From: Frederic Weisbecker <fweisbec@gmail.com>
To: Ingo Molnar <mingo@kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
Frederic Weisbecker <fweisbec@gmail.com>,
Jesper Dangaard Brouer <brouer@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
Wanpeng Li <wanpeng.li@hotmail.com>,
Thomas Gleixner <tglx@linutronix.de>,
Rik van Riel <riel@redhat.com>,
Stanislaw Gruszka <sgruszka@redhat.com>
Subject: [PATCH] sched/cputime: Fix ksoftirqd cputime accounting regression
Date: Tue, 25 Apr 2017 16:10:48 +0200
Message-ID: <1493129448-5356-1-git-send-email-fweisbec@gmail.com> (raw)
irq_time_read() returns the irqtime minus the ksoftirqd time. This
is necessary because irq_time_read() is used to substract the IRQ time
from the sum_exec_runtime of a task. If we were to include the softirq
time of ksoftirqd, this task would substract its own CPU time everytime
it updates ksoftirqd->sum_exec_runtime which would therefore never
progress.
But this behaviour got broken by commit a499a5a14db:
("sched/cputime: Increment kcpustat directly on irqtime account")
which now includes ksoftirqd softirq time in the time returned by
irq_time_read().
This has resulted in wrong ksotfirqd cputime reported to userspace
through /proc/stat and thus "top" not showing ksoftirqd when it should
after intense networking load.
ksoftirqd->stime happens to be correct but it gets scaled down by
sum_exec_runtime through task_cputime_adjusted().
To fix this, just account the strict IRQ time in a separate counter and
use it to report the IRQ time.
Reported-and-tested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
---
kernel/sched/cputime.c | 27 ++++++++++++++++-----------
kernel/sched/sched.h | 9 +++++++--
2 files changed, 23 insertions(+), 13 deletions(-)
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index f3778e2b..aea3135 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -34,6 +34,18 @@ void disable_sched_clock_irqtime(void)
sched_clock_irqtime = 0;
}
+static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
+ enum cpu_usage_stat idx)
+{
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+ u64_stats_update_begin(&irqtime->sync);
+ cpustat[idx] += delta;
+ irqtime->total += delta;
+ irqtime->tick_delta += delta;
+ u64_stats_update_end(&irqtime->sync);
+}
+
/*
* Called before incrementing preempt_count on {soft,}irq_enter
* and before decrementing preempt_count on {soft,}irq_exit.
@@ -41,7 +53,6 @@ void disable_sched_clock_irqtime(void)
void irqtime_account_irq(struct task_struct *curr)
{
struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
- u64 *cpustat = kcpustat_this_cpu->cpustat;
s64 delta;
int cpu;
@@ -52,22 +63,16 @@ void irqtime_account_irq(struct task_struct *curr)
delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
irqtime->irq_start_time += delta;
- u64_stats_update_begin(&irqtime->sync);
/*
* We do not account for softirq time from ksoftirqd here.
* We want to continue accounting softirq time to ksoftirqd thread
* in that case, so as not to confuse scheduler with a special task
* that do not consume any time, but still wants to run.
*/
- if (hardirq_count()) {
- cpustat[CPUTIME_IRQ] += delta;
- irqtime->tick_delta += delta;
- } else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) {
- cpustat[CPUTIME_SOFTIRQ] += delta;
- irqtime->tick_delta += delta;
- }
-
- u64_stats_update_end(&irqtime->sync);
+ if (hardirq_count())
+ irqtime_account_delta(irqtime, delta, CPUTIME_IRQ);
+ else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
+ irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ);
}
EXPORT_SYMBOL_GPL(irqtime_account_irq);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 5cbf922..767aab3 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1869,6 +1869,7 @@ static inline void nohz_balance_exit_idle(unsigned int cpu) { }
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
struct irqtime {
+ u64 total;
u64 tick_delta;
u64 irq_start_time;
struct u64_stats_sync sync;
@@ -1876,16 +1877,20 @@ struct irqtime {
DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
+/*
+ * Returns the irqtime minus the softirq time computed by ksoftirqd.
+ * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
+ * and never move forward.
+ */
static inline u64 irq_time_read(int cpu)
{
struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
- u64 *cpustat = kcpustat_cpu(cpu).cpustat;
unsigned int seq;
u64 total;
do {
seq = __u64_stats_fetch_begin(&irqtime->sync);
- total = cpustat[CPUTIME_SOFTIRQ] + cpustat[CPUTIME_IRQ];
+ total = irqtime->total;
} while (__u64_stats_fetch_retry(&irqtime->sync, seq));
return total;
--
2.7.4
next reply index
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-25 14:10 Frederic Weisbecker [this message]
2017-04-26 14:30 ` Jesper Dangaard Brouer
2017-04-26 15:44 ` Rik van Riel
2017-04-27 14:16 ` [tip:sched/urgent] " tip-bot for Frederic Weisbecker
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=1493129448-5356-1-git-send-email-fweisbec@gmail.com \
--to=fweisbec@gmail.com \
--cc=brouer@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
--cc=sgruszka@redhat.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=wanpeng.li@hotmail.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
LKML Archive on lore.kernel.org
Archives are clonable:
git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git
# If you have public-inbox 1.1+ installed, you may
# initialize and index your mirror using the following commands:
public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
linux-kernel@vger.kernel.org
public-inbox-index lkml
Example config snippet for mirrors
Newsgroup available over NNTP:
nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel
AGPL code for this site: git clone https://public-inbox.org/public-inbox.git