nohz tweaking
Subsystems (3)
cover nohz tweaking
Greetings,
the two remainting patches of the nohz performance work I've been doing. Both have been sent to the mailing lists before. Ingo had a comment about patch #1, but no one but me seems to be interested in patch #2. Neverless I would like to get both patches upstream. I can create a branch for them on git390 but I feel that they should go the path all the other nohz/time/clocksource patches went.
Signature · 4 lines
blue skies, Martin. "Reality continues to ruin my life." - Calvin.
PATCH 1/2 nohz: reuse ktime in sub-functions of tick_check_idle.
From: Martin Schwidefsky <[email protected]>
On a system with NOHZ=y tick_check_idle calls tick_nohz_stop_idle and tick_nohz_update_jiffies. Given the right conditions (ts->idle_active and/or ts->tick_stopped) both function get a time stamp with ktime_get. The same time stamp can be reused if both function require one.
On s390 this change has the additional benefit that gcc inlines the tick_nohz_stop_idle function into tick_check_idle. The number of instructions to execute tick_check_idle drops from 225 to 144 (without the ktime_get optimization it is 367 vs 215 instructions).
before:
0) | tick_check_idle() {
0) | tick_nohz_stop_idle() {
0) | ktime_get() {
0) | read_tod_clock() {
0) 0.601 us | }
0) 1.765 us | }
0) 3.047 us | }
0) | ktime_get() {
0) | read_tod_clock() {
0) 0.570 us | }
0) 1.727 us | }
0) | tick_do_update_jiffies64() {
0) 0.609 us | }
0) 8.055 us | }after:
0) | tick_check_idle() {
0) | ktime_get() {
0) | read_tod_clock() {
0) 0.617 us | }
0) 1.773 us | }
0) | tick_do_update_jiffies64() {
0) 0.593 us | }
0) 4.477 us | }---
kernel/time/tick-sched.c | 62 +++++++++++++++++++++++++---------------------- 1 file changed, 33 insertions(+), 29 deletions(-)
kernel/time/tick-sched.c +33 -29
@@ -134,18 +134,13 @@* value. We do this unconditionally on any cpu, as we don't know whether the * cpu, which has the update task assigned is in a long sleep. */ -static void tick_nohz_update_jiffies (void ) +static void tick_nohz_update_jiffies (ktime_t now) {int cpu =smp_processor_id ();struct tick_sched *ts = &per_cpu (tick_cpu_sched, cpu);unsigned long flags; -ktime_t now; - -if (!ts->tick_stopped) -return ;cpumask_clear_cpu (cpu, nohz_cpu_mask); - now =ktime_get (); ts->idle_waketime = now;local_irq_save (flags);
@@ -155,20 +150,17 @@touch_softlockup_watchdog (); } -static void tick_nohz_stop_idle (int cpu) +static void tick_nohz_stop_idle (int cpu,ktime_t now) {struct tick_sched *ts = &per_cpu (tick_cpu_sched, cpu); +ktime_t delta; -if (ts->idle_active) { -ktime_t now, delta; - now =ktime_get (); - delta =ktime_sub (now, ts->idle_entrytime); - ts->idle_lastupdate = now; - ts->idle_sleeptime =ktime_add (ts->idle_sleeptime, delta); - ts->idle_active =0 ; + delta =ktime_sub (now, ts->idle_entrytime); + ts->idle_lastupdate = now; + ts->idle_sleeptime =ktime_add (ts->idle_sleeptime, delta); + ts->idle_active =0 ; -sched_clock_idle_wakeup_event (0 ); - } +sched_clock_idle_wakeup_event (0 ); }static ktime_t tick_nohz_start_idle (struct tick_sched *ts)
@@ -431,7 +423,11 @@ktime_t now;local_irq_disable (); -tick_nohz_stop_idle (cpu); +if (ts->idle_active || (ts->inidle && ts->tick_stopped)) + now =ktime_get (); + +if (ts->idle_active) +tick_nohz_stop_idle (cpu, now);if (!ts->inidle || !ts->tick_stopped) { ts->inidle =0 ;
@@ -445,7 +441,6 @@/* Update jiffies first */ select_nohz_load_balancer (0 ); - now =ktime_get ();tick_do_update_jiffies64 (now);cpumask_clear_cpu (cpu, nohz_cpu_mask);
