This adds POWERPC specific hooks for scaled time accounting.
POWER6 includes a SPURR register. The SPURR is based off the PURR
register but is scaled based on CPU frequency and issue rates. This
gives a more accurate account of the instructions used per task. The
PURR and timebase will be constant relative to the wall clock,
irrespective of the CPU frequency.
This implementation reads the SPURR register in account_system_vtime
which is only call called on context witch and hard and soft irq entry
and exit. The percentage of user and system time is then estimated
using the ratio of these accounted by the PURR. If the SPURR is not
present, the PURR read.
An earlier implementation of this patch read the SPURR whenever the
PURR was read, which included the system call entry and exit path.
Unfortunately this showed a performance regression on lmbench runs, so
was re-implemented.
I've included the lmbench results here when run bare metal on POWER6.
1st column is the unpatch results. 2nd column is the results using the
below patch and the 3rd is the % diff of these results from the base.
4th and 5th columns are the results and % differnce from the base
using the older patch (SPURR read in syscall entry/exit path).
Base Scaled-Acct SPURR-in-syscall
Result Result % diff Result % diff
Simple syscall: 0.3086 0.3086 0.0000 0.3452 11.8600
Simple read: 0.4591 0.4671 1.7425 0.5044 9.86713
Simple write: 0.4364 0.4366 0.0458 0.4731 8.40971
Simple stat: 2.0055 2.0295 1.1967 2.0669 3.06158
Simple fstat: 0.5962 0.5876 -1.442 0.6368 6.80979
Simple open/close: 3.1283 3.1009 -0.875 3.2088 2.57328
Select on 10 fd's: 0.8554 0.8457 -1.133 0.8667 1.32101
Select on 100 fd's: 3.5292 3.6329 2.9383 3.6664 3.88756
Select on 250 fd's: 7.9097 8.1881 3.5197 8.2242 3.97613
Select on 500 fd's: 15.2659 15.836 3.7357 15.873 3.97814
Select on 10 tcp fd's: 0.9576 0.9416 -1.670 0.9752 1.83792
Select on 100 tcp fd's: 7.248 7.2254 -0.311 7.2685 0.28283
Select on 250 tcp fd's: 17.7742 17.707 -0.375 17.749 -0.1406
Select on 500 tcp fd's: 35.4258 35.25 -0.496 35.286 -0.3929
Signal handler installation: 0.6131 0.6075 -0.913 0.647 5.52927
Signal handler overhead: 2.0919 2.1078 0.7600 2.1831 4.35967
Protection fault: 0.7345 0.7478 1.8107 0.8031 9.33968
Pipe latency: 33.006 16.398 -50.31 33.475 1.42368
AF_UNIX sock stream latency: 14.5093 30.910 113.03 30.715 111.692
Process fork+exit: 219.8 222.8 1.3648 229.37 4.35623
Process fork+execve: 876.14 873.28 -0.32 868.66 -0.8533
Process fork+/bin/sh -c: 2830 2876.5 1.6431 2958 4.52296
File /var/tmp/XXX write bw: 1193497 1195536 0.1708 118657 -0.5799
Pagefaults on /var/tmp/XXX: 3.1272 3.2117 2.7020 3.2521 3.99398
Also, kernel compile times show no difference with this patch applied.
Signed-off-by: Michael Neuling <[email protected]>
---
arch/powerpc/kernel/asm-offsets.c | 1 +
arch/powerpc/kernel/time.c | 32 ++++++++++++++++++++++++++++++--
include/asm-powerpc/paca.h | 3 +++
3 files changed, 34 insertions(+), 2 deletions(-)
Index: linux-2.6-ozlabs/arch/powerpc/kernel/asm-offsets.c
===================================================================
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/asm-offsets.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/asm-offsets.c
@@ -141,6 +141,7 @@ int main(void)
DEFINE(PACALPPACAPTR, offsetof(struct paca_struct, lppaca_ptr));
DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr));
+ DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr));
DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
DEFINE(PACA_SLBSHADOWPTR, offsetof(struct paca_struct, slb_shadow_ptr));
Index: linux-2.6-ozlabs/arch/powerpc/kernel/time.c
===================================================================
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/time.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/time.c
@@ -168,23 +168,44 @@ static u64 read_purr(void)
}
/*
+ * Read the SPURR on systems that have it, otherwise the purr
+ */
+static u64 read_spurr(void)
+{
+ if (cpu_has_feature(CPU_FTR_SPURR))
+ return mfspr(SPRN_SPURR);
+ return read_purr();
+}
+
+/*
* Account time for a transition between system, hard irq
* or soft irq state.
