Housekeeping subsystem v6
Subsystems (8)
Frederic Weisbecker
maintainerIngo,
Please pull the core/isolation-v7 branch that can be found at:
git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
core/isolation-v7
HEAD: 69dc2180d1f17ff1f861c7231f4a07423c30842a
Changes since last take:
* Move kernel/housekeeping.c to kernel/sched/isolation.c and linux/housekeeping.h to linux/sched/isolation.h
* Fix tilegx build error reported by Kbuild test robot
* Rebase against latest tip:sched/core
Thanks,
Frederic
---
Frederic Weisbecker (12):
housekeeping: Move housekeeping related code to its own file
watchdog: Use housekeeping_cpumask() instead of ad-hoc version
housekeeping: Provide a dynamic off-case to housekeeping_any_cpu()
housekeeping: Make housekeeping cpumask private
housekeeping: Use its own static key
housekeeping: Rename is_housekeeping_cpu to housekeeping_cpu
housekeeping: Move it under its own config, independent from NO_HZ
housekeeping: Introduce housekeeping flags
housekeeping: Handle the nohz_full= parameter
housekeeping: Move isolcpus to housekeeping
housekeeping: Add basic isolcpus flags
housekeeping: Document isolcpus flags
Documentation/admin-guide/kernel-parameters.txt | 33 +++-- drivers/base/cpu.c | 11 +- drivers/net/ethernet/tile/tilegx.c | 6 +- include/linux/sched.h | 2 - include/linux/sched/isolation.h | 51 ++++++++ include/linux/tick.h | 39 +----- init/Kconfig | 7 ++ init/main.c | 2 + kernel/cgroup/cpuset.c | 15 +-- kernel/rcu/tree_plugin.h | 3 +- kernel/rcu/update.c | 3 +- kernel/sched/Makefile | 1 + kernel/sched/core.c | 25 +--- kernel/sched/fair.c | 3 +- kernel/sched/isolation.c | 155 ++++++++++++++++++++++++ kernel/sched/topology.c | 24 +--- kernel/time/tick-sched.c | 31 +---- kernel/watchdog.c | 13 +- 18 files changed, 282 insertions(+), 142 deletions(-)
Frederic Weisbecker
maintainerPATCH 1/12 housekeeping: Move housekeeping related code to its own file
The housekeeping code is currently tied to the nohz code. As we are planning to make housekeeping independant from it, start with moving the relevant code to its own file.
Acked-by Paul E. McKenney <[email protected]>
Signed-off-by Frederic Weisbecker <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Wanpeng Li <[email protected]>
--- drivers/net/ethernet/tile/tilegx.c | 2 +- include/linux/sched/isolation.h | 56 ++++++++++++++++++++++++++++++++++++++ include/linux/tick.h | 37 ------------------------- init/main.c | 2 ++ kernel/rcu/tree_plugin.h | 1 + kernel/rcu/update.c | 1 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 1 + kernel/sched/fair.c | 1 + kernel/sched/isolation.c | 33 ++++++++++++++++++++++ kernel/time/tick-sched.c | 18 ------------ kernel/watchdog.c | 1 + 12 files changed, 98 insertions(+), 56 deletions(-) create mode 100644 include/linux/sched/isolation.h create mode 100644 kernel/sched/isolation.c
drivers/net/ethernet/tile/tilegx.c +1 -1
@@ -40,7 +40,7 @@#include <linux/tcp.h> #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> -#include <linux/tick.h> +#include <linux/sched/isolation.h> #include <asm/checksum.h> #include <asm/homecache.h>
include/linux/sched/isolation.h new file +56 -0
56 lines not on this page · raw message
include/linux/tick.h +0 -37
@@ -137,7 +137,6 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }#ifdef CONFIG_NO_HZ_FULL extern bool tick_nohz_full_running;extern cpumask_var_t tick_nohz_full_mask; -extern cpumask_var_t housekeeping_mask;static inline bool tick_nohz_full_enabled (void ) {
@@ -161,11 +160,6 @@ static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask)cpumask_or (mask, mask, tick_nohz_full_mask); } -static inline int housekeeping_any_cpu (void ) -{ -return cpumask_any_and (housekeeping_mask, cpu_online_mask); -} -extern void tick_nohz_dep_set (enum tick_dep_bits bit);extern void tick_nohz_dep_clear (enum tick_dep_bits bit);extern void tick_nohz_dep_set_cpu (int cpu,enum tick_dep_bits bit);
@@ -235,10 +229,6 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal,extern void tick_nohz_full_kick_cpu (int cpu);extern void __tick_nohz_task_switch (void );#else -static inline int housekeeping_any_cpu (void ) -{ -return smp_processor_id (); -}static inline bool tick_nohz_full_enabled (void ) {return false; }static inline bool tick_nohz_full_cpu (int cpu) {return false; }static inline void tick_nohz_full_add_cpus_to (struct cpumask *mask) { }
@@ -260,33 +250,6 @@ static inline void tick_nohz_full_kick_cpu(int cpu) { }static inline void __tick_nohz_task_switch (void ) { }#endif -static inline const struct cpumask *housekeeping_cpumask (void ) -{ -#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) -return housekeeping_mask; -#endif -return cpu_possible_mask; -} - -static inline bool is_housekeeping_cpu (int cpu) -{ -#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) -return cpumask_test_cpu (cpu, housekeeping_mask); -#endif -return true; -} - -static inline void housekeeping_affine (struct task_struct *t) -{ -#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) -set_cpus_allowed_ptr (t, housekeeping_mask); - -#endif -} -static inline void tick_nohz_task_switch (void ) {if (tick_nohz_full_enabled ())
init/main.c +2 -0
@@ -46,6 +46,7 @@#include <linux/cgroup.h> #include <linux/efi.h> #include <linux/tick.h> +#include <linux/sched/isolation.h> #include <linux/interrupt.h> #include <linux/taskstats_kern.h> #include <linux/delayacct.h>
@@ -606,6 +607,7 @@ asmlinkage __visible void __init start_kernel(void)early_irq_init ();init_IRQ ();tick_init (); +housekeeping_init ();rcu_init_nohz ();init_timers ();hrtimers_init ();
kernel/rcu/tree_plugin.h +1 -0
@@ -29,6 +29,7 @@#include <linux/oom.h> #include <linux/sched/debug.h> #include <linux/smpboot.h> +#include <linux/sched/isolation.h> #include <uapi/linux/sched/types.h> #include "../time/tick-internal.h"
kernel/rcu/update.c +1 -0
@@ -51,6 +51,7 @@#include <linux/kthread.h> #include <linux/tick.h> #include <linux/rcupdate_wait.h> +#include <linux/sched/isolation.h> #define CREATE_TRACE_POINTS
kernel/sched/Makefile +1 -0
@@ -26,3 +26,4 @@ obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o +obj-$(CONFIG_NO_HZ_FULL) += isolation.o
kernel/sched/core.c +1 -0
@@ -26,6 +26,7 @@#include <linux/profile.h> #include <linux/security.h> #include <linux/syscalls.h> +#include <linux/sched/isolation.h> #include <asm/switch_to.h> #include <asm/tlb.h>
kernel/sched/fair.c +1 -0
@@ -32,6 +32,7 @@#include <linux/mempolicy.h> #include <linux/migrate.h> #include <linux/task_work.h> +#include <linux/sched/isolation.h> #include <trace/events/sched.h>
kernel/sched/isolation.c new file +33 -0
@@ -0,0 +1,33 @@ +/* +* Housekeeping management. Manage the targets for routine code that can run on +* any CPU: unbound workqueues, timers, kthreads and any offloadable work. +* +* Copyright (C) 2017 Red Hat, Inc., Frederic Weisbecker +* +*/ + +#include <linux/sched/isolation.h> +#include <linux/tick.h> +#include <linux/init.h> +#include <linux/kernel.h> + +cpumask_var_t housekeeping_mask; + +void __init housekeeping_init (void ) +{ +if (!tick_nohz_full_enabled ()) +return ; + +if (!alloc_cpumask_var (&housekeeping_mask,GFP_KERNEL )) { +WARN (1 ,"NO_HZ: Can't allocate not-full dynticks cpumask\n" ); +cpumask_clear (tick_nohz_full_mask); + tick_nohz_full_running = false; +return ; + } + +cpumask_andnot (housekeeping_mask, + cpu_possible_mask, tick_nohz_full_mask); + +/* We need at least one CPU to handle housekeeping work */ +WARN_ON_ONCE (cpumask_empty (housekeeping_mask)); +}
kernel/time/tick-sched.c +0 -18
@@ -166,7 +166,6 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)#ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; -cpumask_var_t housekeeping_mask;bool tick_nohz_full_running;static atomic_t tick_dep_mask;
@@ -438,13 +437,6 @@ void __init tick_nohz_init(void)return ; } -if (!alloc_cpumask_var (&housekeeping_mask,GFP_KERNEL )) { -WARN (1 ,"NO_HZ: Can't allocate not-full dynticks cpumask\n" ); -cpumask_clear (tick_nohz_full_mask); - tick_nohz_full_running = false; -return ; - } -/* * Full dynticks uses irq work to drive the tick rescheduling on safe * locking contexts. But then we need irq work to raise its own
@@ -453,7 +445,6 @@ void __init tick_nohz_init(void)if (!arch_irq_work_has_interrupt ()) {pr_warn ("NO_HZ: Can't run full dynticks because arch doesn't support irq work self-IPIs\n" );cpumask_clear (tick_nohz_full_mask); -cpumask_copy (housekeeping_mask, cpu_possible_mask); tick_nohz_full_running = false;return ; }
@@ -466,9 +457,6 @@ void __init tick_nohz_init(void)cpumask_clear_cpu (cpu, tick_nohz_full_mask); } -cpumask_andnot (housekeeping_mask, - cpu_possible_mask, tick_nohz_full_mask); -for_each_cpu (cpu, tick_nohz_full_mask)context_tracking_cpu_set (cpu);
@@ -478,12 +466,6 @@ void __init tick_nohz_init(void)WARN_ON (ret <0 );pr_info ("NO_HZ: Full dynticks CPUs: %*pbl.\n" , cpumask_pr_args(tick_nohz_full_mask)); - -/* -* We need at least one CPU to handle housekeeping work such -* as timekeeping, unbound timers, workqueues, ... -*/ - WARN_ON_ONCE(cpumask_empty(housekeeping_mask)); }#endif
kernel/watchdog.c +1 -0
@@ -24,6 +24,7 @@#include <linux/workqueue.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> +#include <linux/sched/isolation.h> #include <asm/irq_regs.h> #include <linux/kvm_para.h>
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation: Move housekeeping related code to its own file
sched/isolation: Move housekeeping related code to its own file
Commit-ID: 7863406143d8bbbbda07a61285c5f4c217908dfd Gitweb: https://git.kernel.org/tip/7863406143d8bbbbda07a61285c5f4c217908dfd Author: Frederic Weisbecker <[email protected]> AuthorDate: Fri, 27 Oct 2017 04:42:28 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 27 Oct 2017 09:55:24 +0200
sched/isolation: Move housekeeping related code to its own file
The housekeeping code is currently tied to the NOHZ code. As we are planning to make housekeeping independent from it, start with moving the relevant code to its own file.