@@ -579,22 +574,18 @@* timer and do not touch the other magic bits which need to be done * when idle is left. */ -static void tick_nohz_kick_tick (int cpu) +static void tick_nohz_kick_tick (int cpu,ktime_t now) {#if 0 /* Switch back to 2.6.27 behaviour */ struct tick_sched *ts = &per_cpu (tick_cpu_sched, cpu); -ktime_t delta, now; - -if (!ts->tick_stopped) -return ; +ktime_t delta;/* * Do not touch the tick device, when the next expiry is either * already reached or less/equal than the tick period. */ - now =ktime_get (); delta =ktime_sub (hrtimer_get_expires (&ts->sched_timer), now);if (delta.tv64 <= tick_period.tv64)return ;
@@ -603,9 +594,26 @@ #endif } +static inline void tick_check_nohz (int cpu) +{ +struct tick_sched *ts = &per_cpu (tick_cpu_sched, cpu); +ktime_t now; + +if (!ts->idle_active && !ts->tick_stopped) +return ; + now =ktime_get (); +if (ts->idle_active) +tick_nohz_stop_idle (cpu, now); +if (ts->tick_stopped) { +tick_nohz_update_jiffies (now); +tick_nohz_kick_tick (cpu, now); + } +} +#else static inline void tick_nohz_switch_to_nohz (void ) { } +static inline void tick_check_nohz (int cpu) { }#endif /* NO_HZ */
@@ -615,11 +623,7 @@void tick_check_idle (int cpu) {tick_check_oneshot_broadcast (cpu); -#ifdef CONFIG_NO_HZ -tick_nohz_stop_idle (cpu); -tick_nohz_update_jiffies (); -tick_nohz_kick_tick (cpu); -#endif +tick_check_nohz (cpu); }/*
[tip:timers/core] nohz: Reuse ktime in sub-functions of tick_check_idle.
Commit-ID: eed3b9cf3fe3fcc7a50238dfcab63a63914e8f42 Gitweb: http://git.kernel.org/tip/eed3b9cf3fe3fcc7a50238dfcab63a63914e8f42 Author: Martin Schwidefsky <[email protected]> AuthorDate: Tue, 29 Sep 2009 14:25:15 +0200 Committer: Thomas Gleixner <[email protected]> CommitDate: Thu, 5 Nov 2009 07:53:53 +0100
nohz: Reuse ktime in sub-functions of tick_check_idle.
On a system with NOHZ=y tick_check_idle calls tick_nohz_stop_idle and tick_nohz_update_jiffies. Given the right conditions (ts->idle_active and/or ts->tick_stopped) both function get a time stamp with ktime_get. The same time stamp can be reused if both function require one.
On s390 this change has the additional benefit that gcc inlines the tick_nohz_stop_idle function into tick_check_idle. The number of instructions to execute tick_check_idle drops from 225 to 144 (without the ktime_get optimization it is 367 vs 215 instructions).
before:
0) | tick_check_idle() {
0) | tick_nohz_stop_idle() {
0) | ktime_get() {
0) | read_tod_clock() {
0) 0.601 us | }
0) 1.765 us | }
0) 3.047 us | }
0) | ktime_get() {
0) | read_tod_clock() {
0) 0.570 us | }
0) 1.727 us | }
0) | tick_do_update_jiffies64() {
0) 0.609 us | }
0) 8.055 us | }after:
0) | tick_check_idle() {
0) | ktime_get() {
0) | read_tod_clock() {
0) 0.617 us | }
0) 1.773 us | }
0) | tick_do_update_jiffies64() {
0) 0.593 us | }
0) 4.477 us | }LKML-Reference: <[email protected]>
--- kernel/time/tick-sched.c | 62 ++++++++++++++++++++++++--------------------- 1 files changed, 33 insertions(+), 29 deletions(-)
kernel/time/tick-sched.c +33 -29
@@ -134,18 +134,13 @@ __setup("nohz=", setup_tick_nohz);* value. We do this unconditionally on any cpu, as we don't know whether the * cpu, which has the update task assigned is in a long sleep. */ -static void tick_nohz_update_jiffies (void ) +static void tick_nohz_update_jiffies (ktime_t now) {int cpu =smp_processor_id ();struct tick_sched *ts = &per_cpu (tick_cpu_sched, cpu);unsigned long flags; -ktime_t now; - -if (!ts->tick_stopped) -return ;cpumask_clear_cpu (cpu, nohz_cpu_mask); - now =ktime_get (); ts->idle_waketime = now;local_irq_save (flags);
