From: Vincent Guittot <vincent.guittot@linaro.org>
To: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>,
Juri Lelli <juri.lelli@redhat.com>,
Ricardo Neri <ricardo.neri@intel.com>,
"Ravi V. Shankar" <ravi.v.shankar@intel.com>,
Ben Segall <bsegall@google.com>,
Daniel Bristot de Oliveira <bristot@redhat.com>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Len Brown <len.brown@intel.com>, Mel Gorman <mgorman@suse.de>,
"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
Steven Rostedt <rostedt@goodmis.org>,
Tim Chen <tim.c.chen@linux.intel.com>,
Valentin Schneider <vschneid@redhat.com>,
Lukasz Luba <lukasz.luba@arm.com>,
Ionela Voinescu <ionela.voinescu@arm.com>,
x86@kernel.org,
"Joel Fernandes (Google)" <joel@joelfernandes.org>,
linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org,
"Tim C . Chen" <tim.c.chen@intel.com>
Subject: Re: [PATCH v3 10/24] sched/fair: Use IPCC scores to select a busiest runqueue
Date: Fri, 31 Mar 2023 14:23:58 +0200 [thread overview]
Message-ID: <CAKfTPtCUVbiVJxRHx_AcXbfm-SeW1ATE8QZ-jOqyfMh+PLwAjw@mail.gmail.com> (raw)
In-Reply-To: <20230330021431.GB26315@ranerica-svr.sc.intel.com>
On Thu, 30 Mar 2023 at 04:03, Ricardo Neri
<ricardo.neri-calderon@linux.intel.com> wrote:
>
> On Tue, Mar 28, 2023 at 12:03:58PM +0200, Vincent Guittot wrote:
> > On Tue, 7 Feb 2023 at 06:01, Ricardo Neri
> > <ricardo.neri-calderon@linux.intel.com> wrote:
> > >
> > > For two runqueues of equal priority and equal number of running of tasks,
> > > select the one whose current task would have the highest IPC class score
> > > if placed on the destination CPU.
> >
> > You failed to explain why it make sense to compare current task score
> > whereas we will most probably not pull this task at the end
>
> Thank you for your feedback Vincent! Please kindly refer to my reply to
> your feedback in patch 7.
>
> > >
> > > For now, use IPCC scores only for scheduling domains with the
> > > SD_ASYM_PACKING flag.
> > >
> > > Cc: Ben Segall <bsegall@google.com>
> > > Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
> > > Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
> > > Cc: Ionela Voinescu <ionela.voinescu@arm.com>
> > > Cc: Joel Fernandes (Google) <joel@joelfernandes.org>
> > > Cc: Len Brown <len.brown@intel.com>
> > > Cc: Lukasz Luba <lukasz.luba@arm.com>
> > > Cc: Mel Gorman <mgorman@suse.de>
> > > Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
> > > Cc: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
> > > Cc: Steven Rostedt <rostedt@goodmis.org>
> > > Cc: Tim C. Chen <tim.c.chen@intel.com>
> > > Cc: Valentin Schneider <vschneid@redhat.com>
> > > Cc: x86@kernel.org
> > > Cc: linux-pm@vger.kernel.org
> > > Cc: linux-kernel@vger.kernel.org
> > > Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
> > > ---
> > > Changes since v2:
> > > * Only use IPCC scores to break ties if the sched domain uses
> > > asym_packing. (Ionela)
> > > * Handle errors of arch_get_ipcc_score(). (Ionela)
> > >
> > > Changes since v1:
> > > * Fixed a bug when selecting a busiest runqueue: when comparing two
> > > runqueues with equal nr_running, we must compute the IPCC score delta
> > > of both.
> > > * Renamed local variables to improve the layout of the code block.
> > > (PeterZ)
> > > * Used the new interface names.
> > > ---
> > > kernel/sched/fair.c | 64 +++++++++++++++++++++++++++++++++++++++++++++
> > > 1 file changed, 64 insertions(+)
> > >
> > > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > > index 72d88270b320..d3c22dc145f7 100644
> > > --- a/kernel/sched/fair.c
> > > +++ b/kernel/sched/fair.c
> > > @@ -9399,6 +9399,37 @@ static bool sched_asym_ipcc_pick(struct sched_group *a,
> > > return sched_asym_ipcc_prefer(a_stats, b_stats);
> > > }
> > >
> > > +/**
> > > + * ipcc_score_delta - Get the IPCC score delta wrt the load balance's dst_cpu
> > > + * @p: A task
> > > + * @env: Load balancing environment
> > > + *
> > > + * Returns: The IPCC score delta that @p would get if placed in the destination
> > > + * CPU of @env. LONG_MIN to indicate that the delta should not be used.