Signed-off-by Frederic Weisbecker <[email protected]>
Acked-by Thomas Gleixner <[email protected]>
Acked-by Paul E. McKenney <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Wanpeng Li <[email protected]>
Signed-off-by Ingo Molnar <[email protected]>
--- drivers/net/ethernet/tile/tilegx.c | 2 +- include/linux/sched/isolation.h | 56 ++++++++++++++++++++++++++++++++++++++ include/linux/tick.h | 37 ------------------------- init/main.c | 2 ++ kernel/rcu/tree_plugin.h | 1 + kernel/rcu/update.c | 1 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 1 + kernel/sched/fair.c | 1 + kernel/sched/isolation.c | 33 ++++++++++++++++++++++ kernel/time/tick-sched.c | 18 ------------ kernel/watchdog.c | 1 + 12 files changed, 98 insertions(+), 56 deletions(-)
drivers/net/ethernet/tile/tilegx.c +1 -1
@@ -40,7 +40,7 @@#include <linux/tcp.h> #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> -#include <linux/tick.h> +#include <linux/sched/isolation.h> #include <asm/checksum.h> #include <asm/homecache.h>
include/linux/sched/isolation.h new file +56 -0
56 lines not on this page · raw message
include/linux/tick.h +0 -37
@@ -137,7 +137,6 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }#ifdef CONFIG_NO_HZ_FULL extern bool tick_nohz_full_running;extern cpumask_var_t tick_nohz_full_mask; -extern cpumask_var_t housekeeping_mask;static inline bool tick_nohz_full_enabled (void ) {
@@ -161,11 +160,6 @@ static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask)cpumask_or (mask, mask, tick_nohz_full_mask); } -static inline int housekeeping_any_cpu (void ) -{ -return cpumask_any_and (housekeeping_mask, cpu_online_mask); -} -extern void tick_nohz_dep_set (enum tick_dep_bits bit);extern void tick_nohz_dep_clear (enum tick_dep_bits bit);extern void tick_nohz_dep_set_cpu (int cpu,enum tick_dep_bits bit);
@@ -235,10 +229,6 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal,extern void tick_nohz_full_kick_cpu (int cpu);extern void __tick_nohz_task_switch (void );#else -static inline int housekeeping_any_cpu (void ) -{ -return smp_processor_id (); -}static inline bool tick_nohz_full_enabled (void ) {return false; }static inline bool tick_nohz_full_cpu (int cpu) {return false; }static inline void tick_nohz_full_add_cpus_to (struct cpumask *mask) { }
@@ -260,33 +250,6 @@ static inline void tick_nohz_full_kick_cpu(int cpu) { }static inline void __tick_nohz_task_switch (void ) { }#endif -static inline const struct cpumask *housekeeping_cpumask (void ) -{ -#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) -return housekeeping_mask; -#endif -return cpu_possible_mask; -} - -static inline bool is_housekeeping_cpu (int cpu) -{ -#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) -return cpumask_test_cpu (cpu, housekeeping_mask); -#endif -return true; -} - -static inline void housekeeping_affine (struct task_struct *t) -{ -#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) -set_cpus_allowed_ptr (t, housekeeping_mask); - -#endif -} -static inline void tick_nohz_task_switch (void ) {if (tick_nohz_full_enabled ())
init/main.c +2 -0
@@ -46,6 +46,7 @@#include <linux/cgroup.h> #include <linux/efi.h> #include <linux/tick.h> +#include <linux/sched/isolation.h> #include <linux/interrupt.h> #include <linux/taskstats_kern.h> #include <linux/delayacct.h>
@@ -606,6 +607,7 @@ asmlinkage __visible void __init start_kernel(void)early_irq_init ();init_IRQ ();tick_init (); +housekeeping_init ();rcu_init_nohz ();init_timers ();hrtimers_init ();
kernel/rcu/tree_plugin.h +1 -0
@@ -29,6 +29,7 @@#include <linux/oom.h> #include <linux/sched/debug.h> #include <linux/smpboot.h> +#include <linux/sched/isolation.h> #include <uapi/linux/sched/types.h> #include "../time/tick-internal.h"
kernel/rcu/update.c +1 -0
@@ -51,6 +51,7 @@#include <linux/kthread.h> #include <linux/tick.h> #include <linux/rcupdate_wait.h> +#include <linux/sched/isolation.h> #define CREATE_TRACE_POINTS
kernel/sched/Makefile +1 -0
@@ -26,3 +26,4 @@ obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o +obj-$(CONFIG_NO_HZ_FULL) += isolation.o
kernel/sched/core.c +1 -0
@@ -26,6 +26,7 @@#include <linux/profile.h> #include <linux/security.h> #include <linux/syscalls.h> +#include <linux/sched/isolation.h> #include <asm/switch_to.h> #include <asm/tlb.h>
kernel/sched/fair.c +1 -0
@@ -32,6 +32,7 @@#include <linux/mempolicy.h> #include <linux/migrate.h> #include <linux/task_work.h> +#include <linux/sched/isolation.h> #include <trace/events/sched.h>
kernel/sched/isolation.c new file +33 -0
@@ -0,0 +1,33 @@ +/* +* Housekeeping management. Manage the targets for routine code that can run on +* any CPU: unbound workqueues, timers, kthreads and any offloadable work. +* +* Copyright (C) 2017 Red Hat, Inc., Frederic Weisbecker +* +*/ + +#include <linux/sched/isolation.h> +#include <linux/tick.h> +#include <linux/init.h> +#include <linux/kernel.h> + +cpumask_var_t housekeeping_mask; + +void __init housekeeping_init (void ) +{ +if (!tick_nohz_full_enabled ()) +return ; + +if (!alloc_cpumask_var (&housekeeping_mask,GFP_KERNEL )) { +WARN (1 ,"NO_HZ: Can't allocate not-full dynticks cpumask\n" ); +cpumask_clear (tick_nohz_full_mask); + tick_nohz_full_running = false; +return ; + } + +cpumask_andnot (housekeeping_mask, + cpu_possible_mask, tick_nohz_full_mask); + +/* We need at least one CPU to handle housekeeping work */ +WARN_ON_ONCE (cpumask_empty (housekeeping_mask)); +}
kernel/time/tick-sched.c +0 -18
@@ -166,7 +166,6 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)#ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; -cpumask_var_t housekeeping_mask;bool tick_nohz_full_running;static atomic_t tick_dep_mask;
@@ -438,13 +437,6 @@ void __init tick_nohz_init(void)return ; } -if (!alloc_cpumask_var (&housekeeping_mask,GFP_KERNEL )) { -WARN (1 ,"NO_HZ: Can't allocate not-full dynticks cpumask\n" ); -cpumask_clear (tick_nohz_full_mask); - tick_nohz_full_running = false; -return ; - } -/* * Full dynticks uses irq work to drive the tick rescheduling on safe * locking contexts. But then we need irq work to raise its own
@@ -453,7 +445,6 @@ void __init tick_nohz_init(void)if (!arch_irq_work_has_interrupt ()) {pr_warn ("NO_HZ: Can't run full dynticks because arch doesn't support irq work self-IPIs\n" );cpumask_clear (tick_nohz_full_mask); -cpumask_copy (housekeeping_mask, cpu_possible_mask); tick_nohz_full_running = false;return ; }
@@ -466,9 +457,6 @@ void __init tick_nohz_init(void)cpumask_clear_cpu (cpu, tick_nohz_full_mask); } -cpumask_andnot (housekeeping_mask, - cpu_possible_mask, tick_nohz_full_mask); -for_each_cpu (cpu, tick_nohz_full_mask)context_tracking_cpu_set (cpu);
@@ -478,12 +466,6 @@ void __init tick_nohz_init(void)WARN_ON (ret <0 );pr_info ("NO_HZ: Full dynticks CPUs: %*pbl.\n" , cpumask_pr_args(tick_nohz_full_mask)); - -/* -* We need at least one CPU to handle housekeeping work such -* as timekeeping, unbound timers, workqueues, ... -*/ - WARN_ON_ONCE(cpumask_empty(housekeeping_mask)); }#endif
kernel/watchdog.c +1 -0
@@ -24,6 +24,7 @@#include <linux/workqueue.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> +#include <linux/sched/isolation.h> #include <asm/irq_regs.h> #include <linux/kvm_para.h>
Frederic Weisbecker
maintainerPATCH 2/12 watchdog: Use housekeeping_cpumask() instead of ad-hoc version
In reply to Frederic WeisbeckerWhile trying to disable the watchog on nohz_full CPUs, the watchdog implements an ad-hoc version of housekeeping_cpumask(). Lets replace those re-invented lines.
Signed-off-by Frederic Weisbecker <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Wanpeng Li <[email protected]>
--- kernel/watchdog.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-)
kernel/watchdog.c +3 -8
@@ -774,15 +774,10 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,void __init lockup_detector_init (void ) { -#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) { +if (tick_nohz_full_enabled ())pr_info ("Disabling watchdog on nohz_full cores by default\n" ); -cpumask_copy (&watchdog_cpumask, housekeeping_mask); - }else -cpumask_copy (&watchdog_cpumask, cpu_possible_mask); -#else -cpumask_copy (&watchdog_cpumask, cpu_possible_mask); -#endif + +cpumask_copy (&watchdog_cpumask,housekeeping_cpumask ());if (!watchdog_nmi_probe ()) nmi_watchdog_available = true;
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation, watchdog: Use housekeeping_cpumask() instead of ad-hoc version
sched/isolation, watchdog: Use housekeeping_cpumask() instead of ad-hoc version
Commit-ID: 13316b31fdaaa45f06793eb7992588359ba6ab9f Gitweb: https://git.kernel.org/tip/13316b31fdaaa45f06793eb7992588359ba6ab9f Author: Frederic Weisbecker <[email protected]> AuthorDate: Fri, 27 Oct 2017 04:42:29 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 27 Oct 2017 09:55:25 +0200
sched/isolation, watchdog: Use housekeeping_cpumask() instead of ad-hoc version
While trying to disable the watchog on nohz_full CPUs, the watchdog implements an ad-hoc version of housekeeping_cpumask(). Lets replace those re-invented lines.
Signed-off-by Frederic Weisbecker <[email protected]>
Acked-by Thomas Gleixner <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Wanpeng Li <[email protected]>
Signed-off-by Ingo Molnar <[email protected]>
--- kernel/watchdog.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-)
kernel/watchdog.c +3 -8
@@ -774,15 +774,10 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,void __init lockup_detector_init (void ) { -#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) { +if (tick_nohz_full_enabled ())pr_info ("Disabling watchdog on nohz_full cores by default\n" ); -cpumask_copy (&watchdog_cpumask, housekeeping_mask); - }else -cpumask_copy (&watchdog_cpumask, cpu_possible_mask); -#else -cpumask_copy (&watchdog_cpumask, cpu_possible_mask); -#endif + +cpumask_copy (&watchdog_cpumask,housekeeping_cpumask ());if (!watchdog_nmi_probe ()) nmi_watchdog_available = true;
Frederic Weisbecker
maintainerPATCH 3/12 housekeeping: Provide a dynamic off-case to housekeeping_any_cpu()
In reply to Frederic Weisbeckerhousekeeping_any_cpu() doesn't handle correctly the case where CONFIG_NO_HZ_FULL=y and no CPU is in nohz_full mode. So far no caller needs this but let's prepare to avoid any future surprise.
Signed-off-by Frederic Weisbecker <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Wanpeng Li <[email protected]>
--- include/linux/sched/isolation.h | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-)
include/linux/sched/isolation.h +8 -13
@@ -7,24 +7,19 @@#ifdef CONFIG_NO_HZ_FULL extern cpumask_var_t housekeeping_mask; - -static inline int housekeeping_any_cpu (void ) -{ -return cpumask_any_and (housekeeping_mask, cpu_online_mask); -} -extern void __init housekeeping_init (void ); -#else - -static inline int housekeeping_any_cpu (void ) -{ -return smp_processor_id (); -} -static inline void housekeeping_init (void ) { }#endif /* CONFIG_NO_HZ_FULL */ +static inline int housekeeping_any_cpu (void ) +{ +#ifdef CONFIG_NO_HZ_FULL +if (tick_nohz_full_enabled ()) +return cpumask_any_and (housekeeping_mask, cpu_online_mask); +#endif +return smp_processor_id (); +}static inline const struct cpumask *housekeeping_cpumask (void ) {
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation: Provide a dynamic off-case to housekeeping_any_cpu()
sched/isolation: Provide a dynamic off-case to housekeeping_any_cpu()
Commit-ID: 9f0ca2d97ef0b5e966be2cfef26c7c094ec14e41 Gitweb: https://git.kernel.org/tip/9f0ca2d97ef0b5e966be2cfef26c7c094ec14e41 Author: Frederic Weisbecker <[email protected]> AuthorDate: Fri, 27 Oct 2017 04:42:30 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 27 Oct 2017 09:55:26 +0200
sched/isolation: Provide a dynamic off-case to housekeeping_any_cpu()
housekeeping_any_cpu() doesn't handle correctly the case where CONFIG_NO_HZ_FULL=y and no CPU is in nohz_full mode. So far no caller needs this but let's prepare to avoid any future surprise.
