From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Dan Hecht <dhecht@vmware.com>
Cc: dwalker@mvista.com, cpufreq@lists.linux.org.uk,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Con Kolivas <kernel@kolivas.org>,
Chris Wright <chrisw@sous-sol.org>,
Virtualization Mailing List <virtualization@lists.osdl.org>,
john stultz <johnstul@us.ibm.com>, Ingo Molnar <mingo@elte.hu>,
Thomas Gleixner <tglx@linutronix.de>,
paulus@au.ibm.com, schwidefsky@de.ibm.com,
Rik van Riel <riel@redhat.com>
Subject: Re: Stolen and degraded time and schedulers
Date: Wed, 14 Mar 2007 13:31:55 -0700 [thread overview]
Message-ID: <45F85BBB.70707@goop.org> (raw)
In-Reply-To: <45F85A62.8050001@vmware.com>
[-- Attachment #1: Type: text/plain, Size: 704 bytes --]
Dan Hecht wrote:
> Sounds good. I don't see this in your patchset you sent yesterday
> though; did you add it after sending out those patches?
Yes.
> if so, could you forward the new patch? does it explicitly prevent
> stolen time from getting accounted as user/system time or does it
> just rely on NO_HZ mode sort of happening to work that way (since the
> one shot timer is skipped ahead for missed ticks)?
Hm, not sure. It doesn't care how often it gets called; it just
accumulates results up to that point, but I'm not sure if the time would
get double accounted. Perhaps it doesn't matter when using
xen_sched_clock().
Did the get_scheduled_time -> sched_clock make sense to you?
J
[-- Attachment #2: xen-stolen-time.patch --]
[-- Type: text/x-patch, Size: 3983 bytes --]
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: john stultz <johnstul@us.ibm.com>
---
arch/i386/xen/time.c | 101 ++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 101 insertions(+)
===================================================================
--- a/arch/i386/xen/time.c
+++ b/arch/i386/xen/time.c
@@ -2,6 +2,7 @@
#include <linux/interrupt.h>
#include <linux/clocksource.h>
#include <linux/clockchips.h>
+#include <linux/kernel_stat.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
@@ -14,6 +15,7 @@
#define XEN_SHIFT 22
#define TIMER_SLOP 100000 /* Xen may fire a timer up to this many ns early */
+#define NS_PER_TICK (1000000000ll / HZ)
static DEFINE_PER_CPU(struct clock_event_device, xen_clock_events);
@@ -28,6 +30,99 @@ struct shadow_time_info {
static DEFINE_PER_CPU(struct shadow_time_info, shadow_time);
+/* runstate info updated by Xen */
+static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate);
+
+/* snapshots of runstate info */
+static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate_snapshot);
+
+/* unused ns of stolen and blocked time */
+static DEFINE_PER_CPU(u64, residual_stolen);
+static DEFINE_PER_CPU(u64, residual_blocked);
+
+/*
+ Runstate accounting
+ */
+static void get_runstate_snapshot(struct vcpu_runstate_info *res)
+{
+ u64 state_time;
+ struct vcpu_runstate_info *state;
+
+ preempt_disable();
+
+ state = &__get_cpu_var(runstate);
+
+ do {
+ state_time = state->state_entry_time;
+ barrier();
+ *res = *state;
+ barrier();
+ } while(state->state_entry_time != state_time);
+
+ preempt_enable();
+}
+
+static void setup_runstate_info(void)
+{
+ struct vcpu_register_runstate_memory_area area;
+
+ area.addr.v = &__get_cpu_var(runstate);
+
+ if (HYPERVISOR_vcpu_op(VCPUOP_register_runstate_memory_area,
+ smp_processor_id(), &area))
+ BUG();
+
+ get_runstate_snapshot(&__get_cpu_var(runstate_snapshot));