*/
void account_system_vtime(struct task_struct *tsk)
{
- u64 now, delta;
+ u64 now, nowscaled, delta, deltascaled;
unsigned long flags;
local_irq_save(flags);
now = read_purr();
delta = now - get_paca()->startpurr;
get_paca()->startpurr = now;
+ nowscaled = read_spurr();
+ deltascaled = nowscaled - get_paca()->startspurr;
+ get_paca()->startspurr = nowscaled;
if (!in_interrupt()) {
+ /* deltascaled includes both user and system time.
+ * Hence scale it based on the purr ratio to estimate
+ * the system time */
+ deltascaled = deltascaled * get_paca()->system_time /
+ (get_paca()->system_time + get_paca()->user_time);
delta += get_paca()->system_time;
get_paca()->system_time = 0;
}
account_system_time(tsk, 0, delta);
+ get_paca()->purrdelta = delta;
+ account_system_time_scaled(tsk, deltascaled);
+ get_paca()->spurrdelta = deltascaled;
local_irq_restore(flags);
}
@@ -196,11 +217,17 @@ void account_system_vtime(struct task_st
*/
void account_process_vtime(struct task_struct *tsk)
{
- cputime_t utime;
+ cputime_t utime, utimescaled;
utime = get_paca()->user_time;
get_paca()->user_time = 0;
account_user_time(tsk, utime);
+
+ /* Estimate the scaled utime by scaling the real utime based
+ * on the last spurr to purr ratio */
+ utimescaled = utime * get_paca()->spurrdelta / get_paca()->purrdelta;
+ get_paca()->spurrdelta = get_paca()->purrdelta = 0;
+ account_user_time_scaled(tsk, utimescaled);
}
static void account_process_time(struct pt_regs *regs)
@@ -222,6 +249,7 @@ struct cpu_purr_data {
int initialized; /* thread is running */
u64 tb; /* last TB value read */
u64 purr; /* last PURR value read */
+ u64 spurr; /* last SPURR value read */
};
/*
Index: linux-2.6-ozlabs/include/asm-powerpc/paca.h
===================================================================
--- linux-2.6-ozlabs.orig/include/asm-powerpc/paca.h
+++ linux-2.6-ozlabs/include/asm-powerpc/paca.h
@@ -103,6 +103,9 @@ struct paca_struct {
u64 user_time; /* accumulated usermode TB ticks */
u64 system_time; /* accumulated system TB ticks */
u64 startpurr; /* PURR/TB value snapshot */
+ u64 startspurr; /* SPURR value snapshot */
+ u64 purrdelta; /* FIXME: document */
+ u64 spurrdelta; /* FIXME: document */
};
extern struct paca_struct paca[];
Michael Neuling wrote:
> This adds POWERPC specific hooks for scaled time accounting.
>
> POWER6 includes a SPURR register. The SPURR is based off the PURR
> register but is scaled based on CPU frequency and issue rates. This
> gives a more accurate account of the instructions used per task. The
> PURR and timebase will be constant relative to the wall clock,
> irrespective of the CPU frequency.
>
> This implementation reads the SPURR register in account_system_vtime
> which is only call called on context witch and hard and soft irq entry
> and exit. The percentage of user and system time is then estimated
> using the ratio of these accounted by the PURR. If the SPURR is not
> present, the PURR read.
>
> An earlier implementation of this patch read the SPURR whenever the
> PURR was read, which included the system call entry and exit path.
> Unfortunately this showed a performance regression on lmbench runs, so
> was re-implemented.
>
> I've included the lmbench results here when run bare metal on POWER6.
> 1st column is the unpatch results. 2nd column is the results using the
> below patch and the 3rd is the % diff of these results from the base.
> 4th and 5th columns are the results and % differnce from the base
> using the older patch (SPURR read in syscall entry/exit path).