Signed-off-by Frederic Weisbecker <[email protected]>
Acked-by Thomas Gleixner <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Wanpeng Li <[email protected]>
Signed-off-by Ingo Molnar <[email protected]>
--- include/linux/sched/isolation.h | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-)
include/linux/sched/isolation.h +6 -11
@@ -7,25 +7,20 @@#ifdef CONFIG_NO_HZ_FULL extern cpumask_var_t housekeeping_mask; - -static inline int housekeeping_any_cpu (void ) -{ -return cpumask_any_and (housekeeping_mask, cpu_online_mask); -} -extern void __init housekeeping_init (void ); -#else +static inline void housekeeping_init (void ) { } +#endif /* CONFIG_NO_HZ_FULL */ static inline int housekeeping_any_cpu (void ) { +#ifdef CONFIG_NO_HZ_FULL +if (tick_nohz_full_enabled ()) +return cpumask_any_and (housekeeping_mask, cpu_online_mask); +#endif return smp_processor_id (); } -static inline void housekeeping_init (void ) { } -#endif /* CONFIG_NO_HZ_FULL */ - -static inline const struct cpumask *housekeeping_cpumask (void ) {#ifdef CONFIG_NO_HZ_FULL
Frederic Weisbecker
maintainerPATCH 4/12 housekeeping: Make housekeeping cpumask private
In reply to Frederic WeisbeckerNobody needs to access this detail. housekeeping_cpumask() already takes care about it.
Signed-off-by Frederic Weisbecker <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Wanpeng Li <[email protected]>
--- include/linux/sched/isolation.h | 31 ++++++++++--------------------- kernel/sched/isolation.c | 36 +++++++++++++++++++++++++++++++++++- 2 files changed, 45 insertions(+), 22 deletions(-)
include/linux/sched/isolation.h +10 -21
@@ -6,46 +6,35 @@#include <linux/tick.h> #ifdef CONFIG_NO_HZ_FULL -extern cpumask_var_t housekeeping_mask; +extern int housekeeping_any_cpu (void ); +extern const struct cpumask *housekeeping_cpumask (void ); +extern void housekeeping_affine (struct task_struct *t); +extern bool housekeeping_test_cpu (int cpu);extern void __init housekeeping_init (void ); +#else -static inline void housekeeping_init (void ) { } -#endif /* CONFIG_NO_HZ_FULL */ static inline int housekeeping_any_cpu (void ) { -#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) -return cpumask_any_and (housekeeping_mask, cpu_online_mask); -#endif return smp_processor_id (); }static inline const struct cpumask *housekeeping_cpumask (void ) { -#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) -return housekeeping_mask; -#endif return cpu_possible_mask; } +static inline void housekeeping_affine (struct task_struct *t) { } +static inline void housekeeping_init (void ) { } +#endif /* CONFIG_NO_HZ_FULL */ +static inline bool is_housekeeping_cpu (int cpu) {#ifdef CONFIG_NO_HZ_FULL if (tick_nohz_full_enabled ()) -return cpumask_test_cpu (cpu, housekeeping_mask); +return housekeeping_test_cpu (cpu);#endif return true; } -static inline void housekeeping_affine (struct task_struct *t) -{ -#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) -set_cpus_allowed_ptr (t, housekeeping_mask); - -#endif -} -#endif /* _LINUX_SCHED_ISOLATION_H */
kernel/sched/isolation.c +35 -1
@@ -11,7 +11,41 @@#include <linux/init.h> #include <linux/kernel.h> -cpumask_var_t housekeeping_mask; +static cpumask_var_t housekeeping_mask; + +int housekeeping_any_cpu (void ) +{ +if (tick_nohz_full_enabled ()) +return cpumask_any_and (housekeeping_mask, cpu_online_mask); + +return smp_processor_id (); +} +EXPORT_SYMBOL_GPL (housekeeping_any_cpu); + +const struct cpumask *housekeeping_cpumask (void ) +{ +if (tick_nohz_full_enabled ()) +return housekeeping_mask; + +return cpu_possible_mask; +} +EXPORT_SYMBOL_GPL (housekeeping_cpumask); + +void housekeeping_affine (struct task_struct *t) +{ +if (tick_nohz_full_enabled ()) +set_cpus_allowed_ptr (t, housekeeping_mask); +} +EXPORT_SYMBOL_GPL (housekeeping_affine); + +bool housekeeping_test_cpu (int cpu) +{ +if (tick_nohz_full_enabled ()) +return cpumask_test_cpu (cpu, housekeeping_mask); + +return true; +} +EXPORT_SYMBOL_GPL (housekeeping_test_cpu);void __init housekeeping_init (void ) {
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation: Make the housekeeping cpumask private
sched/isolation: Make the housekeeping cpumask private
Commit-ID: 7e56a1cf4b28f5739526877b8dbad623fae2e4e7 Gitweb: https://git.kernel.org/tip/7e56a1cf4b28f5739526877b8dbad623fae2e4e7 Author: Frederic Weisbecker <[email protected]> AuthorDate: Fri, 27 Oct 2017 04:42:31 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 27 Oct 2017 09:55:26 +0200
sched/isolation: Make the housekeeping cpumask private
Nobody needs to access this detail. housekeeping_cpumask() already takes care of it.
Signed-off-by Frederic Weisbecker <[email protected]>
Acked-by Thomas Gleixner <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Wanpeng Li <[email protected]>
Signed-off-by Ingo Molnar <[email protected]>
--- include/linux/sched/isolation.h | 31 ++++++++++--------------------- kernel/sched/isolation.c | 36 +++++++++++++++++++++++++++++++++++- 2 files changed, 45 insertions(+), 22 deletions(-)
include/linux/sched/isolation.h +10 -21
@@ -6,46 +6,35 @@#include <linux/tick.h> #ifdef CONFIG_NO_HZ_FULL -extern cpumask_var_t housekeeping_mask; +extern int housekeeping_any_cpu (void ); +extern const struct cpumask *housekeeping_cpumask (void ); +extern void housekeeping_affine (struct task_struct *t); +extern bool housekeeping_test_cpu (int cpu);extern void __init housekeeping_init (void ); +#else -static inline void housekeeping_init (void ) { } -#endif /* CONFIG_NO_HZ_FULL */ static inline int housekeeping_any_cpu (void ) { -#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) -return cpumask_any_and (housekeeping_mask, cpu_online_mask); -#endif return smp_processor_id (); }static inline const struct cpumask *housekeeping_cpumask (void ) { -#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) -return housekeeping_mask; -#endif return cpu_possible_mask; } +static inline void housekeeping_affine (struct task_struct *t) { } +static inline void housekeeping_init (void ) { } +#endif /* CONFIG_NO_HZ_FULL */ +static inline bool is_housekeeping_cpu (int cpu) {#ifdef CONFIG_NO_HZ_FULL if (tick_nohz_full_enabled ()) -return cpumask_test_cpu (cpu, housekeeping_mask); +return housekeeping_test_cpu (cpu);#endif return true; } -static inline void housekeeping_affine (struct task_struct *t) -{ -#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) -set_cpus_allowed_ptr (t, housekeeping_mask); - -#endif -} -#endif /* _LINUX_SCHED_ISOLATION_H */
kernel/sched/isolation.c +35 -1
@@ -11,7 +11,41 @@#include <linux/init.h> #include <linux/kernel.h> -cpumask_var_t housekeeping_mask; +static cpumask_var_t housekeeping_mask; + +int housekeeping_any_cpu (void ) +{ +if (tick_nohz_full_enabled ()) +return cpumask_any_and (housekeeping_mask, cpu_online_mask); + +return smp_processor_id (); +} +EXPORT_SYMBOL_GPL (housekeeping_any_cpu); + +const struct cpumask *housekeeping_cpumask (void ) +{ +if (tick_nohz_full_enabled ()) +return housekeeping_mask; + +return cpu_possible_mask; +} +EXPORT_SYMBOL_GPL (housekeeping_cpumask); + +void housekeeping_affine (struct task_struct *t) +{ +if (tick_nohz_full_enabled ()) +set_cpus_allowed_ptr (t, housekeeping_mask); +} +EXPORT_SYMBOL_GPL (housekeeping_affine); + +bool housekeeping_test_cpu (int cpu) +{ +if (tick_nohz_full_enabled ()) +return cpumask_test_cpu (cpu, housekeeping_mask); + +return true; +} +EXPORT_SYMBOL_GPL (housekeeping_test_cpu);void __init housekeeping_init (void ) {
Frederic Weisbecker
maintainerPATCH 5/12 housekeeping: Use its own static key
In reply to Frederic WeisbeckerHousekeeping code still depends on nohz_full static key. Since we want to decouple housekeeping from nohz, let's create a housekeeping own static key. It's mostly relevant for calls to is_housekeeping_cpu() from the scheduler.
Signed-off-by Frederic Weisbecker <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Wanpeng Li <[email protected]>
--- include/linux/sched/isolation.h | 3 ++- kernel/sched/isolation.c | 13 +++++++++---- 2 files changed, 11 insertions(+), 5 deletions(-)
include/linux/sched/isolation.h +2 -1
@@ -6,6 +6,7 @@#include <linux/tick.h> #ifdef CONFIG_NO_HZ_FULL +DECLARE_STATIC_KEY_FALSE (housekeeping_overriden);extern int housekeeping_any_cpu (void );extern const struct cpumask *housekeeping_cpumask (void );extern void housekeeping_affine (struct task_struct *t);
@@ -31,7 +32,7 @@ static inline void housekeeping_init(void) { }static inline bool is_housekeeping_cpu (int cpu) {#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) +if (static_branch_unlikely (&housekeeping_overriden))return housekeeping_test_cpu (cpu);#endif return true;
kernel/sched/isolation.c +9 -4
@@ -10,12 +10,15 @@#include <linux/tick.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/static_key.h> +DEFINE_STATIC_KEY_FALSE (housekeeping_overriden); +EXPORT_SYMBOL_GPL (housekeeping_overriden);static cpumask_var_t housekeeping_mask;int housekeeping_any_cpu (void ) { -if (tick_nohz_full_enabled ()) +if (static_branch_unlikely (&housekeeping_overriden))return cpumask_any_and (housekeeping_mask, cpu_online_mask);return smp_processor_id ();
@@ -24,7 +27,7 @@ EXPORT_SYMBOL_GPL(housekeeping_any_cpu);const struct cpumask *housekeeping_cpumask (void ) { -if (tick_nohz_full_enabled ()) +if (static_branch_unlikely (&housekeeping_overriden))return housekeeping_mask;return cpu_possible_mask;
@@ -33,14 +36,14 @@ EXPORT_SYMBOL_GPL(housekeeping_cpumask);void housekeeping_affine (struct task_struct *t) { -if (tick_nohz_full_enabled ()) +if (static_branch_unlikely (&housekeeping_overriden))set_cpus_allowed_ptr (t, housekeeping_mask); }EXPORT_SYMBOL_GPL (housekeeping_affine);bool housekeeping_test_cpu (int cpu) { -if (tick_nohz_full_enabled ()) +if (static_branch_unlikely (&housekeeping_overriden))return cpumask_test_cpu (cpu, housekeeping_mask);return true;
@@ -62,6 +65,8 @@ void __init housekeeping_init(void)cpumask_andnot (housekeeping_mask, cpu_possible_mask, tick_nohz_full_mask); +static_branch_enable (&housekeeping_overriden); +/* We need at least one CPU to handle housekeeping work */ WARN_ON_ONCE (cpumask_empty (housekeeping_mask)); }
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation: Use its own static key
sched/isolation: Use its own static key
Commit-ID: e179f5a04ba46ee5c5439480c2bfd68c358168b7 Gitweb: https://git.kernel.org/tip/e179f5a04ba46ee5c5439480c2bfd68c358168b7 Author: Frederic Weisbecker <[email protected]> AuthorDate: Fri, 27 Oct 2017 04:42:32 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 27 Oct 2017 09:55:27 +0200
sched/isolation: Use its own static key
Housekeeping code still depends on the nohz_full static key. Since we want to decouple housekeeping from NOHZ, let's create a housekeeping specific static key.
It's mostly relevant for calls to is_housekeeping_cpu() from the scheduler.