> > > + */
> > > +static long ipcc_score_delta(struct task_struct *p, struct lb_env *env)
> > > +{
> > > + unsigned long score_src, score_dst;
> > > + unsigned short ipcc = p->ipcc;
> > > +
> > > + if (!sched_ipcc_enabled())
> > > + return LONG_MIN;
> > > +
> > > + /* Only asym_packing uses IPCC scores at the moment. */
> > > + if (!(env->sd->flags & SD_ASYM_PACKING))
> > > + return LONG_MIN;
> > > +
> > > + score_dst = arch_get_ipcc_score(ipcc, env->dst_cpu);
> > > + if (IS_ERR_VALUE(score_dst))
> > > + return LONG_MIN;
> > > +
> > > + score_src = arch_get_ipcc_score(ipcc, task_cpu(p));
> > > + if (IS_ERR_VALUE(score_src))
> > > + return LONG_MIN;
> > > +
> > > + return score_dst - score_src;
> > > +}
> > > +
> > > #else /* CONFIG_IPC_CLASSES */
> > > static void update_sg_lb_ipcc_stats(int dst_cpu, struct sg_lb_stats *sgs,
> > > struct rq *rq)
> > > @@ -9429,6 +9460,11 @@ static bool sched_asym_ipcc_pick(struct sched_group *a,
> > > return false;
> > > }
> > >
> > > +static long ipcc_score_delta(struct task_struct *p, struct lb_env *env)
> > > +{
> > > + return LONG_MIN;
> > > +}
> > > +
> > > #endif /* CONFIG_IPC_CLASSES */
> > >
> > > /**
> > > @@ -10589,6 +10625,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
> > > {
> > > struct rq *busiest = NULL, *rq;
> > > unsigned long busiest_util = 0, busiest_load = 0, busiest_capacity = 1;
> > > + long busiest_ipcc_delta = LONG_MIN;
> > > unsigned int busiest_nr = 0;
> > > int i;
> > >
> > > @@ -10705,8 +10742,35 @@ static struct rq *find_busiest_queue(struct lb_env *env,
> > >
> > > case migrate_task:
> > > if (busiest_nr < nr_running) {
> > > + struct task_struct *curr;
> > > +
> > > busiest_nr = nr_running;
> > > busiest = rq;
> > > +
> > > + /*
> > > + * Remember the IPCC score delta of busiest::curr.
> > > + * We may need it to break a tie with other queues
> > > + * with equal nr_running.
> > > + */
> > > + curr = rcu_dereference(busiest->curr);
> > > + busiest_ipcc_delta = ipcc_score_delta(curr, env);
> >
> > Hmm, i don't like this at all
> >
> > Also, curr is the least probable task to be pulled which means that
> > all this his useless
>
> but when doing asym_packing balancing nr_running = 1, need_active_balance()
> returns true and we will pull the current task, no? This is also true for
> fully_busy groups with one task per CPU. These are the only two cases that
> currently use IPCC scores.
hmm, for sure it's not true for fully_busy and I don't see anything
about asym_packing mandating that nr_running = 1
You should have a look at misfit task which seems to better fit your
situation where you have one task that doesn't fit its cpu instead of
adding such condition
>
> If there are more than one tasks in the runqueue, the group will be
> classified as overloaded and we will not use IPCC scores nor active
> balance.