+}
+
+static void do_stolen_accounting(void)
+{
+ struct vcpu_runstate_info state;
+ struct vcpu_runstate_info *snap;
+ u64 blocked, runnable, offline, stolen;
+ cputime_t ticks;
+
+ get_runstate_snapshot(&state);
+
+ WARN_ON(state.state != RUNSTATE_running);
+
+ snap = &__get_cpu_var(runstate_snapshot);
+
+ /* work out how much time the VCPU has not been runn*ing* */
+ blocked = state.time[RUNSTATE_blocked] - snap->time[RUNSTATE_blocked];
+ runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable];
+ offline = state.time[RUNSTATE_offline] - snap->time[RUNSTATE_offline];
+
+ *snap = state;
+
+ /* Add the appropriate number of ticks of stolen time,
+ including any left-overs from last time. Passing NULL to
+ account_steal_time accounts the time as stolen. */
+ stolen = runnable + offline + __get_cpu_var(residual_stolen);
+ ticks = 0;
+ while(stolen >= NS_PER_TICK) {
+ ticks++;
+ stolen -= NS_PER_TICK;
+ }
+ __get_cpu_var(residual_stolen) = stolen;
+ account_steal_time(NULL, ticks);
+
+ /* Add the appropriate number of ticks of blocked time,
+ including any left-overs from last time. Passing idle to
+ account_steal_time accounts the time as idle/wait. */
+ blocked += __get_cpu_var(residual_blocked);
+ ticks = 0;
+ while(blocked >= NS_PER_TICK) {
+ ticks++;
+ blocked -= NS_PER_TICK;
+ }
+ __get_cpu_var(residual_blocked) = blocked;
+ account_steal_time(idle_task(smp_processor_id()), ticks);
+}
+
+
+
+/* Get the CPU speed from Xen */
unsigned long xen_cpu_khz(void)
{
u64 cpu_khz = 1000000ULL << 32;
@@ -264,6 +359,8 @@ static irqreturn_t xen_timerop_timer_int
ret = IRQ_HANDLED;
}
+ do_stolen_accounting();
+
return ret;
}
@@ -338,6 +435,8 @@ static irqreturn_t xen_vcpuop_timer_inte
ret = IRQ_HANDLED;
}
+ do_stolen_accounting();
+
return ret;
}
@@ -380,6 +479,8 @@ static void xen_setup_timer(int cpu)
evt->cpumask = cpumask_of_cpu(cpu);
evt->irq = irq;
clockevents_register_device(evt);
+
+ setup_runstate_info();
put_cpu_var(xen_clock_events);
}
[-- Attachment #3: xen-sched-clock.patch --]
[-- Type: text/x-patch, Size: 2222 bytes --]
Subject: Implement xen_sched_clock
Implement xen_sched_clock, which returns the number of ns the current
vcpu has been actually in the running state (vs blocked,
runnable-but-not-running, or offline) since boot.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: john stultz <johnstul@us.ibm.com>
---
arch/i386/xen/enlighten.c | 2 +-
arch/i386/xen/time.c | 14 ++++++++++++++
arch/i386/xen/xen-ops.h | 1 +
3 files changed, 16 insertions(+), 1 deletion(-)
===================================================================
--- a/arch/i386/xen/enlighten.c
+++ b/arch/i386/xen/enlighten.c
@@ -664,7 +664,7 @@ static const struct paravirt_ops xen_par
.set_wallclock = xen_set_wallclock,
.get_wallclock = xen_get_wallclock,
.get_cpu_khz = xen_cpu_khz,
- .get_scheduled_cycles = native_read_tsc,
+ .sched_clock = xen_sched_clock,
#ifdef CONFIG_X86_LOCAL_APIC
.apic_write = paravirt_nop,
===================================================================
--- a/arch/i386/xen/time.c
+++ b/arch/i386/xen/time.c
@@ -16,6 +16,8 @@
#define XEN_SHIFT 22
#define TIMER_SLOP 100000 /* Xen may fire a timer up to this many ns early */
#define NS_PER_TICK (1000000000ll / HZ)
+
+static cycle_t xen_clocksource_read(void);
static DEFINE_PER_CPU(struct clock_event_device, xen_clock_events);