Signed-off-by Frederic Weisbecker <[email protected]>
Acked-by Thomas Gleixner <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Wanpeng Li <[email protected]>
Signed-off-by Ingo Molnar <[email protected]>
--- include/linux/sched/isolation.h | 3 ++- kernel/sched/isolation.c | 13 +++++++++---- 2 files changed, 11 insertions(+), 5 deletions(-)
include/linux/sched/isolation.h +2 -1
@@ -6,6 +6,7 @@#include <linux/tick.h> #ifdef CONFIG_NO_HZ_FULL +DECLARE_STATIC_KEY_FALSE (housekeeping_overriden);extern int housekeeping_any_cpu (void );extern const struct cpumask *housekeeping_cpumask (void );extern void housekeeping_affine (struct task_struct *t);
@@ -31,7 +32,7 @@ static inline void housekeeping_init(void) { }static inline bool is_housekeeping_cpu (int cpu) {#ifdef CONFIG_NO_HZ_FULL -if (tick_nohz_full_enabled ()) +if (static_branch_unlikely (&housekeeping_overriden))return housekeeping_test_cpu (cpu);#endif return true;
kernel/sched/isolation.c +9 -4
@@ -10,12 +10,15 @@#include <linux/tick.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/static_key.h> +DEFINE_STATIC_KEY_FALSE (housekeeping_overriden); +EXPORT_SYMBOL_GPL (housekeeping_overriden);static cpumask_var_t housekeeping_mask;int housekeeping_any_cpu (void ) { -if (tick_nohz_full_enabled ()) +if (static_branch_unlikely (&housekeeping_overriden))return cpumask_any_and (housekeeping_mask, cpu_online_mask);return smp_processor_id ();
@@ -24,7 +27,7 @@ EXPORT_SYMBOL_GPL(housekeeping_any_cpu);const struct cpumask *housekeeping_cpumask (void ) { -if (tick_nohz_full_enabled ()) +if (static_branch_unlikely (&housekeeping_overriden))return housekeeping_mask;return cpu_possible_mask;
@@ -33,14 +36,14 @@ EXPORT_SYMBOL_GPL(housekeeping_cpumask);void housekeeping_affine (struct task_struct *t) { -if (tick_nohz_full_enabled ()) +if (static_branch_unlikely (&housekeeping_overriden))set_cpus_allowed_ptr (t, housekeeping_mask); }EXPORT_SYMBOL_GPL (housekeeping_affine);bool housekeeping_test_cpu (int cpu) { -if (tick_nohz_full_enabled ()) +if (static_branch_unlikely (&housekeeping_overriden))return cpumask_test_cpu (cpu, housekeeping_mask);return true;
@@ -62,6 +65,8 @@ void __init housekeeping_init(void)cpumask_andnot (housekeeping_mask, cpu_possible_mask, tick_nohz_full_mask); +static_branch_enable (&housekeeping_overriden); +/* We need at least one CPU to handle housekeeping work */ WARN_ON_ONCE (cpumask_empty (housekeeping_mask)); }
Frederic Weisbecker
maintainerPATCH 6/12 housekeeping: Rename is_housekeeping_cpu to housekeeping_cpu
In reply to Frederic WeisbeckerTo keep a proper housekeeping namespace.
Signed-off-by Frederic Weisbecker <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Wanpeng Li <[email protected]>
--- include/linux/sched/isolation.h | 2 +- kernel/sched/core.c | 6 +++--- kernel/sched/fair.c | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-)
include/linux/sched/isolation.h +1 -1
@@ -29,7 +29,7 @@ static inline void housekeeping_affine(struct task_struct *t) { }static inline void housekeeping_init (void ) { }#endif /* CONFIG_NO_HZ_FULL */ -static inline bool is_housekeeping_cpu (int cpu) +static inline bool housekeeping_cpu (int cpu) {#ifdef CONFIG_NO_HZ_FULL if (static_branch_unlikely (&housekeeping_overriden))
kernel/sched/core.c +3 -3
@@ -527,7 +527,7 @@ int get_nohz_timer_target(void)int i, cpu =smp_processor_id ();struct sched_domain *sd; -if (!idle_cpu (cpu) &&is_housekeeping_cpu (cpu)) +if (!idle_cpu (cpu) &&housekeeping_cpu (cpu))return cpu;rcu_read_lock ();
@@ -536,14 +536,14 @@ int get_nohz_timer_target(void)if (cpu == i)continue ; -if (!idle_cpu (i) &&is_housekeeping_cpu (i)) { +if (!idle_cpu (i) &&housekeeping_cpu (i)) { cpu = i; goto unlock; } } } -if (!is_housekeeping_cpu (cpu)) +if (!housekeeping_cpu (cpu)) cpu =housekeeping_any_cpu (); unlock:rcu_read_unlock ();
kernel/sched/fair.c +1 -1
@@ -9027,7 +9027,7 @@ void nohz_balance_enter_idle(int cpu)return ;/* Spare idle load balancing on CPUs that don't want to be disturbed: */ -if (!is_housekeeping_cpu (cpu)) +if (!housekeeping_cpu (cpu))return ;if (test_bit (NOHZ_TICK_STOPPED ,nohz_flags (cpu)))
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation: Rename is_housekeeping_cpu() to housekeeping_cpu()
sched/isolation: Rename is_housekeeping_cpu() to housekeeping_cpu()
Commit-ID: 204c083a009378dfa751175b5fcddc75988bab6c Gitweb: https://git.kernel.org/tip/204c083a009378dfa751175b5fcddc75988bab6c Author: Frederic Weisbecker <[email protected]> AuthorDate: Fri, 27 Oct 2017 04:42:33 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 27 Oct 2017 09:55:28 +0200
sched/isolation: Rename is_housekeeping_cpu() to housekeeping_cpu()
Fit it into the housekeeping_*() namespace.
Signed-off-by Frederic Weisbecker <[email protected]>
Acked-by Thomas Gleixner <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Wanpeng Li <[email protected]>
Signed-off-by Ingo Molnar <[email protected]>
--- include/linux/sched/isolation.h | 2 +- kernel/sched/core.c | 6 +++--- kernel/sched/fair.c | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-)
include/linux/sched/isolation.h +1 -1
@@ -29,7 +29,7 @@ static inline void housekeeping_affine(struct task_struct *t) { }static inline void housekeeping_init (void ) { }#endif /* CONFIG_NO_HZ_FULL */ -static inline bool is_housekeeping_cpu (int cpu) +static inline bool housekeeping_cpu (int cpu) {#ifdef CONFIG_NO_HZ_FULL if (static_branch_unlikely (&housekeeping_overriden))
kernel/sched/core.c +3 -3
@@ -527,7 +527,7 @@ int get_nohz_timer_target(void)int i, cpu =smp_processor_id ();struct sched_domain *sd; -if (!idle_cpu (cpu) &&is_housekeeping_cpu (cpu)) +if (!idle_cpu (cpu) &&housekeeping_cpu (cpu))return cpu;rcu_read_lock ();
@@ -536,14 +536,14 @@ int get_nohz_timer_target(void)if (cpu == i)continue ; -if (!idle_cpu (i) &&is_housekeeping_cpu (i)) { +if (!idle_cpu (i) &&housekeeping_cpu (i)) { cpu = i; goto unlock; } } } -if (!is_housekeeping_cpu (cpu)) +if (!housekeeping_cpu (cpu)) cpu =housekeeping_any_cpu (); unlock:rcu_read_unlock ();
kernel/sched/fair.c +1 -1
@@ -9027,7 +9027,7 @@ void nohz_balance_enter_idle(int cpu)return ;/* Spare idle load balancing on CPUs that don't want to be disturbed: */ -if (!is_housekeeping_cpu (cpu)) +if (!housekeeping_cpu (cpu))return ;if (test_bit (NOHZ_TICK_STOPPED ,nohz_flags (cpu)))
Frederic Weisbecker
maintainerPATCH 7/12 housekeeping: Move it under its own config, independent from NO_HZ
In reply to Frederic WeisbeckerSplit housekeeping config from CONFIG_NO_HZ_FULL. This way we finally separate the isolation code from nohz.
Although a dependency to CONFIG_NO_HZ_FULL remains for now until the housekeeping code doesn't deal anymore with nohz internals directly.
Signed-off-by Frederic Weisbecker <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Wanpeng Li <[email protected]>
--- include/linux/sched/isolation.h | 6 +++--- init/Kconfig | 8 ++++++++ kernel/sched/Makefile | 2 +- 3 files changed, 12 insertions(+), 4 deletions(-)
include/linux/sched/isolation.h +3 -3
@@ -5,7 +5,7 @@#include <linux/init.h> #include <linux/tick.h> -#ifdef CONFIG_NO_HZ_FULL +#ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE (housekeeping_overriden);extern int housekeeping_any_cpu (void );extern const struct cpumask *housekeeping_cpumask (void );
@@ -27,11 +27,11 @@ static inline const struct cpumask *housekeeping_cpumask(void)static inline void housekeeping_affine (struct task_struct *t) { }static inline void housekeeping_init (void ) { } -#endif /* CONFIG_NO_HZ_FULL */ +#endif /* CONFIG_CPU_ISOLATION */ static inline bool housekeeping_cpu (int cpu) { -#ifdef CONFIG_NO_HZ_FULL +#ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely (&housekeeping_overriden))return housekeeping_test_cpu (cpu);#endif
init/Kconfig +8 -0
@@ -472,6 +472,14 @@ config TASK_IO_ACCOUNTING endmenu # "CPU/Task time and stats accounting" +config CPU_ISOLATION + bool "CPU isolation" + depends on NO_HZ_FULL + help + Make sure that CPUs running critical tasks are not disturbed by + any source of "noise" such as unbound workqueues, timers, kthreads... + Unbound jobs get offloaded to housekeeping CPUs. + source "kernel/rcu/Kconfig" config BUILD_BIN2C
kernel/sched/Makefile +1 -1
@@ -26,4 +26,4 @@ obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o -obj-$(CONFIG_NO_HZ_FULL) += isolation.o +obj-$(CONFIG_CPU_ISOLATION) += isolation.o
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation: Split out new CONFIG_CPU_ISOLATION=y config from CONFIG_NO_HZ_FULL
sched/isolation: Split out new CONFIG_CPU_ISOLATION=y config from CONFIG_NO_HZ_FULL
Commit-ID: 5c4991e24c69737bd41fc2737b1e3980abbf73f9 Gitweb: https://git.kernel.org/tip/5c4991e24c69737bd41fc2737b1e3980abbf73f9 Author: Frederic Weisbecker <[email protected]> AuthorDate: Fri, 27 Oct 2017 04:42:34 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 27 Oct 2017 09:55:28 +0200
sched/isolation: Split out new CONFIG_CPU_ISOLATION=y config from CONFIG_NO_HZ_FULL
Split the housekeeping config from CONFIG_NO_HZ_FULL. This way we finally separate the isolation code from NOHZ.
Although a dependency to CONFIG_NO_HZ_FULL remains for now, while the housekeeping code still deals with NOHZ internals.