>
> Base Scaled-Acct SPURR-in-syscall
> Result Result % diff Result % diff
> Simple syscall: 0.3086 0.3086 0.0000 0.3452 11.8600
> Simple read: 0.4591 0.4671 1.7425 0.5044 9.86713
> Simple write: 0.4364 0.4366 0.0458 0.4731 8.40971
> Simple stat: 2.0055 2.0295 1.1967 2.0669 3.06158
> Simple fstat: 0.5962 0.5876 -1.442 0.6368 6.80979
> Simple open/close: 3.1283 3.1009 -0.875 3.2088 2.57328
> Select on 10 fd's: 0.8554 0.8457 -1.133 0.8667 1.32101
> Select on 100 fd's: 3.5292 3.6329 2.9383 3.6664 3.88756
> Select on 250 fd's: 7.9097 8.1881 3.5197 8.2242 3.97613
> Select on 500 fd's: 15.2659 15.836 3.7357 15.873 3.97814
> Select on 10 tcp fd's: 0.9576 0.9416 -1.670 0.9752 1.83792
> Select on 100 tcp fd's: 7.248 7.2254 -0.311 7.2685 0.28283
> Select on 250 tcp fd's: 17.7742 17.707 -0.375 17.749 -0.1406
> Select on 500 tcp fd's: 35.4258 35.25 -0.496 35.286 -0.3929
> Signal handler installation: 0.6131 0.6075 -0.913 0.647 5.52927
> Signal handler overhead: 2.0919 2.1078 0.7600 2.1831 4.35967
> Protection fault: 0.7345 0.7478 1.8107 0.8031 9.33968
> Pipe latency: 33.006 16.398 -50.31 33.475 1.42368
> AF_UNIX sock stream latency: 14.5093 30.910 113.03 30.715 111.692
> Process fork+exit: 219.8 222.8 1.3648 229.37 4.35623
> Process fork+execve: 876.14 873.28 -0.32 868.66 -0.8533
> Process fork+/bin/sh -c: 2830 2876.5 1.6431 2958 4.52296
> File /var/tmp/XXX write bw: 1193497 1195536 0.1708 118657 -0.5799
> Pagefaults on /var/tmp/XXX: 3.1272 3.2117 2.7020 3.2521 3.99398
>
> Also, kernel compile times show no difference with this patch applied.
>
> Signed-off-by: Michael Neuling <[email protected]>
>
> ---
>
> arch/powerpc/kernel/asm-offsets.c | 1 +
> arch/powerpc/kernel/time.c | 32 ++++++++++++++++++++++++++++++--
> include/asm-powerpc/paca.h | 3 +++
> 3 files changed, 34 insertions(+), 2 deletions(-)
>
> Index: linux-2.6-ozlabs/arch/powerpc/kernel/asm-offsets.c
> ===================================================================
> --- linux-2.6-ozlabs.orig/arch/powerpc/kernel/asm-offsets.c
> +++ linux-2.6-ozlabs/arch/powerpc/kernel/asm-offsets.c
> @@ -141,6 +141,7 @@ int main(void)
> DEFINE(PACALPPACAPTR, offsetof(struct paca_struct, lppaca_ptr));
> DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
> DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr));
> + DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr));
> DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
> DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
> DEFINE(PACA_SLBSHADOWPTR, offsetof(struct paca_struct, slb_shadow_ptr));
> Index: linux-2.6-ozlabs/arch/powerpc/kernel/time.c
> ===================================================================
> --- linux-2.6-ozlabs.orig/arch/powerpc/kernel/time.c
> +++ linux-2.6-ozlabs/arch/powerpc/kernel/time.c
> @@ -168,23 +168,44 @@ static u64 read_purr(void)
> }
>
> /*
> + * Read the SPURR on systems that have it, otherwise the purr
> + */
> +static u64 read_spurr(void)
> +{
> + if (cpu_has_feature(CPU_FTR_SPURR))
> + return mfspr(SPRN_SPURR);
> + return read_purr();
> +}
> +
> +/*
> * Account time for a transition between system, hard irq
> * or soft irq state.
> */
> void account_system_vtime(struct task_struct *tsk)
> {
> - u64 now, delta;
> + u64 now, nowscaled, delta, deltascaled;
> unsigned long flags;
>
> local_irq_save(flags);
> now = read_purr();
> delta = now - get_paca()->startpurr;
> get_paca()->startpurr = now;
> + nowscaled = read_spurr();
> + deltascaled = nowscaled - get_paca()->startspurr;
> + get_paca()->startspurr = nowscaled;
> if (!in_interrupt()) {
> + /* deltascaled includes both user and system time.
> + * Hence scale it based on the purr ratio to estimate
> + * the system time */
> + deltascaled = deltascaled * get_paca()->system_time /
> + (get_paca()->system_time + get_paca()->user_time);
> delta += get_paca()->system_time;
> get_paca()->system_time = 0;
> }
> account_system_time(tsk, 0, delta);
> + get_paca()->purrdelta = delta;
> + account_system_time_scaled(tsk, deltascaled);
> + get_paca()->spurrdelta = deltascaled;
> local_irq_restore(flags);
> }
>
> @@ -196,11 +217,17 @@ void account_system_vtime(struct task_st
> */
> void account_process_vtime(struct task_struct *tsk)
> {
> - cputime_t utime;
> + cputime_t utime, utimescaled;
>
> utime = get_paca()->user_time;
> get_paca()->user_time = 0;
> account_user_time(tsk, utime);
> +
> + /* Estimate the scaled utime by scaling the real utime based
> + * on the last spurr to purr ratio */
> + utimescaled = utime * get_paca()->spurrdelta / get_paca()->purrdelta;
The assumption is account_process_vtime() is always called after account_system_vtime(),
is my understanding correct?