>
> Thanks and BR,
> Ricardo
next prev parent reply other threads:[~2023-03-31 12:24 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-02-07 5:10 [PATCH v3 00/24] sched: Introduce classes of tasks for load balance Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 01/24] sched/task_struct: Introduce IPC classes of tasks Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 02/24] sched: Add interfaces for IPC classes Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 03/24] sched/core: Initialize the IPC class of a new task Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 04/24] sched/core: Add user_tick as argument to scheduler_tick() Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 05/24] sched/core: Update the IPC class of the current task Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 06/24] sched/fair: Collect load-balancing stats for IPC classes Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 07/24] sched/fair: Compute IPC class scores for load balancing Ricardo Neri
2023-03-28 10:00 ` Vincent Guittot
2023-03-30 2:07 ` Ricardo Neri
2023-03-31 12:20 ` Vincent Guittot
2023-04-17 22:52 ` Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 08/24] sched/fair: Use IPCC stats to break ties between asym_packing sched groups Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 09/24] sched/fair: Use IPCC stats to break ties between fully_busy SMT groups Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 10/24] sched/fair: Use IPCC scores to select a busiest runqueue Ricardo Neri
2023-03-28 10:03 ` Vincent Guittot
2023-03-30 2:14 ` Ricardo Neri
2023-03-31 12:23 ` Vincent Guittot [this message]
2023-04-17 23:01 ` Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 11/24] thermal: intel: hfi: Introduce Intel Thread Director classes Ricardo Neri
2023-03-27 16:31 ` Rafael J. Wysocki
2023-03-28 23:42 ` Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 12/24] x86/cpufeatures: Add the Intel Thread Director feature definitions Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 13/24] thermal: intel: hfi: Store per-CPU IPCC scores Ricardo Neri
2023-03-27 16:37 ` Rafael J. Wysocki
2023-03-28 23:43 ` Ricardo Neri
2023-03-29 12:08 ` Rafael J. Wysocki
2023-03-30 2:15 ` Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 14/24] thermal: intel: hfi: Update the IPC class of the current task Ricardo Neri
2023-03-27 16:42 ` Rafael J. Wysocki
2023-03-28 23:41 ` Ricardo Neri
2023-03-29 12:13 ` Rafael J. Wysocki
2023-03-30 3:06 ` Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 15/24] thermal: intel: hfi: Report the IPC class score of a CPU Ricardo Neri
2023-03-27 16:50 ` Rafael J. Wysocki
2023-03-28 23:41 ` Ricardo Neri
2023-03-29 12:17 ` Rafael J. Wysocki
2023-03-31 2:07 ` Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 16/24] thermal: intel: hfi: Define a default class for unclassified tasks Ricardo Neri
2023-03-27 16:51 ` Rafael J. Wysocki
2023-03-28 23:49 ` Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 17/24] thermal: intel: hfi: Enable the Intel Thread Director Ricardo Neri
2023-03-27 16:53 ` Rafael J. Wysocki
2023-03-28 23:50 ` Ricardo Neri
2023-02-07 5:10 ` [PATCH v3 18/24] sched/task_struct: Add helpers for IPC classification Ricardo Neri
2023-02-07 5:11 ` [PATCH v3 19/24] sched/core: Initialize helpers of task classification Ricardo Neri
2023-02-07 5:11 ` [PATCH v3 20/24] sched/fair: Introduce sched_smt_siblings_idle() Ricardo Neri
2023-02-07 5:11 ` [PATCH v3 21/24] thermal: intel: hfi: Implement model-specific checks for task classification Ricardo Neri
2023-03-27 17:03 ` Rafael J. Wysocki
2023-03-29 0:15 ` Ricardo Neri
2023-03-29 12:21 ` Rafael J. Wysocki
2023-03-30 2:41 ` Ricardo Neri
2023-03-31 17:08 ` Rafael J. Wysocki
2023-04-03 14:12 ` Ricardo Neri
2023-02-07 5:11 ` [PATCH v3 22/24] x86/cpufeatures: Add feature bit for HRESET Ricardo Neri
2023-02-07 5:11 ` [PATCH v3 23/24] x86/hreset: Configure history reset Ricardo Neri
2023-02-07 5:11 ` [PATCH v3 24/24] x86/process: Reset hardware history in context switch Ricardo Neri
2023-03-05 22:49 ` [PATCH v3 00/24] sched: Introduce classes of tasks for load balance Ricardo Neri
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=CAKfTPtCUVbiVJxRHx_AcXbfm-SeW1ATE8QZ-jOqyfMh+PLwAjw@mail.gmail.com \
--to=vincent.guittot@linaro.org \
--cc=bristot@redhat.com \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=ionela.voinescu@arm.com \
--cc=joel@joelfernandes.org \
--cc=juri.lelli@redhat.com \
--cc=len.brown@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=lukasz.luba@arm.com \
--cc=mgorman@suse.de \
--cc=peterz@infradead.org \
--cc=rafael.j.wysocki@intel.com \
--cc=ravi.v.shankar@intel.com \
--cc=ricardo.neri-calderon@linux.intel.com \
--cc=ricardo.neri@intel.com \
--cc=rostedt@goodmis.org \
--cc=srinivas.pandruvada@linux.intel.com \
--cc=tim.c.chen@intel.com \
--cc=tim.c.chen@linux.intel.com \
--cc=vschneid@redhat.com \
--cc=x86@kernel.org \
/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;
as well as URLs for NNTP newsgroup(s).