mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: K Prateek Nayak <kprateek.nayak@amd.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Juri Lelli <juri.lelli@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Valentin Schneider <vschneid@redhat.com>,
	"Ben Segall" <bsegall@google.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	"Andy Lutomirski" <luto@kernel.org>,
	<linux-kernel@vger.kernel.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Mel Gorman <mgorman@suse.de>,
	"Sebastian Andrzej Siewior" <bigeasy@linutronix.de>,
	Clark Williams <clrkwllms@kernel.org>,
	<linux-rt-devel@lists.linux.dev>, Tejun Heo <tj@kernel.org>,
	"Frederic Weisbecker" <frederic@kernel.org>,
	Barret Rhoden <brho@google.com>, "Petr Mladek" <pmladek@suse.com>,
	Josh Don <joshdon@google.com>, Qais Yousef <qyousef@layalina.io>,
	"Paul E. McKenney" <paulmck@kernel.org>,
	David Vernet <dvernet@meta.com>,
	K Prateek Nayak <kprateek.nayak@amd.com>,
	"Gautham R. Shenoy" <gautham.shenoy@amd.com>,
	Swapnil Sapkal <swapnil.sapkal@amd.com>
Subject: [RFC PATCH 22/22] [DEBUG] sched/fair: Debug pick_eevdf() returning NULL!
Date: Thu, 20 Feb 2025 09:32:57 +0000	[thread overview]
Message-ID: <20250220093257.9380-23-kprateek.nayak@amd.com> (raw)
In-Reply-To: <20250220093257.9380-1-kprateek.nayak@amd.com>

Dump the stats of cfs_rq and the entities queued on it when pick_eevdf()
fails to find a runnable entity. Take the panic that follows since this
scenario implies breakdown of the scheduling algorithm.

XXX: This will only build with CONFIG_CFS_BANDWIDTH enabled.

Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
---
 kernel/sched/fair.c | 75 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 75 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 97566a043398..270e5f4b2741 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5610,6 +5610,78 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags);
 
+static void debug_print_se(int cpu, struct sched_entity *se, bool h_throttled)
+{
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+	pr_warn("CPU%d: se: load(%lu) vruntime(%lld) entity_key(%lld) deadline(%lld) min_vruntime(%lld) on_rq(%d)\n", cpu, scale_load_down(se->load.weight), se->vruntime, entity_key(cfs_rq, se), se->deadline, se->min.vruntime, se->on_rq);
+	pr_warn("CPU%d: se kcs: kernel_cs_count(%d) min_kcs_vruntime(%lld) pick_entity(%d)\n", cpu, se->kernel_cs_count, se->min.kcs_vruntime, pick_entity(cfs_rq, se, h_throttled));
+}
+
+static void debug_print_cfs_rq(int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se, bool h_throttled)
+{
+	pr_warn("CPU%d: ----- cfs_rq ----\n", cpu);
+	pr_warn("CPU%d: cfs_rq: throttled?(%d) cfs_rq->throttled(%d) h_nr_queued(%d) h_nr_runnable(%d) nr_queued(%d) gse->kernel_cs_count(%d)\n", cpu, h_throttled, cfs_rq->throttled, cfs_rq->h_nr_queued, cfs_rq->h_nr_runnable, cfs_rq->nr_queued, (se)? se->kernel_cs_count: -1);
+	pr_warn("CPU%d: cfs_rq EEVDF: avg_vruntime(%lld) avg_load(%lld) avg_kcs_vruntime(%lld) avg_kcs_load(%lld) \n", cpu, cfs_rq->avg_vruntime, cfs_rq->avg_load, cfs_rq->avg_kcs_vruntime, cfs_rq->avg_kcs_load);
+
+	if (cfs_rq->curr) {
+		pr_warn("CPU%d: ----- cfs_rq->curr ----\n", cpu);
+		debug_print_se(cpu, cfs_rq->curr, h_throttled);
+	}
+	pr_warn("CPU%d: ----- cfs_rq done ----\n", cpu);
+}
+
+static void debug_recursive(int cpu, struct rb_node *node, bool h_throttled)
+{
+	debug_print_se(cpu, __node_2_se(node), h_throttled);
+
+	if (node->rb_left) {
+		pr_warn("CPU%d: ----- Left Subtree ----\n", cpu);
+		debug_recursive(cpu, node->rb_left, h_throttled);
+		pr_warn("CPU%d: ----- Left Subtree Done ----\n", cpu);
+	}
+
+	if (node->rb_right) {
+		pr_warn("CPU%d: ----- Right Subtree ----\n", cpu);
+		debug_recursive(cpu, node->rb_right, h_throttled);
+		pr_warn("CPU%d: ----- Right Subtree Done ----\n", cpu);
+	}
+}
+
+static void debug_pick_next_entity(struct cfs_rq *cfs_rq, bool h_throttled)
+{
+	struct sched_entity *se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
+	struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
+	struct task_struct *p = rq_of(cfs_rq)->curr;
+	int cpu = smp_processor_id();
+
+	if (p) {
+		pr_warn("CPU%d: ----- current task ----\n", cpu);
+		pr_warn("CPU%d: pid(%d) comm(%s) task_cpu(%d) task_on_rq_queued(%d) task_on_rq_migrating(%d) normal_policy(%d) idle_policy(%d)\n", cpu, p->pid, p->comm, task_cpu(p), task_on_rq_queued(p), task_on_rq_migrating(p), normal_policy(p->policy), idle_policy(p->policy));
+		pr_warn("CPU%d: ----- current task done ----\n", cpu);
+	}
+
+	debug_print_cfs_rq(cpu, cfs_rq, se, h_throttled);
+
+	if (node) {
+		pr_warn("CPU%d: ----- rbtree traversal: root ----\n", cpu);
+		debug_recursive(cpu, node, h_throttled);
+		pr_warn("CPU%d: ----- rbtree done ----\n", cpu);
+	}
+
+	cfs_rq = cfs_rq_of(se);
+	se = parent_entity(se);
+
+	for_each_sched_entity(se) {
+		pr_warn("CPU%d: ----- parent cfs_rq ----\n", cpu);
+		debug_print_cfs_rq(cpu, cfs_rq, se, h_throttled);
+
+		cfs_rq = cfs_rq_of(se);
+	}
+
+	debug_print_cfs_rq(cpu, cfs_rq, NULL, false);
+}
+
 /*
  * Pick the next process, keeping these things in mind, in this order:
  * 1) keep things fair between processes/task groups
@@ -5633,6 +5705,9 @@ pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq, bool h_throttled)
 	}
 
