Linux-Fsdevel Archive on lore.kernel.org
 help / Atom feed
From: Thomas Gleixner <tglx@linutronix.de>
To: LKML <linux-kernel@vger.kernel.org>
Cc: Waiman Long <longman@redhat.com>,
	Matthew Wilcox <willy@infradead.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Alexey Dobriyan <adobriyan@gmail.com>,
	Kees Cook <keescook@chromium.org>,
	linux-fsdevel@vger.kernel.org,
	Davidlohr Bueso <dave@stgolabs.net>,
	Miklos Szeredi <miklos@szeredi.hu>,
	Daniel Colascione <dancol@google.com>,
	Dave Chinner <david@fromorbit.com>,
	Randy Dunlap <rdunlap@infradead.org>,
	Marc Zyngier <marc.zyngier@arm.com>
Subject: [patch V2 1/2] genriq: Avoid summation loops for /proc/stat
Date: Fri, 08 Feb 2019 14:48:03 +0100
Message-ID: <20190208135020.925487496@linutronix.de> (raw)
In-Reply-To: <20190208134802.218483159@linutronix.de>

Waiman reported that on large systems with a large amount of interrupts the
readout of /proc/stat takes a long time to sum up the interrupt
statistics. In principle this is not a problem. but for unknown reasons
some enterprise quality software reads /proc/stat with a high frequency.

The reason for this is that interrupt statistics are accounted per cpu. So
the /proc/stat logic has to sum up the interrupt stats for each interrupt.

This can be largely avoided for interrupts which are not marked as
'PER_CPU' interrupts by simply adding a per interrupt summation counter
which is incremented along with the per interrupt per cpu counter.

The PER_CPU interrupts need to avoid that and use only per cpu accounting
because they share the interrupt number and the interrupt descriptor and
concurrent updates would conflict or require unwanted synchronization.

Reported-by: Waiman Long <longman@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

8<-------------

v2: Undo the unintentional layout change of struct irq_desc.

 include/linux/irqdesc.h |    1 +
 kernel/irq/chip.c       |   12 ++++++++++--
 kernel/irq/internals.h  |    8 +++++++-
 kernel/irq/irqdesc.c    |    7 ++++++-
 4 files changed, 24 insertions(+), 4 deletions(-)


--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -65,6 +65,7 @@ struct irq_desc {
 	unsigned int		core_internal_state__do_not_mess_with_it;
 	unsigned int		depth;		/* nested irq disables */
 	unsigned int		wake_depth;	/* nested wake enables */
+	unsigned int		tot_count;
 	unsigned int		irq_count;	/* For detecting broken IRQs */
 	unsigned long		last_unhandled;	/* Aging timer for unhandled count */
 	unsigned int		irqs_unhandled;
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -855,7 +855,11 @@ void handle_percpu_irq(struct irq_desc *
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 
-	kstat_incr_irqs_this_cpu(desc);
+	/*
+	 * PER CPU interrupts are not serialized. Do not touch
+	 * desc->tot_count.
+	 */
+	__kstat_incr_irqs_this_cpu(desc);
 
 	if (chip->irq_ack)
 		chip->irq_ack(&desc->irq_data);
@@ -884,7 +888,11 @@ void handle_percpu_devid_irq(struct irq_
 	unsigned int irq = irq_desc_get_irq(desc);
 	irqreturn_t res;
 
-	kstat_incr_irqs_this_cpu(desc);
+	/*
+	 * PER CPU interrupts are not serialized. Do not touch
+	 * desc->tot_count.
+	 */
+	__kstat_incr_irqs_this_cpu(desc);
 
 	if (chip->irq_ack)
 		chip->irq_ack(&desc->irq_data);
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -242,12 +242,18 @@ static inline void irq_state_set_masked(
 
 #undef __irqd_to_state
 
-static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
+static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc)
 {
 	__this_cpu_inc(*desc->kstat_irqs);
 	__this_cpu_inc(kstat.irqs_sum);
 }
 
+static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
+{
+	__kstat_incr_irqs_this_cpu(desc);
+	desc->tot_count++;
+}
+
 static inline int irq_desc_get_node(struct irq_desc *desc)
 {
 	return irq_common_data_get_node(&desc->irq_common_data);
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -119,6 +119,7 @@ static void desc_set_defaults(unsigned i
 	desc->depth = 1;
 	desc->irq_count = 0;
 	desc->irqs_unhandled = 0;
+	desc->tot_count = 0;
 	desc->name = NULL;
 	desc->owner = owner;
 	for_each_possible_cpu(cpu)
@@ -919,11 +920,15 @@ unsigned int kstat_irqs_cpu(unsigned int
 unsigned int kstat_irqs(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
-	int cpu;
 	unsigned int sum = 0;
+	int cpu;
 
 	if (!desc || !desc->kstat_irqs)
 		return 0;
+	if (!irq_settings_is_per_cpu_devid(desc) &&
+	    !irq_settings_is_per_cpu(desc))
+	    return desc->tot_count;
+
 	for_each_possible_cpu(cpu)
 		sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
 	return sum;



  reply index

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-08 13:48 [patch V2 0/2] genirq, proc: Speedup /proc/stat interrupt statistics Thomas Gleixner
2019-02-08 13:48 ` Thomas Gleixner [this message]
2019-02-08 22:32   ` [patch V2 1/2] genriq: Avoid summation loops for /proc/stat Andrew Morton
2019-02-08 22:46     ` Waiman Long
2019-02-08 23:21       ` Andrew Morton
2019-02-09  3:41         ` Matthew Wilcox
2019-02-13 15:55           ` David Laight
2019-02-08 13:48 ` [patch V2 2/2] proc/stat: Make the interrupt statistics more efficient Thomas Gleixner
2019-02-08 17:01   ` Alexey Dobriyan
2019-02-08 15:20 ` [patch V2 0/2] genirq, proc: Speedup /proc/stat interrupt statistics Waiman Long
2019-02-08 17:01 ` Davidlohr Bueso
2019-02-08 17:40 ` Marc Zyngier

Reply instructions:

You may reply publically 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=20190208135020.925487496@linutronix.de \
    --to=tglx@linutronix.de \
    --cc=adobriyan@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=dancol@google.com \
    --cc=dave@stgolabs.net \
    --cc=david@fromorbit.com \
    --cc=keescook@chromium.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=longman@redhat.com \
    --cc=marc.zyngier@arm.com \
    --cc=miklos@szeredi.hu \
    --cc=rdunlap@infradead.org \
    --cc=willy@infradead.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

Linux-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \
		linux-fsdevel@vger.kernel.org linux-fsdevel@archiver.kernel.org
	public-inbox-index linux-fsdevel


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-fsdevel


AGPL code for this site: git clone https://public-inbox.org/ public-inbox