> + get_paca()->spurrdelta = get_paca()->purrdelta = 0;
> + account_user_time_scaled(tsk, utimescaled);
> }
>
> static void account_process_time(struct pt_regs *regs)
> @@ -222,6 +249,7 @@ struct cpu_purr_data {
> int initialized; /* thread is running */
> u64 tb; /* last TB value read */
> u64 purr; /* last PURR value read */
> + u64 spurr; /* last SPURR value read */
> };
>
> /*
> Index: linux-2.6-ozlabs/include/asm-powerpc/paca.h
> ===================================================================
> --- linux-2.6-ozlabs.orig/include/asm-powerpc/paca.h
> +++ linux-2.6-ozlabs/include/asm-powerpc/paca.h
> @@ -103,6 +103,9 @@ struct paca_struct {
> u64 user_time; /* accumulated usermode TB ticks */
> u64 system_time; /* accumulated system TB ticks */
> u64 startpurr; /* PURR/TB value snapshot */
> + u64 startspurr; /* SPURR value snapshot */
> + u64 purrdelta; /* FIXME: document */
> + u64 spurrdelta; /* FIXME: document */
> };
>
> extern struct paca_struct paca[];
--
Warm Regards,
Balbir Singh
Linux Technology Center
IBM, ISTL
In message <[email protected]> you wrote:
> Michael Neuling wrote:
> > This adds POWERPC specific hooks for scaled time accounting.
> >
> > POWER6 includes a SPURR register. The SPURR is based off the PURR
> > register but is scaled based on CPU frequency and issue rates. This
> > gives a more accurate account of the instructions used per task. The
> > PURR and timebase will be constant relative to the wall clock,
> > irrespective of the CPU frequency.
> >
> > This implementation reads the SPURR register in account_system_vtime
> > which is only call called on context witch and hard and soft irq entry
> > and exit. The percentage of user and system time is then estimated
> > using the ratio of these accounted by the PURR. If the SPURR is not
> > present, the PURR read.
> >
> > An earlier implementation of this patch read the SPURR whenever the
> > PURR was read, which included the system call entry and exit path.
> > Unfortunately this showed a performance regression on lmbench runs, so
> > was re-implemented.
> >
> > I've included the lmbench results here when run bare metal on POWER6.
> > 1st column is the unpatch results. 2nd column is the results using the
> > below patch and the 3rd is the % diff of these results from the base.
> > 4th and 5th columns are the results and % differnce from the base
> > using the older patch (SPURR read in syscall entry/exit path).
> >
> > Base Scaled-Acct SPURR-in-syscall
> > Result Result % diff Result % diff
> > Simple syscall: 0.3086 0.3086 0.0000 0.3452 11.8600
> > Simple read: 0.4591 0.4671 1.7425 0.5044 9.86713
> > Simple write: 0.4364 0.4366 0.0458 0.4731 8.40971
> > Simple stat: 2.0055 2.0295 1.1967 2.0669 3.06158
> > Simple fstat: 0.5962 0.5876 -1.442 0.6368 6.80979
> > Simple open/close: 3.1283 3.1009 -0.875 3.2088 2.57328
> > Select on 10 fd's: 0.8554 0.8457 -1.133 0.8667 1.32101
> > Select on 100 fd's: 3.5292 3.6329 2.9383 3.6664 3.88756
> > Select on 250 fd's: 7.9097 8.1881 3.5197 8.2242 3.97613
> > Select on 500 fd's: 15.2659 15.836 3.7357 15.873 3.97814
> > Select on 10 tcp fd's: 0.9576 0.9416 -1.670 0.9752 1.83792
> > Select on 100 tcp fd's: 7.248 7.2254 -0.311 7.2685 0.28283
> > Select on 250 tcp fd's: 17.7742 17.707 -0.375 17.749 -0.1406
> > Select on 500 tcp fd's: 35.4258 35.25 -0.496 35.286 -0.3929
> > Signal handler installation: 0.6131 0.6075 -0.913 0.647 5.52927
> > Signal handler overhead: 2.0919 2.1078 0.7600 2.1831 4.35967
> > Protection fault: 0.7345 0.7478 1.8107 0.8031 9.33968
> > Pipe latency: 33.006 16.398 -50.31 33.475 1.42368
> > AF_UNIX sock stream latency: 14.5093 30.910 113.03 30.715 111.692
> > Process fork+exit: 219.8 222.8 1.3648 229.37 4.35623
> > Process fork+execve: 876.14 873.28 -0.32 868.66 -0.8533
> > Process fork+/bin/sh -c: 2830 2876.5 1.6431 2958 4.52296
> > File /var/tmp/XXX write bw: 1193497 1195536 0.1708 118657 -0.5799
> > Pagefaults on /var/tmp/XXX: 3.1272 3.2117 2.7020 3.2521 3.99398
> >
> > Also, kernel compile times show no difference with this patch applied.