@@ -155,20 +150,17 @@ static void tick_nohz_update_jiffies(void)touch_softlockup_watchdog (); } -static void tick_nohz_stop_idle (int cpu) +static void tick_nohz_stop_idle (int cpu,ktime_t now) {struct tick_sched *ts = &per_cpu (tick_cpu_sched, cpu); +ktime_t delta; -if (ts->idle_active) { -ktime_t now, delta; - now =ktime_get (); - delta =ktime_sub (now, ts->idle_entrytime); - ts->idle_lastupdate = now; - ts->idle_sleeptime =ktime_add (ts->idle_sleeptime, delta); - ts->idle_active =0 ; + delta =ktime_sub (now, ts->idle_entrytime); + ts->idle_lastupdate = now; + ts->idle_sleeptime =ktime_add (ts->idle_sleeptime, delta); + ts->idle_active =0 ; -sched_clock_idle_wakeup_event (0 ); - } +sched_clock_idle_wakeup_event (0 ); }static ktime_t tick_nohz_start_idle (struct tick_sched *ts)
@@ -431,7 +423,11 @@ void tick_nohz_restart_sched_tick(void)ktime_t now;local_irq_disable (); -tick_nohz_stop_idle (cpu); +if (ts->idle_active || (ts->inidle && ts->tick_stopped)) + now =ktime_get (); + +if (ts->idle_active) +tick_nohz_stop_idle (cpu, now);if (!ts->inidle || !ts->tick_stopped) { ts->inidle =0 ;
@@ -445,7 +441,6 @@ void tick_nohz_restart_sched_tick(void)/* Update jiffies first */ select_nohz_load_balancer (0 ); - now =ktime_get ();tick_do_update_jiffies64 (now);cpumask_clear_cpu (cpu, nohz_cpu_mask);
@@ -579,22 +574,18 @@ static void tick_nohz_switch_to_nohz(void)* timer and do not touch the other magic bits which need to be done * when idle is left. */ -static void tick_nohz_kick_tick (int cpu) +static void tick_nohz_kick_tick (int cpu,ktime_t now) {#if 0 /* Switch back to 2.6.27 behaviour */ struct tick_sched *ts = &per_cpu (tick_cpu_sched, cpu); -ktime_t delta, now; - -if (!ts->tick_stopped) -return ; +ktime_t delta;/* * Do not touch the tick device, when the next expiry is either * already reached or less/equal than the tick period. */ - now =ktime_get (); delta =ktime_sub (hrtimer_get_expires (&ts->sched_timer), now);if (delta.tv64 <= tick_period.tv64)return ;
@@ -603,9 +594,26 @@ static void tick_nohz_kick_tick(int cpu) #endif } +static inline void tick_check_nohz (int cpu) +{ +struct tick_sched *ts = &per_cpu (tick_cpu_sched, cpu); +ktime_t now; + +if (!ts->idle_active && !ts->tick_stopped) +return ; + now =ktime_get (); +if (ts->idle_active) +tick_nohz_stop_idle (cpu, now); +if (ts->tick_stopped) { +tick_nohz_update_jiffies (now); +tick_nohz_kick_tick (cpu, now); + } +} +#else static inline void tick_nohz_switch_to_nohz (void ) { } +static inline void tick_check_nohz (int cpu) { }#endif /* NO_HZ */
@@ -615,11 +623,7 @@ static inline void tick_nohz_switch_to_nohz(void) { }void tick_check_idle (int cpu) {tick_check_oneshot_broadcast (cpu); -#ifdef CONFIG_NO_HZ -tick_nohz_stop_idle (cpu); -tick_nohz_update_jiffies (); -tick_nohz_kick_tick (cpu); -#endif +tick_check_nohz (cpu); }/*
PATCH 2/2 nohz: introduce arch_needs_cpu
In reply to Martin SchwidefskyFrom: Martin Schwidefsky <[email protected]>
Allow the architecture to request a normal jiffy tick when the system goes idle and tick_nohz_stop_sched_tick is called . On s390 the hook is used to prevent the system going fully idle if there has been an interrupt other than a clock comparator interrupt since the last wakeup.
On s390 the HiperSockets response time for 1 connection ping-pong goes down from 42 to 34 microseconds. The CPU cost decreases by 27%.