 	se = pick_eevdf(cfs_rq, h_throttled);
+	if (!se)
+		debug_pick_next_entity(cfs_rq, h_throttled);
+
 	if (se->sched_delayed) {
 		dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
 		/*
-- 
2.43.0


  parent reply	other threads:[~2025-02-20  9:41 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-02-20  9:32 [RFC PATCH 00/22] sched/fair: Defer CFS throttling to exit to user mode K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 01/22] kernel/entry/common: Move syscall_enter_from_user_mode_work() out of header K Prateek Nayak
2025-02-20 10:43   ` Peter Zijlstra
2025-02-20 10:56     ` K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 02/22] sched/fair: Convert "se->runnable_weight" to unsigned int and pack the struct K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 03/22] [PoC] kernel/entry/common: Mark syscall as a kernel critical section K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 04/22] [PoC] kernel/sched: Inititalize "kernel_cs_count" for new tasks K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 05/22] sched/fair: Track EEVDF stats for entities preempted in kernel mode K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 06/22] sched/fair: Propagate the min_vruntime of kernel mode preempted entity K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 07/22] sched/fair: Propagate preempted entity information up cgroup hierarchy K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 08/22] sched/fair: Allow pick_eevdf() to pick in-kernel entities on throttled hierarchy K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 09/22] sched/fair: Introduce cfs_rq throttled states in preparation for partial throttling K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 10/22] sched/fair: Prepare throttle_cfs_rq() to allow " K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 11/22] sched/fair: Prepare unthrottle_cfs_rq() to demote throttle status K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 12/22] sched/fair: Prepare bandwidth distribution to unthrottle partial throttles right away K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 13/22] sched/fair: Correct the throttle status supplied to pick_eevdf() K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 14/22] sched/fair: Mark a task if it was picked on a partially throttled hierarchy K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 15/22] sched/fair: Call resched_curr() from sched_notify_syscall_exit() K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 16/22] sched/fair: Prepare enqueue to partially unthrottle cfs_rq K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 17/22] sched/fair: Clear pick on throttled indicator when task leave fair class K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 18/22] sched/fair: Prepare pick_next_task_fair() to unthrottle a throttled hierarchy K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 19/22] sched/fair: Ignore in-kernel indicators for running task outside of schedule() K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 20/22] sched/fair: Implement determine_throttle_state() for partial throttle K Prateek Nayak
2025-02-20  9:32 ` [RFC PATCH 21/22] [MAYBE BUGFIX] sched/fair: Group all the se->min_* members together for propagation K Prateek Nayak
2025-02-20  9:32 ` K Prateek Nayak [this message]
2025-02-20 10:55 ` [RFC PATCH 00/22] sched/fair: Defer CFS throttling to exit to user mode Peter Zijlstra
2025-02-20 11:18   ` K Prateek Nayak
2025-02-20 11:32     ` Peter Zijlstra
2025-02-20 12:04       ` K Prateek Nayak
2025-02-21  2:04         ` Josh Don
2025-02-21  3:37           ` K Prateek Nayak
2025-02-21 19:42             ` Josh Don
2025-02-20 15:40       ` Valentin Schneider
2025-02-20 16:58         ` K Prateek Nayak
2025-02-21  1:47         ` Josh Don
2025-02-25 21:13           ` Valentin Schneider

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=20250220093257.9380-23-kprateek.nayak@amd.com \
    --to=kprateek.nayak@amd.com \
    --cc=bigeasy@linutronix.de \
    --cc=brho@google.com \
    --cc=bsegall@google.com \
    --cc=clrkwllms@kernel.org \
    --cc=dietmar.eggemann@arm.com \
    --cc=dvernet@meta.com \
    --cc=frederic@kernel.org \
    --cc=gautham.shenoy@amd.com \
    --cc=joshdon@google.com \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rt-devel@lists.linux.dev \
    --cc=luto@kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=paulmck@kernel.org \
    --cc=peterz@infradead.org \
    --cc=pmladek@suse.com \
    --cc=qyousef@layalina.io \
    --cc=rostedt@goodmis.org \
    --cc=swapnil.sapkal@amd.com \
    --cc=tglx@linutronix.de \
    --cc=tj@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.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®