@@ -120,6 +122,18 @@ static void do_stolen_accounting(void)
account_steal_time(idle_task(smp_processor_id()), ticks);
}
+/* Xen sched_clock implementation. Returns the number of RUNNING ns */
+unsigned long long xen_sched_clock(void)
+{
+ struct vcpu_runstate_info state;
+ cycle_t now = xen_clocksource_read();
+
+ get_runstate_snapshot(&state);
+
+ WARN_ON(state.state != RUNSTATE_running);
+
+ return state.time[RUNSTATE_running] + (now - state.state_entry_time);
+}
/* Get the CPU speed from Xen */
===================================================================
--- a/arch/i386/xen/xen-ops.h
+++ b/arch/i386/xen/xen-ops.h
@@ -14,6 +14,7 @@ void __init xen_time_init(void);
void __init xen_time_init(void);
unsigned long xen_get_wallclock(void);
int xen_set_wallclock(unsigned long time);
+unsigned long long xen_sched_clock(void);
void xen_mark_init_mm_pinned(void);
next prev parent reply other threads:[~2007-03-14 20:32 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-03-13 16:31 Stolen and degraded time and schedulers Jeremy Fitzhardinge
2007-03-13 20:12 ` john stultz
2007-03-13 20:32 ` Jeremy Fitzhardinge
2007-03-13 21:27 ` Daniel Walker
2007-03-13 21:59 ` Jeremy Fitzhardinge
2007-03-14 0:43 ` Dan Hecht
2007-03-14 4:37 ` Jeremy Fitzhardinge
2007-03-14 13:58 ` Lennart Sorensen
2007-03-14 15:08 ` Jeremy Fitzhardinge
2007-03-14 15:12 ` Lennart Sorensen
2007-03-14 19:02 ` Dan Hecht
2007-03-14 19:34 ` Jeremy Fitzhardinge
2007-03-14 19:45 ` Rik van Riel
2007-03-14 19:47 ` Jeremy Fitzhardinge
2007-03-14 20:02 ` Rik van Riel
2007-03-14 20:26 ` Dan Hecht
2007-03-14 20:31 ` Jeremy Fitzhardinge [this message]
2007-03-14 20:46 ` Dan Hecht
2007-03-14 21:18 ` Jeremy Fitzhardinge
2007-03-15 19:09 ` Dan Hecht
2007-03-15 19:18 ` Jeremy Fitzhardinge
2007-03-15 19:48 ` Rik van Riel
2007-03-15 19:53 ` Jeremy Fitzhardinge
2007-03-15 20:07 ` Dan Hecht
2007-03-15 20:14 ` Rik van Riel
2007-03-15 20:35 ` Dan Hecht
2007-03-16 8:59 ` Martin Schwidefsky
2007-03-14 20:38 ` Ingo Molnar
2007-03-14 20:59 ` Jeremy Fitzhardinge
2007-03-16 8:38 ` Ingo Molnar
2007-03-16 16:53 ` Jeremy Fitzhardinge
2007-03-15 5:23 ` Paul Mackerras
2007-03-15 19:33 ` Jeremy Fitzhardinge
2007-03-14 2:00 ` Daniel Walker
2007-03-14 6:52 ` Jeremy Fitzhardinge
2007-03-14 8:20 ` Zan Lynx
2007-03-14 16:11 ` Daniel Walker
2007-03-14 16:37 ` Jeremy Fitzhardinge
2007-03-14 16:59 ` Daniel Walker
2007-03-14 17:08 ` Jeremy Fitzhardinge
2007-03-14 18:06 ` Daniel Walker
2007-03-14 18:41 ` Jeremy Fitzhardinge
2007-03-14 19:00 ` Daniel Walker
2007-03-14 19:44 ` Jeremy Fitzhardinge
2007-03-14 20:33 ` Daniel Walker
2007-03-14 21:16 ` Jeremy Fitzhardinge
2007-03-14 21:34 ` Daniel Walker
2007-03-14 21:42 ` Jeremy Fitzhardinge
2007-03-14 21:36 ` Con Kolivas
2007-03-14 21:38 ` Jeremy Fitzhardinge
2007-03-14 21:40 ` Con Kolivas
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=45F85BBB.70707@goop.org \
--to=jeremy@goop.org \
--cc=chrisw@sous-sol.org \
--cc=cpufreq@lists.linux.org.uk \
--cc=dhecht@vmware.com \
--cc=dwalker@mvista.com \
--cc=johnstul@us.ibm.com \
--cc=kernel@kolivas.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=paulus@au.ibm.com \
--cc=riel@redhat.com \
--cc=schwidefsky@de.ibm.com \
--cc=tglx@linutronix.de \
--cc=virtualization@lists.osdl.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
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;
as well as URLs for NNTP newsgroup(s).