---
arch/s390/include/asm/cputime.h | 8 ++++++++ arch/s390/kernel/s390_ext.c | 2 ++ arch/s390/kernel/vtime.c | 2 ++ drivers/s390/cio/cio.c | 1 + include/linux/tick.h | 3 +++ kernel/time/tick-sched.c | 13 ++++++++----- 6 files changed, 24 insertions(+), 5 deletions(-)
arch/s390/include/asm/cputime.h +8 -0
@@ -183,6 +183,7 @@unsigned long long idle_count;unsigned long long idle_enter;unsigned long long idle_time; +int nohz_delay; }; DECLARE_PER_CPU(struct s390_idle_data, s390_idle);
@@ -198,4 +199,11 @@ vtime_start_cpu(); } +static inline int s390_nohz_delay (int cpu) +{ +return per_cpu (s390_idle, cpu).nohz_delay !=0 ; +} + +#define arch_needs_cpu (cpu) s390_nohz_delay(cpu) +#endif /* _S390_CPUTIME_H */
arch/s390/kernel/s390_ext.c +2 -0
@@ -126,6 +126,8 @@/* Serve timer interrupts first. */ clock_comparator_work ();kstat_cpu (smp_processor_id ()).irqs[EXTERNAL_INTERRUPT ]++; +if (code !=0x1004 ) +__get_cpu_var (s390_idle).nohz_delay =1 ; index =ext_hash (code);for (p = ext_int_hash[index]; p; p = p->next) {if (likely (p->code == code))
arch/s390/kernel/vtime.c +2 -0
@@ -167,6 +167,8 @@/* Wait for external, I/O or machine check interrupt. */ psw.mask = psw_kernel_bits |PSW_MASK_WAIT |PSW_MASK_IO |PSW_MASK_EXT ; + idle->nohz_delay =0 ; +/* Check if the CPU timer needs to be reprogrammed. */ if (vq->do_spt) {__u64 vmax =VTIMER_MAX_SLICE ;
drivers/s390/cio/cio.c +1 -0
@@ -618,6 +618,7 @@ old_regs =set_irq_regs (regs);s390_idle_check ();irq_enter (); +__get_cpu_var (s390_idle).nohz_delay =1 ;if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator)/* Serve timer interrupts first. */ clock_comparator_work ();
include/linux/tick.h +3 -0
@@ -98,6 +98,9 @@extern struct tick_sched *tick_get_tick_sched (int cpu);extern void tick_check_idle (int cpu);extern int tick_oneshot_mode_active (void ); +# ifndef arch_needs_cpu +# define arch_needs_cpu (cpu) (0) +# endif # else static inline void tick_clock_notify (void ) { }static inline int tick_check_oneshot_change (int allow_nohz) {return 0 ; }
kernel/time/tick-sched.c +8 -5
@@ -264,12 +264,15 @@ last_jiffies = jiffies; }while (read_seqretry (&xtime_lock, seq)); -/* Get the next timer wheel timer */ - next_jiffies =get_next_timer_interrupt (last_jiffies); - delta_jiffies = next_jiffies - last_jiffies; - -if (rcu_needs_cpu (cpu) ||printk_needs_cpu (cpu)) +if (rcu_needs_cpu (cpu) ||printk_needs_cpu (cpu) || +arch_needs_cpu (cpu)) { + next_jiffies = last_jiffies +1 ; delta_jiffies =1 ; + }else { +/* Get the next timer wheel timer */ + next_jiffies =get_next_timer_interrupt (last_jiffies); + delta_jiffies = next_jiffies - last_jiffies; + }/* * Do not stop the tick, if we are only one off * or if the cpu is required for rcu
[tip:timers/core] nohz: Introduce arch_needs_cpu
Commit-ID: 3c5d92a0cfb5103c0d5ab74d4ae6373d3af38148 Gitweb: http://git.kernel.org/tip/3c5d92a0cfb5103c0d5ab74d4ae6373d3af38148 Author: Martin Schwidefsky <[email protected]> AuthorDate: Tue, 29 Sep 2009 14:25:16 +0200 Committer: Thomas Gleixner <[email protected]> CommitDate: Thu, 5 Nov 2009 07:53:53 +0100
nohz: Introduce arch_needs_cpu
Allow the architecture to request a normal jiffy tick when the system goes idle and tick_nohz_stop_sched_tick is called . On s390 the hook is used to prevent the system going fully idle if there has been an interrupt other than a clock comparator interrupt since the last wakeup.
On s390 the HiperSockets response time for 1 connection ping-pong goes down from 42 to 34 microseconds. The CPU cost decreases by 27%.
