From: Peter Zijlstra <peterz@infradead.org>
To: mingo@kernel.org
Cc: longman@redhat.com, chenridong@huaweicloud.com,
peterz@infradead.org, juri.lelli@redhat.com,
vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
vschneid@redhat.com, tj@kernel.org, hannes@cmpxchg.org,
mkoutny@suse.com, cgroups@vger.kernel.org,
linux-kernel@vger.kernel.org, jstultz@google.com,
kprateek.nayak@amd.com
Subject: [RFC][PATCH 2/8] sched/fair: Add cgroup_mode switch
Date: Tue, 17 Mar 2026 10:51:15 +0100 [thread overview]
Message-ID: <20260317104342.586950604@infradead.org> (raw)
In-Reply-To: 20260317095113.387450089@infradead.org
Since calc_group_shares() has issues with 'many' CPUs, specifically the
computed shares value gets to be roughly 1/nr_cpus, prepare to add a few
alternative methods.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
kernel/sched/debug.c | 72 +++++++++++++++++++++++++++++++++++++++++++++++++++
kernel/sched/sched.h | 1
2 files changed, 73 insertions(+)
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -587,6 +587,74 @@ static void debugfs_fair_server_init(voi
}
}
+#ifdef CONFIG_FAIR_GROUP_SCHED
+int cgroup_mode = 0;
+
+static const char *cgroup_mode_str[] = {
+ "smp",
+};
+
+static int sched_cgroup_mode(const char *str)
+{
+ for (int i = 0; i < ARRAY_SIZE(cgroup_mode_str); i++) {
+ if (!strcmp(str, cgroup_mode_str[i]))
+ return i;
+ }
+ return -EINVAL;
+}
+
+static ssize_t sched_cgroup_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[16];
+ int mode;
+
+ if (cnt > 15)
+ cnt = 15;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+ mode = sched_cgroup_mode(strstrip(buf));
+ if (mode < 0)
+ return mode;
+
+ cgroup_mode = mode;
+
+ *ppos += cnt;
+ return cnt;
+}
+
+static int sched_cgroup_show(struct seq_file *m, void *v)
+{
+ for (int i = 0; i < ARRAY_SIZE(cgroup_mode_str); i++) {
+ if (cgroup_mode == i)
+ seq_puts(m, "(");
+ seq_puts(m, cgroup_mode_str[i]);
+ if (cgroup_mode == i)
+ seq_puts(m, ")");
+
+ seq_puts(m, " ");
+ }
+ seq_puts(m, "\n");
+ return 0;
+}
+
+static int sched_cgroup_open(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, sched_cgroup_show, NULL);
+}
+
+static const struct file_operations sched_cgroup_fops = {
+ .open = sched_cgroup_open,
+ .write = sched_cgroup_write,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+#endif
+
static __init int sched_init_debug(void)
{
struct dentry __maybe_unused *numa;
@@ -624,6 +692,10 @@ static __init int sched_init_debug(void)
debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ debugfs_create_file("cgroup_mode", 0444, debugfs_sched, NULL, &sched_cgroup_fops);
+#endif
+
debugfs_fair_server_init();
#ifdef CONFIG_SCHED_CLASS_EXT
debugfs_ext_server_init();
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -565,6 +565,7 @@ static inline struct task_group *css_tg(
extern int tg_nop(struct task_group *tg, void *data);
#ifdef CONFIG_FAIR_GROUP_SCHED
+extern int cgroup_mode;
extern void free_fair_sched_group(struct task_group *tg);
extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
extern void online_fair_sched_group(struct task_group *tg);
next prev parent reply other threads:[~2026-03-17 10:47 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-17 9:51 [RFC][PATCH 0/8] sched: Flatten the pick Peter Zijlstra
2026-03-17 9:51 ` [RFC][PATCH 1/8] sched/debug: Collapse subsequent CONFIG_SCHED_CLASS_EXT sections Peter Zijlstra
2026-03-17 9:51 ` Peter Zijlstra [this message]
2026-03-17 9:51 ` [RFC][PATCH 3/8] sched/fair: Add cgroup_mode: UP Peter Zijlstra
2026-03-17 9:51 ` [RFC][PATCH 4/8] sched/fair: Add cgroup_mode: MAX Peter Zijlstra
2026-03-17 9:51 ` [RFC][PATCH 5/8] sched/fair: Add cgroup_mode: CONCUR Peter Zijlstra
2026-03-17 9:51 ` [RFC][PATCH 6/8] sched/fair: Add newidle balance to pick_task_fair() Peter Zijlstra
2026-03-17 9:51 ` [RFC][PATCH 7/8] sched: Remove sched_class::pick_next_task() Peter Zijlstra
2026-03-17 9:51 ` [RFC][PATCH 8/8] sched/eevdf: Move to a single runqueue Peter Zijlstra
2026-03-17 17:46 ` K Prateek Nayak
2026-03-18 9:02 ` Peter Zijlstra
2026-03-18 9:32 ` K Prateek Nayak
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=20260317104342.586950604@infradead.org \
--to=peterz@infradead.org \
--cc=bsegall@google.com \
--cc=cgroups@vger.kernel.org \
--cc=chenridong@huaweicloud.com \
--cc=dietmar.eggemann@arm.com \
--cc=hannes@cmpxchg.org \
--cc=jstultz@google.com \
--cc=juri.lelli@redhat.com \
--cc=kprateek.nayak@amd.com \
--cc=linux-kernel@vger.kernel.org \
--cc=longman@redhat.com \
--cc=mgorman@suse.de \
--cc=mingo@kernel.org \
--cc=mkoutny@suse.com \
--cc=rostedt@goodmis.org \
--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