Signed-off-by Frederic Weisbecker <[email protected]>
Acked-by Thomas Gleixner <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Wanpeng Li <[email protected]>
Signed-off-by Ingo Molnar <[email protected]>
--- include/linux/sched/isolation.h | 6 +++--- init/Kconfig | 8 ++++++++ kernel/sched/Makefile | 2 +- 3 files changed, 12 insertions(+), 4 deletions(-)
include/linux/sched/isolation.h +3 -3
@@ -5,7 +5,7 @@#include <linux/init.h> #include <linux/tick.h> -#ifdef CONFIG_NO_HZ_FULL +#ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE (housekeeping_overriden);extern int housekeeping_any_cpu (void );extern const struct cpumask *housekeeping_cpumask (void );
@@ -27,11 +27,11 @@ static inline const struct cpumask *housekeeping_cpumask(void)static inline void housekeeping_affine (struct task_struct *t) { }static inline void housekeeping_init (void ) { } -#endif /* CONFIG_NO_HZ_FULL */ +#endif /* CONFIG_CPU_ISOLATION */ static inline bool housekeeping_cpu (int cpu) { -#ifdef CONFIG_NO_HZ_FULL +#ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely (&housekeeping_overriden))return housekeeping_test_cpu (cpu);#endif
init/Kconfig +8 -0
@@ -472,6 +472,14 @@ config TASK_IO_ACCOUNTING endmenu # "CPU/Task time and stats accounting" +config CPU_ISOLATION + bool "CPU isolation" + depends on NO_HZ_FULL + help + Make sure that CPUs running critical tasks are not disturbed by + any source of "noise" such as unbound workqueues, timers, kthreads... + Unbound jobs get offloaded to housekeeping CPUs. + source "kernel/rcu/Kconfig" config BUILD_BIN2C
kernel/sched/Makefile +1 -1
@@ -26,4 +26,4 @@ obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o -obj-$(CONFIG_NO_HZ_FULL) += isolation.o +obj-$(CONFIG_CPU_ISOLATION) += isolation.o
Frederic Weisbecker
maintainerPATCH 8/12 housekeeping: Introduce housekeeping flags
In reply to Frederic WeisbeckerBefore we implement isolcpus under housekeeping, we need the isolation features to be more finegrained. For example some people want nohz_full without the full scheduler isolation, others want full scheduler isolation without nohz_full.
So let's cut all these isolation features piecewise, at the risk of overcutting it right now. We can still merge some flags later if they always make sense together.
Signed-off-by Frederic Weisbecker <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Wanpeng Li <[email protected]>
--- drivers/net/ethernet/tile/tilegx.c | 4 ++-- include/linux/sched/isolation.h | 26 +++++++++++++++++--------- kernel/rcu/tree_plugin.h | 2 +- kernel/rcu/update.c | 2 +- kernel/sched/core.c | 8 ++++---- kernel/sched/fair.c | 2 +- kernel/sched/isolation.c | 26 +++++++++++++++----------- kernel/watchdog.c | 3 ++- 8 files changed, 43 insertions(+), 30 deletions(-)
drivers/net/ethernet/tile/tilegx.c +2 -2
@@ -2270,8 +2270,8 @@ static int __init tile_net_init_module(void)tile_net_dev_init (name, mac);if (!network_cpus_init ()) -cpumask_and (&network_cpus_map,housekeeping_cpumask (), - cpu_online_mask); +cpumask_and (&network_cpus_map, +housekeeping_cpumask (HK_FLAG_MISC ), cpu_online_mask);return 0 ; }
include/linux/sched/isolation.h +17 -9
@@ -5,35 +5,43 @@#include <linux/init.h> #include <linux/tick.h> +enum hk_flags { +HK_FLAG_TIMER =1 , +HK_FLAG_RCU = (1 <<1 ), +HK_FLAG_MISC = (1 <<2 ), +HK_FLAG_SCHED = (1 <<3 ), +}; +#ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE (housekeeping_overriden); -extern int housekeeping_any_cpu (void ); -extern const struct cpumask *housekeeping_cpumask (void ); -extern void housekeeping_affine (struct task_struct *t); -extern bool housekeeping_test_cpu (int cpu); +extern int housekeeping_any_cpu (enum hk_flags flags); +extern const struct cpumask *housekeeping_cpumask (enum hk_flags flags); +extern void housekeeping_affine (struct task_struct *t,enum hk_flags flags); +extern bool housekeeping_test_cpu (int cpu,enum hk_flags flags);extern void __init housekeeping_init (void );#else -static inline int housekeeping_any_cpu (void ) +static inline int housekeeping_any_cpu (enum hk_flags flags) {return smp_processor_id (); } -static inline const struct cpumask *housekeeping_cpumask (void ) +static inline const struct cpumask *housekeeping_cpumask (enum hk_flags flags) {return cpu_possible_mask; } -static inline void housekeeping_affine (struct task_struct *t) { } +static inline void housekeeping_affine (struct task_struct *t, +enum hk_flags flags) { }static inline void housekeeping_init (void ) { }#endif /* CONFIG_CPU_ISOLATION */ -static inline bool housekeeping_cpu (int cpu) +static inline bool housekeeping_cpu (int cpu,enum hk_flags flags) {#ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely (&housekeeping_overriden)) -return housekeeping_test_cpu (cpu); +return housekeeping_test_cpu (cpu, flags);#endif return true; }
kernel/rcu/tree_plugin.h +1 -1
@@ -2584,7 +2584,7 @@ static void rcu_bind_gp_kthread(void)if (!tick_nohz_full_enabled ())return ; -housekeeping_affine (current); +housekeeping_affine (current,HK_FLAG_RCU ); }/* Record the current task on dyntick-idle entry. */
kernel/rcu/update.c +1 -1
@@ -719,7 +719,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)LIST_HEAD (rcu_tasks_holdouts);/* Run on housekeeping CPUs by default. Sysadm can move if desired. */ -housekeeping_affine (current); +housekeeping_affine (current,HK_FLAG_RCU );/* * Each pass through the following loop makes one check for
kernel/sched/core.c +4 -4
@@ -527,7 +527,7 @@ int get_nohz_timer_target(void)int i, cpu =smp_processor_id ();struct sched_domain *sd; -if (!idle_cpu (cpu) &&housekeeping_cpu (cpu)) +if (!idle_cpu (cpu) &&housekeeping_cpu (cpu,HK_FLAG_TIMER ))return cpu;rcu_read_lock ();
@@ -536,15 +536,15 @@ int get_nohz_timer_target(void)if (cpu == i)continue ; -if (!idle_cpu (i) &&housekeeping_cpu (i)) { +if (!idle_cpu (i) &&housekeeping_cpu (i,HK_FLAG_TIMER )) { cpu = i; goto unlock; } } } -if (!housekeeping_cpu (cpu)) - cpu =housekeeping_any_cpu (); +if (!housekeeping_cpu (cpu,HK_FLAG_TIMER )) + cpu =housekeeping_any_cpu (HK_FLAG_TIMER ); unlock:rcu_read_unlock ();return cpu;
kernel/sched/fair.c +1 -1
@@ -9027,7 +9027,7 @@ void nohz_balance_enter_idle(int cpu)return ;/* Spare idle load balancing on CPUs that don't want to be disturbed: */ -if (!housekeeping_cpu (cpu)) +if (!housekeeping_cpu (cpu,HK_FLAG_SCHED ))return ;if (test_bit (NOHZ_TICK_STOPPED ,nohz_flags (cpu)))
kernel/sched/isolation.c +15 -11
@@ -15,37 +15,39 @@DEFINE_STATIC_KEY_FALSE (housekeeping_overriden);EXPORT_SYMBOL_GPL (housekeeping_overriden);static cpumask_var_t housekeeping_mask; +static unsigned int housekeeping_flags; -int housekeeping_any_cpu (void ) +int housekeeping_any_cpu (enum hk_flags flags) {if (static_branch_unlikely (&housekeeping_overriden)) -return cpumask_any_and (housekeeping_mask, cpu_online_mask); - +if (housekeeping_flags & flags) +return cpumask_any_and (housekeeping_mask, cpu_online_mask);return smp_processor_id (); }EXPORT_SYMBOL_GPL (housekeeping_any_cpu); -const struct cpumask *housekeeping_cpumask (void ) +const struct cpumask *housekeeping_cpumask (enum hk_flags flags) {if (static_branch_unlikely (&housekeeping_overriden)) -return housekeeping_mask; - +if (housekeeping_flags & flags) +return housekeeping_mask;return cpu_possible_mask; }EXPORT_SYMBOL_GPL (housekeeping_cpumask); -void housekeeping_affine (struct task_struct *t) +void housekeeping_affine (struct task_struct *t,enum hk_flags flags) {if (static_branch_unlikely (&housekeeping_overriden)) -set_cpus_allowed_ptr (t, housekeeping_mask); +if (housekeeping_flags & flags) +set_cpus_allowed_ptr (t, housekeeping_mask); }EXPORT_SYMBOL_GPL (housekeeping_affine); -bool housekeeping_test_cpu (int cpu) +bool housekeeping_test_cpu (int cpu,enum hk_flags flags) {if (static_branch_unlikely (&housekeeping_overriden)) -return cpumask_test_cpu (cpu, housekeeping_mask); - +if (housekeeping_flags & flags) +return cpumask_test_cpu (cpu, housekeeping_mask);return true; }EXPORT_SYMBOL_GPL (housekeeping_test_cpu);
@@ -65,6 +67,8 @@ void __init housekeeping_init(void)cpumask_andnot (housekeeping_mask, cpu_possible_mask, tick_nohz_full_mask); + housekeeping_flags =HK_FLAG_TIMER |HK_FLAG_RCU |HK_FLAG_MISC ; +static_branch_enable (&housekeeping_overriden);/* We need at least one CPU to handle housekeeping work */
kernel/watchdog.c +2 -1
@@ -777,7 +777,8 @@ void __init lockup_detector_init(void)if (tick_nohz_full_enabled ())pr_info ("Disabling watchdog on nohz_full cores by default\n" ); -cpumask_copy (&watchdog_cpumask,housekeeping_cpumask ()); +cpumask_copy (&watchdog_cpumask, +housekeeping_cpumask (HK_FLAG_TIMER ));if (!watchdog_nmi_probe ()) nmi_watchdog_available = true;
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation: Introduce housekeeping flags
sched/isolation: Introduce housekeeping flags
Commit-ID: de201559df872f83d0c08fb4effe3efd28e6cbc8 Gitweb: https://git.kernel.org/tip/de201559df872f83d0c08fb4effe3efd28e6cbc8 Author: Frederic Weisbecker <[email protected]> AuthorDate: Fri, 27 Oct 2017 04:42:35 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 27 Oct 2017 09:55:29 +0200
sched/isolation: Introduce housekeeping flags
Before we implement isolcpus under housekeeping, we need the isolation features to be more finegrained. For example some people want NOHZ_FULL without the full scheduler isolation, others want full scheduler isolation without NOHZ_FULL.
So let's cut all these isolation features piecewise, at the risk of overcutting it right now. We can still merge some flags later if they always make sense together.