LKML-Reference: <[email protected]>
--- arch/s390/include/asm/cputime.h | 8 ++++++++ arch/s390/kernel/s390_ext.c | 2 ++ arch/s390/kernel/vtime.c | 2 ++ drivers/s390/cio/cio.c | 1 + include/linux/tick.h | 3 +++ kernel/time/tick-sched.c | 13 ++++++++----- 6 files changed, 24 insertions(+), 5 deletions(-)
arch/s390/include/asm/cputime.h +8 -0
@@ -183,6 +183,7 @@ struct s390_idle_data {unsigned long long idle_count;unsigned long long idle_enter;unsigned long long idle_time; +int nohz_delay; }; DECLARE_PER_CPU(struct s390_idle_data, s390_idle);
@@ -198,4 +199,11 @@ static inline void s390_idle_check(void) vtime_start_cpu(); } +static inline int s390_nohz_delay (int cpu) +{ +return per_cpu (s390_idle, cpu).nohz_delay !=0 ; +} + +#define arch_needs_cpu (cpu) s390_nohz_delay(cpu) +#endif /* _S390_CPUTIME_H */
arch/s390/kernel/s390_ext.c +2 -0
@@ -126,6 +126,8 @@ void __irq_entry do_extint(struct pt_regs *regs, unsigned short code)/* Serve timer interrupts first. */ clock_comparator_work ();kstat_cpu (smp_processor_id ()).irqs[EXTERNAL_INTERRUPT ]++; +if (code !=0x1004 ) +__get_cpu_var (s390_idle).nohz_delay =1 ; index =ext_hash (code);for (p = ext_int_hash[index]; p; p = p->next) {if (likely (p->code == code))
arch/s390/kernel/vtime.c +2 -0
@@ -167,6 +167,8 @@ void vtime_stop_cpu(void)/* Wait for external, I/O or machine check interrupt. */ psw.mask = psw_kernel_bits |PSW_MASK_WAIT |PSW_MASK_IO |PSW_MASK_EXT ; + idle->nohz_delay =0 ; +/* Check if the CPU timer needs to be reprogrammed. */ if (vq->do_spt) {__u64 vmax =VTIMER_MAX_SLICE ;
drivers/s390/cio/cio.c +1 -0
@@ -618,6 +618,7 @@ void __irq_entry do_IRQ(struct pt_regs *regs) old_regs =set_irq_regs (regs);s390_idle_check ();irq_enter (); +__get_cpu_var (s390_idle).nohz_delay =1 ;if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator)/* Serve timer interrupts first. */ clock_comparator_work ();
include/linux/tick.h +3 -0
@@ -98,6 +98,9 @@ extern int tick_check_oneshot_change(int allow_nohz);extern struct tick_sched *tick_get_tick_sched (int cpu);extern void tick_check_idle (int cpu);extern int tick_oneshot_mode_active (void ); +# ifndef arch_needs_cpu +# define arch_needs_cpu (cpu) (0) +# endif # else static inline void tick_clock_notify (void ) { }static inline int tick_check_oneshot_change (int allow_nohz) {return 0 ; }
kernel/time/tick-sched.c +8 -5
@@ -264,12 +264,15 @@ void tick_nohz_stop_sched_tick(int inidle) last_jiffies = jiffies; }while (read_seqretry (&xtime_lock, seq)); -/* Get the next timer wheel timer */ - next_jiffies =get_next_timer_interrupt (last_jiffies); - delta_jiffies = next_jiffies - last_jiffies; - -if (rcu_needs_cpu (cpu) ||printk_needs_cpu (cpu)) +if (rcu_needs_cpu (cpu) ||printk_needs_cpu (cpu) || +arch_needs_cpu (cpu)) { + next_jiffies = last_jiffies +1 ; delta_jiffies =1 ; + }else { +/* Get the next timer wheel timer */ + next_jiffies =get_next_timer_interrupt (last_jiffies); + delta_jiffies = next_jiffies - last_jiffies; + }/* * Do not stop the tick, if we are only one off * or if the cpu is required for rcu
Martin,
Quoted 7 lines · Martin Schwidefsky
Greetings,
the two remainting patches of the nohz performance work I've been doing. Both have been sent to the mailing lists before. Ingo had a comment about patch #1, but no one but me seems to be interested in patch #2. Neverless I would like to get both patches upstream. I can create a branch for them on git390 but I feel that they should go the path all the other nohz/time/clocksource patches went.
