LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Glauber Costa <glommer@redhat.com>
To: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, Rik van Riel <riel@redhat.com>,
	Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Avi Kivity <avi@redhat.com>
Subject: [PATCH v3 3/6] KVM-GST: KVM Steal time accounting
Date: Fri, 11 Feb 2011 13:19:21 -0500	[thread overview]
Message-ID: <1297448364-14051-4-git-send-email-glommer@redhat.com> (raw)
In-Reply-To: <1297448364-14051-1-git-send-email-glommer@redhat.com>

This patch accounts steal time time in kernel/sched.
I kept it from last proposal, because I still see advantages
in it: Doing it here will give us easier access from scheduler
variables such as the cpu rq. The next patch shows an example of
usage for it.

Since functions like account_idle_time() can be called from
multiple places, not only account_process_tick(), steal time
grabbing is repeated in each account function separatedely.

Signed-off-by: Glauber Costa <glommer@redhat.com>
CC: Rik van Riel <riel@redhat.com>
CC: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Avi Kivity <avi@redhat.com>
---
 include/linux/sched.h |    1 +
 kernel/sched.c        |   47 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+), 0 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d747f94..5dbf509 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -302,6 +302,7 @@ long io_schedule_timeout(long timeout);
 extern void cpu_init (void);
 extern void trap_init(void);
 extern void update_process_times(int user);
+extern u64 (*hypervisor_steal_time)(int cpu);
 extern void scheduler_tick(void);
 
 extern void sched_show_task(struct task_struct *p);
diff --git a/kernel/sched.c b/kernel/sched.c
index 18d38e4..60b0cf8 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -524,6 +524,8 @@ struct rq {
 	u64 prev_irq_time;
 #endif
 
+	u64 prev_steal_ticks;
+
 	/* calc_load related fields */
 	unsigned long calc_load_update;
 	long calc_load_active;
@@ -1780,6 +1782,16 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 	dec_nr_running(rq);
 }
 
+u64 (*hypervisor_steal_time)(int cpu) = NULL;
+
+static u64 steal_time_clock(int cpu)
+{
+	if (!hypervisor_steal_time)
+		return 0;
+
+	return hypervisor_steal_time(cpu);
+}
+
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 
 /*
@@ -3509,6 +3521,33 @@ unsigned long long thread_group_sched_runtime(struct task_struct *p)
 }
 
 /*
+ * We have to at flush steal time information every time something else
+ * is accounted. Since the accounting functions are all visible to the rest
+ * of the kernel, it gets tricky to do them in one place. This helper function
+ * helps us.
+ *
+ * When the system is idle, the concept of steal time does not apply. We just
+ * tell the underlying hypervisor that we grabbed the data, but skip steal time
+ * accounting
+ */
+static int touch_steal_time(int is_idle)
+{
+	u64 steal, st;
+
+	steal = steal_time_clock(smp_processor_id());
+
+	st = steal / TICK_NSEC - this_rq()->prev_steal_ticks;
+
+	this_rq()->prev_steal_ticks += st;
+
+	if (!st || is_idle)
+		return 0;
+
+	account_steal_time(st);
+	return 1;
+}
+
+/*
  * Account user cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @cputime: the cpu time spent in user space since the last update
@@ -3520,6 +3559,9 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
 	cputime64_t tmp;
 
+	if (touch_steal_time(0))
+		return;
+
 	/* Add user time to process. */
 	p->utime = cputime_add(p->utime, cputime);
 	p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
@@ -3580,6 +3622,9 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
 	cputime64_t tmp;
 
+	if (touch_steal_time(0))
+		return;
+
 	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
 		account_guest_time(p, cputime, cputime_scaled);
 		return;
@@ -3627,6 +3672,8 @@ void account_idle_time(cputime_t cputime)
 	cputime64_t cputime64 = cputime_to_cputime64(cputime);
 	struct rq *rq = this_rq();
 
+	touch_steal_time(1);
+
 	if (atomic_read(&rq->nr_iowait) > 0)
 		cpustat->iowait = cputime64_add(cpustat->iowait, cputime64);
 	else
-- 
1.7.2.3


  parent reply	other threads:[~2011-02-11 18:21 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-02-11 18:19 [PATCH v3 0/6] Steal time for KVM Glauber Costa
2011-02-11 18:19 ` [PATCH v3 1/6] KVM-HDR: KVM Steal time implementation Glauber Costa
2011-02-15 14:25   ` Avi Kivity
2011-02-11 18:19 ` [PATCH v3 2/6] KVM-HV: " Glauber Costa
2011-02-15 14:34   ` Avi Kivity
2011-02-11 18:19 ` Glauber Costa [this message]
2011-02-11 19:05   ` [PATCH v3 3/6] KVM-GST: KVM Steal time accounting Peter Zijlstra
2011-02-12 23:46     ` Glauber Costa
2011-02-15 14:35   ` Avi Kivity
2011-02-15 14:45     ` Peter Zijlstra
2011-02-15 15:17       ` Avi Kivity
2011-02-15 15:24         ` Rik van Riel
2011-02-15 15:26           ` Avi Kivity
2011-02-15 15:27         ` Peter Zijlstra
2011-02-11 18:19 ` [PATCH v3 4/6] KVM-GST: KVM Steal time registration Glauber Costa
2011-02-15 14:41   ` Avi Kivity
2011-02-15 15:48     ` Peter Zijlstra
2011-02-11 18:19 ` [PATCH v3 5/6] KVM-GST: adjust scheduler cpu power Glauber Costa
2011-02-11 19:05   ` Peter Zijlstra
2011-02-11 18:19 ` [PATCH v3 6/6] Describe KVM_MSR_STEAL_TIME Glauber Costa

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=1297448364-14051-4-git-send-email-glommer@redhat.com \
    --to=glommer@redhat.com \
    --cc=avi@redhat.com \
    --cc=jeremy.fitzhardinge@citrix.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=riel@redhat.com \
    --subject='Re: [PATCH v3 3/6] KVM-GST: KVM Steal time accounting' \
    /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).