Signed-off-by Frederic Weisbecker <[email protected]>
Acked-by Thomas Gleixner <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Wanpeng Li <[email protected]>
Signed-off-by Ingo Molnar <[email protected]>
--- drivers/net/ethernet/tile/tilegx.c | 4 ++-- include/linux/sched/isolation.h | 26 +++++++++++++++++--------- kernel/rcu/tree_plugin.h | 2 +- kernel/rcu/update.c | 2 +- kernel/sched/core.c | 8 ++++---- kernel/sched/fair.c | 2 +- kernel/sched/isolation.c | 26 +++++++++++++++----------- kernel/watchdog.c | 3 ++- 8 files changed, 43 insertions(+), 30 deletions(-)
drivers/net/ethernet/tile/tilegx.c +2 -2
@@ -2270,8 +2270,8 @@ static int __init tile_net_init_module(void)tile_net_dev_init (name, mac);if (!network_cpus_init ()) -cpumask_and (&network_cpus_map,housekeeping_cpumask (), - cpu_online_mask); +cpumask_and (&network_cpus_map, +housekeeping_cpumask (HK_FLAG_MISC ), cpu_online_mask);return 0 ; }
include/linux/sched/isolation.h +17 -9
@@ -5,35 +5,43 @@#include <linux/init.h> #include <linux/tick.h> +enum hk_flags { +HK_FLAG_TIMER =1 , +HK_FLAG_RCU = (1 <<1 ), +HK_FLAG_MISC = (1 <<2 ), +HK_FLAG_SCHED = (1 <<3 ), +}; +#ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE (housekeeping_overriden); -extern int housekeeping_any_cpu (void ); -extern const struct cpumask *housekeeping_cpumask (void ); -extern void housekeeping_affine (struct task_struct *t); -extern bool housekeeping_test_cpu (int cpu); +extern int housekeeping_any_cpu (enum hk_flags flags); +extern const struct cpumask *housekeeping_cpumask (enum hk_flags flags); +extern void housekeeping_affine (struct task_struct *t,enum hk_flags flags); +extern bool housekeeping_test_cpu (int cpu,enum hk_flags flags);extern void __init housekeeping_init (void );#else -static inline int housekeeping_any_cpu (void ) +static inline int housekeeping_any_cpu (enum hk_flags flags) {return smp_processor_id (); } -static inline const struct cpumask *housekeeping_cpumask (void ) +static inline const struct cpumask *housekeeping_cpumask (enum hk_flags flags) {return cpu_possible_mask; } -static inline void housekeeping_affine (struct task_struct *t) { } +static inline void housekeeping_affine (struct task_struct *t, +enum hk_flags flags) { }static inline void housekeeping_init (void ) { }#endif /* CONFIG_CPU_ISOLATION */ -static inline bool housekeeping_cpu (int cpu) +static inline bool housekeeping_cpu (int cpu,enum hk_flags flags) {#ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely (&housekeeping_overriden)) -return housekeeping_test_cpu (cpu); +return housekeeping_test_cpu (cpu, flags);#endif return true; }
kernel/rcu/tree_plugin.h +1 -1
@@ -2584,7 +2584,7 @@ static void rcu_bind_gp_kthread(void)if (!tick_nohz_full_enabled ())return ; -housekeeping_affine (current); +housekeeping_affine (current,HK_FLAG_RCU ); }/* Record the current task on dyntick-idle entry. */
kernel/rcu/update.c +1 -1
@@ -719,7 +719,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)LIST_HEAD (rcu_tasks_holdouts);/* Run on housekeeping CPUs by default. Sysadm can move if desired. */ -housekeeping_affine (current); +housekeeping_affine (current,HK_FLAG_RCU );/* * Each pass through the following loop makes one check for
kernel/sched/core.c +4 -4
@@ -527,7 +527,7 @@ int get_nohz_timer_target(void)int i, cpu =smp_processor_id ();struct sched_domain *sd; -if (!idle_cpu (cpu) &&housekeeping_cpu (cpu)) +if (!idle_cpu (cpu) &&housekeeping_cpu (cpu,HK_FLAG_TIMER ))return cpu;rcu_read_lock ();
@@ -536,15 +536,15 @@ int get_nohz_timer_target(void)if (cpu == i)continue ; -if (!idle_cpu (i) &&housekeeping_cpu (i)) { +if (!idle_cpu (i) &&housekeeping_cpu (i,HK_FLAG_TIMER )) { cpu = i; goto unlock; } } } -if (!housekeeping_cpu (cpu)) - cpu =housekeeping_any_cpu (); +if (!housekeeping_cpu (cpu,HK_FLAG_TIMER )) + cpu =housekeeping_any_cpu (HK_FLAG_TIMER ); unlock:rcu_read_unlock ();return cpu;
kernel/sched/fair.c +1 -1
@@ -9027,7 +9027,7 @@ void nohz_balance_enter_idle(int cpu)return ;/* Spare idle load balancing on CPUs that don't want to be disturbed: */ -if (!housekeeping_cpu (cpu)) +if (!housekeeping_cpu (cpu,HK_FLAG_SCHED ))return ;if (test_bit (NOHZ_TICK_STOPPED ,nohz_flags (cpu)))
kernel/sched/isolation.c +15 -11
@@ -15,37 +15,39 @@DEFINE_STATIC_KEY_FALSE (housekeeping_overriden);EXPORT_SYMBOL_GPL (housekeeping_overriden);static cpumask_var_t housekeeping_mask; +static unsigned int housekeeping_flags; -int housekeeping_any_cpu (void ) +int housekeeping_any_cpu (enum hk_flags flags) {if (static_branch_unlikely (&housekeeping_overriden)) -return cpumask_any_and (housekeeping_mask, cpu_online_mask); - +if (housekeeping_flags & flags) +return cpumask_any_and (housekeeping_mask, cpu_online_mask);return smp_processor_id (); }EXPORT_SYMBOL_GPL (housekeeping_any_cpu); -const struct cpumask *housekeeping_cpumask (void ) +const struct cpumask *housekeeping_cpumask (enum hk_flags flags) {if (static_branch_unlikely (&housekeeping_overriden)) -return housekeeping_mask; - +if (housekeeping_flags & flags) +return housekeeping_mask;return cpu_possible_mask; }EXPORT_SYMBOL_GPL (housekeeping_cpumask); -void housekeeping_affine (struct task_struct *t) +void housekeeping_affine (struct task_struct *t,enum hk_flags flags) {if (static_branch_unlikely (&housekeeping_overriden)) -set_cpus_allowed_ptr (t, housekeeping_mask); +if (housekeeping_flags & flags) +set_cpus_allowed_ptr (t, housekeeping_mask); }EXPORT_SYMBOL_GPL (housekeeping_affine); -bool housekeeping_test_cpu (int cpu) +bool housekeeping_test_cpu (int cpu,enum hk_flags flags) {if (static_branch_unlikely (&housekeeping_overriden)) -return cpumask_test_cpu (cpu, housekeeping_mask); - +if (housekeeping_flags & flags) +return cpumask_test_cpu (cpu, housekeeping_mask);return true; }EXPORT_SYMBOL_GPL (housekeeping_test_cpu);
@@ -65,6 +67,8 @@ void __init housekeeping_init(void)cpumask_andnot (housekeeping_mask, cpu_possible_mask, tick_nohz_full_mask); + housekeeping_flags =HK_FLAG_TIMER |HK_FLAG_RCU |HK_FLAG_MISC ; +static_branch_enable (&housekeeping_overriden);/* We need at least one CPU to handle housekeeping work */
kernel/watchdog.c +2 -1
@@ -777,7 +777,8 @@ void __init lockup_detector_init(void)if (tick_nohz_full_enabled ())pr_info ("Disabling watchdog on nohz_full cores by default\n" ); -cpumask_copy (&watchdog_cpumask,housekeeping_cpumask ()); +cpumask_copy (&watchdog_cpumask, +housekeeping_cpumask (HK_FLAG_TIMER ));if (!watchdog_nmi_probe ()) nmi_watchdog_available = true;
Frederic Weisbecker
maintainerPATCH 9/12 housekeeping: Handle the nohz_full= parameter
In reply to Frederic WeisbeckerWe want to centralize the isolation management from the housekeeping subsystem. Therefore we need to handle the nohz_full= parameter from there.
Since nohz_full= so far has involved unbound timers, watchdog, RCU and tilegx NAPI isolation, we keep that default behaviour.
nohz_full= is deemed to be deprecated in the future. We want to control the isolation features from the isolcpus= parameter.
Signed-off-by Frederic Weisbecker <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Wanpeng Li <[email protected]>
--- include/linux/sched/isolation.h | 1 + include/linux/tick.h | 2 ++ init/Kconfig | 1 - kernel/sched/isolation.c | 44 +++++++++++++++++++++++++++++------------ kernel/time/tick-sched.c | 13 +++--------- 5 files changed, 37 insertions(+), 24 deletions(-)
include/linux/sched/isolation.h +1 -0
@@ -10,6 +10,7 @@ enum hk_flags {HK_FLAG_RCU = (1 <<1 ),HK_FLAG_MISC = (1 <<2 ),HK_FLAG_SCHED = (1 <<3 ), + HK_FLAG_TICK = (1 << 4), };#ifdef CONFIG_CPU_ISOLATION
include/linux/tick.h +2 -0
@@ -228,6 +228,7 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal,extern void tick_nohz_full_kick_cpu (int cpu);extern void __tick_nohz_task_switch (void ); +extern void __init tick_nohz_full_setup (cpumask_var_t cpumask);#else static inline bool tick_nohz_full_enabled (void ) {return false; }static inline bool tick_nohz_full_cpu (int cpu) {return false; }
@@ -248,6 +249,7 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal,static inline void tick_nohz_full_kick_cpu (int cpu) { }static inline void __tick_nohz_task_switch (void ) { } +static inline void tick_nohz_full_setup (cpumask_var_t cpumask) { }#endif static inline void tick_nohz_task_switch (void )
init/Kconfig +0 -1
@@ -474,7 +474,6 @@ endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION bool "CPU isolation" - depends on NO_HZ_FULL help Make sure that CPUs running critical tasks are not disturbed by any source of "noise" such as unbound workqueues, timers, kthreads...
kernel/sched/isolation.c +31 -13
54 lines not on this page · raw message
kernel/time/tick-sched.c +3 -10
@@ -385,20 +385,13 @@ void __tick_nohz_task_switch(void)local_irq_restore (flags); } -/* Parse the boot-time nohz CPU list from the kernel parameters. */ -static int __init tick_nohz_full_setup (char *str) +/* Get the boot-time nohz CPU list from the kernel parameters. */ +void __init tick_nohz_full_setup (cpumask_var_t cpumask) {alloc_bootmem_cpumask_var (&tick_nohz_full_mask); -if (cpulist_parse (str, tick_nohz_full_mask) <0 ) { -pr_warn ("NO_HZ: Incorrect nohz_full cpumask\n" ); -free_bootmem_cpumask_var (tick_nohz_full_mask); -return 1 ; - } +cpumask_copy (tick_nohz_full_mask, cpumask); tick_nohz_full_running = true; - -return 1 ; } -__setup ("nohz_full=" , tick_nohz_full_setup);static int tick_nohz_cpu_down (unsigned int cpu) {
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation: Handle the nohz_full= parameter
sched/isolation: Handle the nohz_full= parameter
Commit-ID: 6f1982fedd59856bcc42a9b521be4c3ffd2f60a7 Gitweb: https://git.kernel.org/tip/6f1982fedd59856bcc42a9b521be4c3ffd2f60a7 Author: Frederic Weisbecker <[email protected]> AuthorDate: Fri, 27 Oct 2017 04:42:36 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 27 Oct 2017 09:55:30 +0200
sched/isolation: Handle the nohz_full= parameter
We want to centralize the isolation management, done by the housekeeping subsystem. Therefore we need to handle the nohz_full= parameter from there.
Since nohz_full= so far has involved unbound timers, watchdog, RCU and tilegx NAPI isolation, we keep that default behaviour.
nohz_full= will be deprecated in the future. We want to control the isolation features from the isolcpus= parameter.
Signed-off-by Frederic Weisbecker <[email protected]>
Acked-by Thomas Gleixner <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Wanpeng Li <[email protected]>
Signed-off-by Ingo Molnar <[email protected]>
--- include/linux/sched/isolation.h | 1 + include/linux/tick.h | 2 ++ init/Kconfig | 1 - kernel/sched/isolation.c | 42 +++++++++++++++++++++++++++++------------ kernel/time/tick-sched.c | 13 +++---------- 5 files changed, 36 insertions(+), 23 deletions(-)
include/linux/sched/isolation.h +1 -0
@@ -10,6 +10,7 @@ enum hk_flags {HK_FLAG_RCU = (1 <<1 ),HK_FLAG_MISC = (1 <<2 ),HK_FLAG_SCHED = (1 <<3 ), + HK_FLAG_TICK = (1 << 4), };#ifdef CONFIG_CPU_ISOLATION
include/linux/tick.h +2 -0
@@ -228,6 +228,7 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal,extern void tick_nohz_full_kick_cpu (int cpu);extern void __tick_nohz_task_switch (void ); +extern void __init tick_nohz_full_setup (cpumask_var_t cpumask);#else static inline bool tick_nohz_full_enabled (void ) {return false; }static inline bool tick_nohz_full_cpu (int cpu) {return false; }
@@ -248,6 +249,7 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal,static inline void tick_nohz_full_kick_cpu (int cpu) { }static inline void __tick_nohz_task_switch (void ) { } +static inline void tick_nohz_full_setup (cpumask_var_t cpumask) { }#endif static inline void tick_nohz_task_switch (void )
init/Kconfig +0 -1
@@ -474,7 +474,6 @@ endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION bool "CPU isolation" - depends on NO_HZ_FULL help Make sure that CPUs running critical tasks are not disturbed by any source of "noise" such as unbound workqueues, timers, kthreads...
kernel/sched/isolation.c +30 -12
53 lines not on this page · raw message
kernel/time/tick-sched.c +3 -10
@@ -385,20 +385,13 @@ out:local_irq_restore (flags); } -/* Parse the boot-time nohz CPU list from the kernel parameters. */ -static int __init tick_nohz_full_setup (char *str) +/* Get the boot-time nohz CPU list from the kernel parameters. */ +void __init tick_nohz_full_setup (cpumask_var_t cpumask) {alloc_bootmem_cpumask_var (&tick_nohz_full_mask); -if (cpulist_parse (str, tick_nohz_full_mask) <0 ) { -pr_warn ("NO_HZ: Incorrect nohz_full cpumask\n" ); -free_bootmem_cpumask_var (tick_nohz_full_mask); -return 1 ; - } +cpumask_copy (tick_nohz_full_mask, cpumask); tick_nohz_full_running = true; - -return 1 ; } -__setup ("nohz_full=" , tick_nohz_full_setup);static int tick_nohz_cpu_down (unsigned int cpu) {
Frederic Weisbecker
maintainerPATCH 10/12 housekeeping: Move isolcpus to housekeeping
In reply to Frederic WeisbeckerWe want to centralize the isolation features on the housekeeping subsystem and scheduler domain isolation is a significant part of it.