Sorry, that's my fault. I forgot them over the watchdog wreckage. Picking them up now.
Thanks,
tglx
Quoted 12 lines · On Wed, 30 Sep 2009 12:06:42 +0200 (CEST) Thomas Gleixner <[email protected]>…
Martin,
Quoted 7 lines · Martin Schwidefsky
Greetings,
the two remainting patches of the nohz performance work I've been doing. Both have been sent to the mailing lists before. Ingo had a comment about patch #1, but no one but me seems to be interested in patch #2. Neverless I would like to get both patches upstream. I can create a branch for them on git390 but I feel that they should go the path all the other nohz/time/clocksource patches went.
Quoted 2 lines
Sorry, that's my fault. I forgot them over the watchdog wreckage. Picking them up now.
Thats great, thanks. And yes the clocksource/watchdog problems have been painful..
Signature · 4 lines
blue skies, Martin. "Reality continues to ruin my life." - Calvin.
Moin Thomas,
Quoted 12 lines · On Wed, 30 Sep 2009 12:06:42 +0200 (CEST) Thomas Gleixner <[email protected]>…
Martin,
Quoted 7 lines · Martin Schwidefsky
Greetings,
the two remainting patches of the nohz performance work I've been doing. Both have been sent to the mailing lists before. Ingo had a comment about patch #1, but no one but me seems to be interested in patch #2. Neverless I would like to get both patches upstream. I can create a branch for them on git390 but I feel that they should go the path all the other nohz/time/clocksource patches went.
Quoted 2 lines
Sorry, that's my fault. I forgot them over the watchdog wreckage. Picking them up now.
I could not find the patches on tip timers/core. Where did you put them ?
Signature · 4 lines
blue skies, Martin. "Reality continues to ruin my life." - Calvin.
Quoted 17 lines · Martin Schwidefsky
Moin Thomas,
Quoted 12 lines · On Wed, 30 Sep 2009 12:06:42 +0200 (CEST) Thomas Gleixner <[email protected]>…
Martin,
Quoted 7 lines · Martin Schwidefsky
Greetings,
the two remainting patches of the nohz performance work I've been doing. Both have been sent to the mailing lists before. Ingo had a comment about patch #1, but no one but me seems to be interested in patch #2. Neverless I would like to get both patches upstream. I can create a branch for them on git390 but I feel that they should go the path all the other nohz/time/clocksource patches went.
Quoted 4 lines
Quoted 2 lines
Sorry, that's my fault. I forgot them over the watchdog wreckage. Picking them up now.
I could not find the patches on tip timers/core. Where did you put them ?
these are the currently pending patches in tip:timers/core:
3c5d92a: nohz: Introduce arch_needs_cpu
eed3b9c: nohz: Reuse ktime in sub-functions of tick_check_idle. 7bc7d63: time: Remove xtime_cache
a092ff0: time: Implement logarithmic time accumulation
Ingo
Hi Ingo,
Quoted 22 lines · On Fri, 6 Nov 2009 09:41:38 +0100 Ingo Molnar <[email protected]> wrote:
Quoted 20 lines · Martin Schwidefsky
Moin Thomas,
Quoted 14 lines · On Wed, 30 Sep 2009 12:06:42 +0200 (CEST) Thomas Gleixner <[email protected]>…
Martin,
Quoted 7 lines · Martin Schwidefsky
Greetings,
the two remainting patches of the nohz performance work I've been doing. Both have been sent to the mailing lists before. Ingo had a comment about patch #1, but no one but me seems to be interested in patch #2. Neverless I would like to get both patches upstream. I can create a branch for them on git390 but I feel that they should go the path all the other nohz/time/clocksource patches went.Sorry, that's my fault. I forgot them over the watchdog wreckage. Picking them up now.
Quoted 8 lines
Quoted 1 line
I could not find the patches on tip timers/core. Where did you put them ?
these are the currently pending patches in tip:timers/core:
3c5d92a: nohz: Introduce
arch_needs_cpu
eed3b9c: nohz: Reuse ktime in sub-functions oftick_check_idle. 7bc7d63: time: Removextime_cache
a092ff0: time: Implement logarithmic time accumulation
Thanks for the list. Thomas added 3c5d92a and eed3b9c yesterday and I am happy now. I have two more optimization patches for the clockevents code, but I'm not don't quite content with them yet.
Signature · 4 lines
blue skies, Martin. "Reality continues to ruin my life." - Calvin.