Linux-Fsdevel Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Jonathan Adams <jwadams@google.com>
To: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org
Cc: netdev@vger.kernel.org, kvm@vger.kernel.org,
	Paolo Bonzini <pbonzini@redhat.com>,
	Greg KH <gregkh@linuxfoundation.org>,
	Jim Mattson <jmattson@google.com>,
	David Rientjes <rientjes@google.com>,
	Jonathan Adams <jwadams@google.com>
Subject: [RFC PATCH 5/7] core/metricfs: expose scheduler stat information through metricfs
Date: Fri,  7 Aug 2020 14:29:14 -0700	[thread overview]
Message-ID: <20200807212916.2883031-6-jwadams@google.com> (raw)
In-Reply-To: <20200807212916.2883031-1-jwadams@google.com>

Add metricfs support for displaying percpu scheduler counters.
The top directory is /sys/kernel/debug/metricfs/stat (analogous
to /proc/stat).  Then there is a subdirectory for each scheduler
stat.  For example:

    cat /sys/kernel/debug/metricfs/stat/user/values

Signed-off-by: Jonathan Adams <jwadams@google.com>

---

jwadams@google.com: rebased to 5.8-pre6
	This is work originally done by another engineer at
	google, who would rather not have their name associated with this
	patchset. They're okay with me sending it under my name.
---
 fs/proc/stat.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 57 insertions(+)

diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 46b3293015fe..deb378507b0b 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -13,6 +13,7 @@
 #include <linux/irqnr.h>
 #include <linux/sched/cputime.h>
 #include <linux/tick.h>
+#include <linux/metricfs.h>
 
 #ifndef arch_irq_stat_cpu
 #define arch_irq_stat_cpu(cpu) 0
@@ -237,3 +238,59 @@ static int __init proc_stat_init(void)
 	return 0;
 }
 fs_initcall(proc_stat_init);
+
+#ifdef CONFIG_METRICFS
+#define METRICFS_ITEM(name, field, desc) \
+static void \
+metricfs_##name(struct metric_emitter *e, int cpu) \
+{ \
+	int64_t v = kcpustat_field(&kcpustat_cpu(cpu), field, cpu); \
+	METRIC_EMIT_PERCPU_INT(e, cpu, v); \
+} \
+METRIC_EXPORT_PERCPU_COUNTER(name, desc, metricfs_##name)
+
+#define METRICFS_FUNC_ITEM(name, func, desc) \
+static void \
+metricfs_##name(struct metric_emitter *e, int cpu) \
+{ \
+	struct kernel_cpustat cpustat; \
+	int64_t v; \
+	kcpustat_cpu_fetch(&cpustat, cpu); \
+	v = func(&cpustat, cpu); \
+	METRIC_EMIT_PERCPU_INT(e, cpu, v); \
+} \
+METRIC_EXPORT_PERCPU_COUNTER(name, desc, metricfs_##name)
+
+METRICFS_ITEM(user, CPUTIME_USER, "time in user mode (nsec)");
+METRICFS_ITEM(nice, CPUTIME_NICE, "time in user mode niced (nsec)");
+METRICFS_ITEM(system, CPUTIME_SYSTEM, "time in system calls (nsec)");
+METRICFS_ITEM(irq, CPUTIME_IRQ, "time in interrupts (nsec)");
+METRICFS_ITEM(softirq, CPUTIME_SOFTIRQ, "time in softirqs (nsec)");
+METRICFS_ITEM(steal, CPUTIME_STEAL, "time in involuntary wait (nsec)");
+METRICFS_ITEM(guest, CPUTIME_GUEST, "time in guest mode (nsec)");
+METRICFS_ITEM(guest_nice, CPUTIME_GUEST_NICE,
+	"time in guest mode niced (nsec)");
+METRICFS_FUNC_ITEM(idle, get_idle_time, "time in idle (nsec)");
+METRICFS_FUNC_ITEM(iowait, get_iowait_time, "time in iowait (nsec)");
+
+static int __init init_stat_metricfs(void)
+{
+	struct metricfs_subsys *subsys;
+
+	subsys = metricfs_create_subsys("stat", NULL);
+	metric_init_user(subsys);
+	metric_init_nice(subsys);
+	metric_init_system(subsys);
+	metric_init_irq(subsys);
+	metric_init_softirq(subsys);
+	metric_init_steal(subsys);
+	metric_init_guest(subsys);
+	metric_init_guest_nice(subsys);
+	metric_init_idle(subsys);
+	metric_init_iowait(subsys);
+
+	return 0;
+}
+module_init(init_stat_metricfs);
+
+#endif
-- 
2.28.0.236.gb10cc79966-goog


  parent reply	other threads:[~2020-08-07 21:30 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-07 21:29 [RFC PATCH 0/7] metricfs metric file system and examples Jonathan Adams
2020-08-07 21:29 ` [RFC PATCH 1/7] core/metricfs: Create metricfs, standardized files under debugfs Jonathan Adams
2020-08-08  5:41   ` Greg KH
2020-08-07 21:29 ` [RFC PATCH 2/7] core/metricfs: add support for percpu metricfs files Jonathan Adams
2020-08-08  5:43   ` Greg KH
2020-08-07 21:29 ` [RFC PATCH 3/7] core/metricfs: metric for kernel warnings Jonathan Adams
2020-08-08  5:45   ` Greg KH
2020-08-07 21:29 ` [RFC PATCH 4/7] core/metricfs: expose softirq information through metricfs Jonathan Adams
2020-08-08  5:46   ` Greg KH
2020-08-07 21:29 ` Jonathan Adams [this message]
2020-08-07 21:29 ` [RFC PATCH 6/7] core/metricfs: expose x86-specific irq " Jonathan Adams
2020-08-13 10:11   ` Thomas Gleixner
2020-08-13 11:47     ` Paolo Bonzini
2020-08-13 12:13       ` Thomas Gleixner
2020-08-13 14:10         ` Paolo Bonzini
2020-08-13 14:21           ` Thomas Gleixner
2020-08-07 21:29 ` [RFC PATCH 7/7] net-metricfs: Export /proc/net/dev via metricfs Jonathan Adams
2020-08-08  2:06 ` [RFC PATCH 0/7] metricfs metric file system and examples Andrew Lunn
2020-08-08 15:59   ` David Ahern
2020-08-10 18:20     ` Jakub Kicinski
2020-08-10  9:23 ` Pavel Machek

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=20200807212916.2883031-6-jwadams@google.com \
    --to=jwadams@google.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=jmattson@google.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=rientjes@google.com \
    --subject='Re: [RFC PATCH 5/7] core/metricfs: expose scheduler stat information through metricfs' \
    /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

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).