No intended behaviour change, we just reuse the housekeeping cpumask and core code.
Signed-off-by Frederic Weisbecker <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Wanpeng Li <[email protected]>
Cc Luiz Capitulino <[email protected]>
--- drivers/base/cpu.c | 11 +++++++- include/linux/sched.h | 2 -- include/linux/sched/isolation.h | 1 + kernel/cgroup/cpuset.c | 15 ++++------ kernel/sched/core.c | 16 +---------- kernel/sched/isolation.c | 61 +++++++++++++++++++++++++++++++++-------- kernel/sched/topology.c | 24 ++++------------ 7 files changed, 72 insertions(+), 58 deletions(-)
drivers/base/cpu.c +10 -1
@@ -18,6 +18,7 @@#include <linux/cpufeature.h> #include <linux/tick.h> #include <linux/pm_qos.h> +#include <linux/sched/isolation.h> #include "base.h"
@@ -271,8 +272,16 @@ static ssize_t print_cpus_isolated(struct device *dev, struct device_attribute *attr, char *buf) { int n = 0, len = PAGE_SIZE-2; +cpumask_var_t isolated; - n =scnprintf (buf, len,"%*pbl\n" ,cpumask_pr_args (cpu_isolated_map)); +if (!alloc_cpumask_var (&isolated,GFP_KERNEL )) +return -ENOMEM ; + +cpumask_andnot (isolated, cpu_possible_mask, +housekeeping_cpumask (HK_FLAG_DOMAIN )); + n =scnprintf (buf, len,"%*pbl\n" ,cpumask_pr_args (isolated)); + +free_cpumask_var (isolated);return n; }
include/linux/sched.h +0 -2
@@ -165,8 +165,6 @@ struct task_group;/* Task command name length: */ #define TASK_COMM_LEN 16 -extern cpumask_var_t cpu_isolated_map; -extern void scheduler_tick (void );#define MAX_SCHEDULE_TIMEOUT LONG_MAX
include/linux/sched/isolation.h +1 -0
@@ -11,6 +11,7 @@ enum hk_flags {HK_FLAG_MISC = (1 <<2 ),HK_FLAG_SCHED = (1 <<3 ),HK_FLAG_TICK = (1 <<4 ), + HK_FLAG_DOMAIN = (1 << 5), };#ifdef CONFIG_CPU_ISOLATION
kernel/cgroup/cpuset.c +5 -10
@@ -57,7 +57,7 @@#include <linux/backing-dev.h> #include <linux/sort.h> #include <linux/oom.h> - +#include <linux/sched/isolation.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <linux/mutex.h>
@@ -656,7 +656,6 @@ static int generate_sched_domains(cpumask_var_t **domains,int csn;/* how many cpuset ptrs in csa so far */ int i, j, k;/* indices for partition finding loops */ cpumask_var_t *doms;/* resulting partition; i.e. sched domains */ -cpumask_var_t non_isolated_cpus;/* load balanced CPUs */ struct sched_domain_attr *dattr;/* attributes for custom domains */ int ndoms =0 ;/* number of sched domains in result */ int nslot;/* next empty doms[] struct cpumask slot */
@@ -666,10 +665,6 @@ static int generate_sched_domains(cpumask_var_t **domains, dattr =NULL ; csa =NULL ; -if (!alloc_cpumask_var (&non_isolated_cpus,GFP_KERNEL )) - goto done; -cpumask_andnot (non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); -/* Special case for the 99% of systems with one, full, sched domain */ if (is_sched_load_balance (&top_cpuset)) { ndoms =1 ;
@@ -683,7 +678,7 @@ static int generate_sched_domains(cpumask_var_t **domains,update_domain_attr_tree (dattr, &top_cpuset); }cpumask_and (doms[0 ], top_cpuset.effective_cpus, - non_isolated_cpus); +housekeeping_cpumask (HK_FLAG_DOMAIN )); goto done; }
@@ -707,7 +702,8 @@ static int generate_sched_domains(cpumask_var_t **domains,*/ if (!cpumask_empty (cp->cpus_allowed) && !(is_sched_load_balance (cp) && -cpumask_intersects (cp->cpus_allowed, non_isolated_cpus))) +cpumask_intersects (cp->cpus_allowed, +housekeeping_cpumask (HK_FLAG_DOMAIN ))))continue ;if (is_sched_load_balance (cp))
@@ -789,7 +785,7 @@ static int generate_sched_domains(cpumask_var_t **domains,if (apn == b->pn) {cpumask_or (dp, dp, b->effective_cpus); -cpumask_and (dp, dp, non_isolated_cpus); +cpumask_and (dp, dp,housekeeping_cpumask (HK_FLAG_DOMAIN ));if (dattr)update_domain_attr_tree (dattr + nslot, b);
@@ -802,7 +798,6 @@ static int generate_sched_domains(cpumask_var_t **domains,BUG_ON (nslot != ndoms); done: -free_cpumask_var (non_isolated_cpus);kfree (csa);/*
kernel/sched/core.c +1 -15
@@ -84,9 +84,6 @@ __read_mostly int scheduler_running;*/ int sysctl_sched_rt_runtime =950000 ; -/* CPUs with isolated domains */ -cpumask_var_t cpu_isolated_map; -/* * __task_rq_lock - lock the rq @p resides on. */
@@ -5735,10 +5732,6 @@ static inline void sched_init_smt(void) { }void __init sched_init_smp (void ) { -cpumask_var_t non_isolated_cpus; - -alloc_cpumask_var (&non_isolated_cpus,GFP_KERNEL ); -sched_init_numa ();/*
@@ -5748,16 +5741,12 @@ void __init sched_init_smp(void)*/ mutex_lock (&sched_domains_mutex);sched_init_domains (cpu_active_mask); -cpumask_andnot (non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); -if (cpumask_empty (non_isolated_cpus)) -cpumask_set_cpu (smp_processor_id (), non_isolated_cpus);mutex_unlock (&sched_domains_mutex);/* Move init over to a non-isolated CPU */ -if (set_cpus_allowed_ptr (current, non_isolated_cpus) <0 ) +if (set_cpus_allowed_ptr (current,housekeeping_cpumask (HK_FLAG_DOMAIN )) <0 )BUG ();sched_init_granularity (); -free_cpumask_var (non_isolated_cpus);init_sched_rt_class ();init_sched_dl_class ();
@@ -5961,9 +5950,6 @@ void __init sched_init(void) calc_load_update = jiffies +LOAD_FREQ ;#ifdef CONFIG_SMP -/* May be allocated at isolcpus cmdline parse time */ -if (cpu_isolated_map ==NULL ) -zalloc_cpumask_var (&cpu_isolated_map,GFP_NOWAIT );idle_thread_set_boot_cpu ();set_cpu_rq_start_time (smp_processor_id ());#endif
kernel/sched/isolation.c +49 -12
81 lines not on this page · raw message
kernel/sched/topology.c +6 -18
@@ -3,6 +3,7 @@*/ #include <linux/sched.h> #include <linux/mutex.h> +#include <linux/sched/isolation.h> #include "sched.h"
@@ -469,21 +470,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)update_top_cache_domain (cpu); } -/* Setup the mask of CPUs configured for isolated domains */ -static int __init isolated_cpu_setup (char *str) -{ -int ret; - -alloc_bootmem_cpumask_var (&cpu_isolated_map); - ret =cpulist_parse (str, cpu_isolated_map); -if (ret ||cpumask_last (cpu_isolated_map) >= nr_cpu_ids) { -pr_err ("sched: Error, all isolcpus= values must be between 0 and %u - ignoring them.\n" , nr_cpu_ids-1 ); -return 0 ; - } -return 1 ; -} -__setup ("isolcpus=" , isolated_cpu_setup); -struct s_data {struct sched_domain **__percpu sd;struct root_domain *rd;
@@ -1792,7 +1778,7 @@ int sched_init_domains(const struct cpumask *cpu_map) doms_cur =alloc_sched_domains (ndoms_cur);if (!doms_cur) doms_cur = &fallback_doms; -cpumask_andnot (doms_cur[0 ], cpu_map, cpu_isolated_map); +cpumask_and (doms_cur[0 ], cpu_map,housekeeping_cpumask (HK_FLAG_DOMAIN )); err =build_sched_domains (doms_cur[0 ],NULL );register_sched_domain_sysctl ();
@@ -1875,7 +1861,8 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], doms_new =alloc_sched_domains (1 );if (doms_new) { n =1 ; -cpumask_andnot (doms_new[0 ], cpu_active_mask, cpu_isolated_map); +cpumask_and (doms_new[0 ], cpu_active_mask, +housekeeping_cpumask (HK_FLAG_DOMAIN )); } }else { n = ndoms_new;
@@ -1898,7 +1885,8 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],if (!doms_new) { n =0 ; doms_new = &fallback_doms; -cpumask_andnot (doms_new[0 ], cpu_active_mask, cpu_isolated_map); +cpumask_and (doms_new[0 ], cpu_active_mask, +housekeeping_cpumask (HK_FLAG_DOMAIN )); }/* Build new domains: */
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation: Move isolcpus= handling to the housekeeping code
sched/isolation: Move isolcpus= handling to the housekeeping code
Commit-ID: edb9382175c3ebdced8ffdb3e0f20052ad9fdbe9 Gitweb: https://git.kernel.org/tip/edb9382175c3ebdced8ffdb3e0f20052ad9fdbe9 Author: Frederic Weisbecker <[email protected]> AuthorDate: Fri, 27 Oct 2017 04:42:37 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 27 Oct 2017 09:55:30 +0200
sched/isolation: Move isolcpus= handling to the housekeeping code
We want to centralize the isolation features, to be done by the housekeeping subsystem and scheduler domain isolation is a significant part of it.
No intended behaviour change, we just reuse the housekeeping cpumask and core code.
