Add scx_cpu0 example scheduler Tejun Heo
2025-11-10  8:36   ` Andrea Righi
2025-11-10 18:44     ` Tejun Heo
2025-11-10 21:06       ` Andrea Righi
2025-11-10 22:08         ` Tejun Heo
2025-11-09 18:31 ` [PATCH 12/13] sched_ext: Factor out scx_dsq_list_node cursor initialization into INIT_DSQ_LIST_CURSOR Tejun Heo
2025-11-10  8:37   ` Andrea Righi
2025-11-09 18:31 ` [PATCH 13/13] sched_ext: Implement load balancer for bypass mode Tejun Heo
2025-11-10  9:38   ` Andrea Righi
2025-11-10 19:21     ` Tejun Heo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=aRNO6j5B4RDugKfJ@dschatzberg-fedora-PF3DHTBV \
    --to=schatzberg.dan@gmail.com \
    --cc=andrea.righi@linux.dev \
    --cc=changwoo@igalia.com \
    --cc=etsal@meta.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=sched-ext@lists.linux.dev \
    --cc=tj@kernel.org \
    --cc=void@manifault.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®