> >
> > Signed-off-by: Michael Neuling <[email protected]>
> >
> > ---
> >
> > arch/powerpc/kernel/asm-offsets.c | 1 +
> > arch/powerpc/kernel/time.c | 32 ++++++++++++++++++++++++++++++--
> > include/asm-powerpc/paca.h | 3 +++
> > 3 files changed, 34 insertions(+), 2 deletions(-)
> >
> > Index: linux-2.6-ozlabs/arch/powerpc/kernel/asm-offsets.c
> > ===================================================================
> > --- linux-2.6-ozlabs.orig/arch/powerpc/kernel/asm-offsets.c
> > +++ linux-2.6-ozlabs/arch/powerpc/kernel/asm-offsets.c
> > @@ -141,6 +141,7 @@ int main(void)
> > DEFINE(PACALPPACAPTR, offsetof(struct paca_struct, lppaca_ptr));
> > DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
> > DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr));
> > + DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr));
> > DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
> > DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
> > DEFINE(PACA_SLBSHADOWPTR, offsetof(struct paca_struct, slb_shadow_ptr))
;
> > Index: linux-2.6-ozlabs/arch/powerpc/kernel/time.c
> > ===================================================================
> > --- linux-2.6-ozlabs.orig/arch/powerpc/kernel/time.c
> > +++ linux-2.6-ozlabs/arch/powerpc/kernel/time.c
> > @@ -168,23 +168,44 @@ static u64 read_purr(void)
> > }
> >
> > /*
> > + * Read the SPURR on systems that have it, otherwise the purr
> > + */
> > +static u64 read_spurr(void)
> > +{
> > + if (cpu_has_feature(CPU_FTR_SPURR))
> > + return mfspr(SPRN_SPURR);
> > + return read_purr();
> > +}
> > +
> > +/*
> > * Account time for a transition between system, hard irq
> > * or soft irq state.
> > */
> > void account_system_vtime(struct task_struct *tsk)
> > {
> > - u64 now, delta;
> > + u64 now, nowscaled, delta, deltascaled;
> > unsigned long flags;
> >
> > local_irq_save(flags);
> > now = read_purr();
> > delta = now - get_paca()->startpurr;
> > get_paca()->startpurr = now;
> > + nowscaled = read_spurr();
> > + deltascaled = nowscaled - get_paca()->startspurr;
> > + get_paca()->startspurr = nowscaled;
> > if (!in_interrupt()) {
> > + /* deltascaled includes both user and system time.
> > + * Hence scale it based on the purr ratio to estimate
> > + * the system time */
> > + deltascaled = deltascaled * get_paca()->system_time /
> > + (get_paca()->system_time + get_paca()->user_time);
> > delta += get_paca()->system_time;
> > get_paca()->system_time = 0;
> > }
> > account_system_time(tsk, 0, delta);
> > + get_paca()->purrdelta = delta;
> > + account_system_time_scaled(tsk, deltascaled);
> > + get_paca()->spurrdelta = deltascaled;
> > local_irq_restore(flags);
> > }
> >
> > @@ -196,11 +217,17 @@ void account_system_vtime(struct task_st
> > */
> > void account_process_vtime(struct task_struct *tsk)
> > {
> > - cputime_t utime;
> > + cputime_t utime, utimescaled;
> >
> > utime = get_paca()->user_time;
> > get_paca()->user_time = 0;
> > account_user_time(tsk, utime);
> > +
> > + /* Estimate the scaled utime by scaling the real utime based
> > + * on the last spurr to purr ratio */
> > + utimescaled = utime * get_paca()->spurrdelta / get_paca()->purrdelta;
>
>
> The assumption is account_process_vtime() is always called after
> account_system_vtime(), is my understanding correct?
Yes, we use last spurr/purr ratio grabbed in account_system_vtime to
scale utime appropriately.
Mikey