Signed-off-by Frederic Weisbecker <[email protected]>
Acked-by Thomas Gleixner <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Wanpeng Li <[email protected]>
Signed-off-by Ingo Molnar <[email protected]>
--- drivers/base/cpu.c | 11 ++++++- include/linux/sched.h | 2 -- include/linux/sched/isolation.h | 1 + kernel/cgroup/cpuset.c | 15 ++++------ kernel/sched/core.c | 16 +---------- kernel/sched/isolation.c | 63 ++++++++++++++++++++++++++++++++--------- kernel/sched/topology.c | 24 ++++------------ 7 files changed, 73 insertions(+), 59 deletions(-)
drivers/base/cpu.c +10 -1
@@ -18,6 +18,7 @@#include <linux/cpufeature.h> #include <linux/tick.h> #include <linux/pm_qos.h> +#include <linux/sched/isolation.h> #include "base.h"
@@ -271,8 +272,16 @@ static ssize_t print_cpus_isolated(struct device *dev, struct device_attribute *attr, char *buf) { int n = 0, len = PAGE_SIZE-2; +cpumask_var_t isolated; - n =scnprintf (buf, len,"%*pbl\n" ,cpumask_pr_args (cpu_isolated_map)); +if (!alloc_cpumask_var (&isolated,GFP_KERNEL )) +return -ENOMEM ; + +cpumask_andnot (isolated, cpu_possible_mask, +housekeeping_cpumask (HK_FLAG_DOMAIN )); + n =scnprintf (buf, len,"%*pbl\n" ,cpumask_pr_args (isolated)); + +free_cpumask_var (isolated);return n; }
include/linux/sched.h +0 -2
@@ -165,8 +165,6 @@ struct task_group;/* Task command name length: */ #define TASK_COMM_LEN 16 -extern cpumask_var_t cpu_isolated_map; -extern void scheduler_tick (void );#define MAX_SCHEDULE_TIMEOUT LONG_MAX
include/linux/sched/isolation.h +1 -0
@@ -11,6 +11,7 @@ enum hk_flags {HK_FLAG_MISC = (1 <<2 ),HK_FLAG_SCHED = (1 <<3 ),HK_FLAG_TICK = (1 <<4 ), + HK_FLAG_DOMAIN = (1 << 5), };#ifdef CONFIG_CPU_ISOLATION
kernel/cgroup/cpuset.c +5 -10
@@ -57,7 +57,7 @@#include <linux/backing-dev.h> #include <linux/sort.h> #include <linux/oom.h> - +#include <linux/sched/isolation.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <linux/mutex.h>
@@ -656,7 +656,6 @@ static int generate_sched_domains(cpumask_var_t **domains,int csn;/* how many cpuset ptrs in csa so far */ int i, j, k;/* indices for partition finding loops */ cpumask_var_t *doms;/* resulting partition; i.e. sched domains */ -cpumask_var_t non_isolated_cpus;/* load balanced CPUs */ struct sched_domain_attr *dattr;/* attributes for custom domains */ int ndoms =0 ;/* number of sched domains in result */ int nslot;/* next empty doms[] struct cpumask slot */
@@ -666,10 +665,6 @@ static int generate_sched_domains(cpumask_var_t **domains, dattr =NULL ; csa =NULL ; -if (!alloc_cpumask_var (&non_isolated_cpus,GFP_KERNEL )) - goto done; -cpumask_andnot (non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); -/* Special case for the 99% of systems with one, full, sched domain */ if (is_sched_load_balance (&top_cpuset)) { ndoms =1 ;
@@ -683,7 +678,7 @@ static int generate_sched_domains(cpumask_var_t **domains,update_domain_attr_tree (dattr, &top_cpuset); }cpumask_and (doms[0 ], top_cpuset.effective_cpus, - non_isolated_cpus); +housekeeping_cpumask (HK_FLAG_DOMAIN )); goto done; }
@@ -707,7 +702,8 @@ static int generate_sched_domains(cpumask_var_t **domains,*/ if (!cpumask_empty (cp->cpus_allowed) && !(is_sched_load_balance (cp) && -cpumask_intersects (cp->cpus_allowed, non_isolated_cpus))) +cpumask_intersects (cp->cpus_allowed, +housekeeping_cpumask (HK_FLAG_DOMAIN ))))continue ;if (is_sched_load_balance (cp))
@@ -789,7 +785,7 @@ restart:if (apn == b->pn) {cpumask_or (dp, dp, b->effective_cpus); -cpumask_and (dp, dp, non_isolated_cpus); +cpumask_and (dp, dp,housekeeping_cpumask (HK_FLAG_DOMAIN ));if (dattr)update_domain_attr_tree (dattr + nslot, b);
@@ -802,7 +798,6 @@ restart:BUG_ON (nslot != ndoms); done: -free_cpumask_var (non_isolated_cpus);kfree (csa);/*
kernel/sched/core.c +1 -15
@@ -84,9 +84,6 @@ __read_mostly int scheduler_running;*/ int sysctl_sched_rt_runtime =950000 ; -/* CPUs with isolated domains */ -cpumask_var_t cpu_isolated_map; -/* * __task_rq_lock - lock the rq @p resides on. */
@@ -5735,10 +5732,6 @@ static inline void sched_init_smt(void) { }void __init sched_init_smp (void ) { -cpumask_var_t non_isolated_cpus; - -alloc_cpumask_var (&non_isolated_cpus,GFP_KERNEL ); -sched_init_numa ();/*
@@ -5748,16 +5741,12 @@ void __init sched_init_smp(void)*/ mutex_lock (&sched_domains_mutex);sched_init_domains (cpu_active_mask); -cpumask_andnot (non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); -if (cpumask_empty (non_isolated_cpus)) -cpumask_set_cpu (smp_processor_id (), non_isolated_cpus);mutex_unlock (&sched_domains_mutex);/* Move init over to a non-isolated CPU */ -if (set_cpus_allowed_ptr (current, non_isolated_cpus) <0 ) +if (set_cpus_allowed_ptr (current,housekeeping_cpumask (HK_FLAG_DOMAIN )) <0 )BUG ();sched_init_granularity (); -free_cpumask_var (non_isolated_cpus);init_sched_rt_class ();init_sched_dl_class ();
@@ -5961,9 +5950,6 @@ void __init sched_init(void) calc_load_update = jiffies +LOAD_FREQ ;#ifdef CONFIG_SMP -/* May be allocated at isolcpus cmdline parse time */ -if (cpu_isolated_map ==NULL ) -zalloc_cpumask_var (&cpu_isolated_map,GFP_NOWAIT );idle_thread_set_boot_cpu ();set_cpu_rq_start_time (smp_processor_id ());#endif
kernel/sched/isolation.c +50 -13
82 lines not on this page · raw message
kernel/sched/topology.c +6 -18
@@ -3,6 +3,7 @@*/ #include <linux/sched.h> #include <linux/mutex.h> +#include <linux/sched/isolation.h> #include "sched.h"
@@ -469,21 +470,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)update_top_cache_domain (cpu); } -/* Setup the mask of CPUs configured for isolated domains */ -static int __init isolated_cpu_setup (char *str) -{ -int ret; - -alloc_bootmem_cpumask_var (&cpu_isolated_map); - ret =cpulist_parse (str, cpu_isolated_map); -if (ret ||cpumask_last (cpu_isolated_map) >= nr_cpu_ids) { -pr_err ("sched: Error, all isolcpus= values must be between 0 and %u - ignoring them.\n" , nr_cpu_ids-1 ); -return 0 ; - } -return 1 ; -} -__setup ("isolcpus=" , isolated_cpu_setup); -struct s_data {struct sched_domain **__percpu sd;struct root_domain *rd;
@@ -1792,7 +1778,7 @@ int sched_init_domains(const struct cpumask *cpu_map) doms_cur =alloc_sched_domains (ndoms_cur);if (!doms_cur) doms_cur = &fallback_doms; -cpumask_andnot (doms_cur[0 ], cpu_map, cpu_isolated_map); +cpumask_and (doms_cur[0 ], cpu_map,housekeeping_cpumask (HK_FLAG_DOMAIN )); err =build_sched_domains (doms_cur[0 ],NULL );register_sched_domain_sysctl ();
@@ -1875,7 +1861,8 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], doms_new =alloc_sched_domains (1 );if (doms_new) { n =1 ; -cpumask_andnot (doms_new[0 ], cpu_active_mask, cpu_isolated_map); +cpumask_and (doms_new[0 ], cpu_active_mask, +housekeeping_cpumask (HK_FLAG_DOMAIN )); } }else { n = ndoms_new;
@@ -1898,7 +1885,8 @@ match1:if (!doms_new) { n =0 ; doms_new = &fallback_doms; -cpumask_andnot (doms_new[0 ], cpu_active_mask, cpu_isolated_map); +cpumask_and (doms_new[0 ], cpu_active_mask, +housekeeping_cpumask (HK_FLAG_DOMAIN )); }/* Build new domains: */
Frederic Weisbecker
maintainerPATCH 11/12 housekeeping: Add basic isolcpus flags
In reply to Frederic WeisbeckerAdd flags to control nohz and domain isolations from "isolcpus=", in order to centralize the isolation features to a common interface. Domain isolation remains the default so not to break the existing isolcpus boot paramater behaviour.
Further flags in the future may include 0hz (1hz tick offload) and timers, workqueue, RCU, kthread, watchdog, likely all merged together in a common flag ("async"?). In any case, this will have to be modifiable by cpusets.
Signed-off-by Frederic Weisbecker <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Wanpeng Li <[email protected]>
Cc Luiz Capitulino <[email protected]>
--- kernel/sched/isolation.c | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-)
kernel/sched/isolation.c +25 -1
@@ -11,6 +11,7 @@#include <linux/init.h> #include <linux/kernel.h> #include <linux/static_key.h> +#include <linux/ctype.h> DEFINE_STATIC_KEY_FALSE (housekeeping_overriden);EXPORT_SYMBOL_GPL (housekeeping_overriden);
@@ -126,6 +127,29 @@ __setup("nohz_full=", housekeeping_nohz_full_setup);static int __init housekeeping_isolcpus_setup (char *str) { -return housekeeping_setup (str,HK_FLAG_DOMAIN ); +unsigned int flags =0 ; + +while (isalpha (*str)) { +if (!strncmp (str,"nohz," ,5 )) { + str +=5 ; + flags |=HK_FLAG_TICK ; +continue ; + } + +if (!strncmp (str,"domain," ,7 )) { + str +=7 ; + flags |=HK_FLAG_DOMAIN ; +continue ; + } + +pr_warn ("isolcpus: Error, unknown flag\n" ); +return 0 ; + } + +/* Default behaviour for isolcpus without flags */ +if (!flags) + flags |=HK_FLAG_DOMAIN ; + +return housekeeping_setup (str, flags); }__setup ("isolcpus=" , housekeeping_isolcpus_setup);
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation: Add basic isolcpus flags
sched/isolation: Add basic isolcpus flags
Commit-ID: 150dfee95feb913876ced5cc559a342384e8ea97 Gitweb: https://git.kernel.org/tip/150dfee95feb913876ced5cc559a342384e8ea97 Author: Frederic Weisbecker <[email protected]> AuthorDate: Fri, 27 Oct 2017 04:42:38 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 27 Oct 2017 09:55:31 +0200
sched/isolation: Add basic isolcpus flags
Add flags to control NOHZ and domain isolation from "isolcpus=", in order to centralize the isolation features to a common interface. Domain isolation remains the default so not to break the existing isolcpus boot paramater behaviour.
Further flags in the future may include 0hz (1hz tick offload) and timers, workqueue, RCU, kthread, watchdog, likely all merged together in a common flag ("async"?). In any case, this will have to be modifiable by cpusets.
Signed-off-by Frederic Weisbecker <[email protected]>
Acked-by Thomas Gleixner <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Wanpeng Li <[email protected]>
Signed-off-by Ingo Molnar <[email protected]>
--- kernel/sched/isolation.c | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-)
kernel/sched/isolation.c +25 -1
@@ -11,6 +11,7 @@#include <linux/init.h> #include <linux/kernel.h> #include <linux/static_key.h> +#include <linux/ctype.h> DEFINE_STATIC_KEY_FALSE (housekeeping_overriden);EXPORT_SYMBOL_GPL (housekeeping_overriden);
@@ -126,6 +127,29 @@ __setup("nohz_full=", housekeeping_nohz_full_setup);static int __init housekeeping_isolcpus_setup (char *str) { -return housekeeping_setup (str,HK_FLAG_DOMAIN ); +unsigned int flags =0 ; + +while (isalpha (*str)) { +if (!strncmp (str,"nohz," ,5 )) { + str +=5 ; + flags |=HK_FLAG_TICK ; +continue ; + } + +if (!strncmp (str,"domain," ,7 )) { + str +=7 ; + flags |=HK_FLAG_DOMAIN ; +continue ; + } + +pr_warn ("isolcpus: Error, unknown flag\n" ); +return 0 ; + } + +/* Default behaviour for isolcpus without flags */ +if (!flags) + flags |=HK_FLAG_DOMAIN ; + +return housekeeping_setup (str, flags); }__setup ("isolcpus=" , housekeeping_isolcpus_setup);
Frederic Weisbecker
maintainerPATCH 12/12 housekeeping: Document isolcpus flags
In reply to Frederic WeisbeckerSigned-off-by Frederic Weisbecker <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Wanpeng Li <[email protected]>
Cc Luiz Capitulino <[email protected]>
--- Documentation/admin-guide/kernel-parameters.txt | 35 +++++++++++++++---------- 1 file changed, 21 insertions(+), 14 deletions(-)
Documentation/admin-guide/kernel-parameters.txt +21 -14
@@ -1727,20 +1727,27 @@ isapnp= [ISAPNP] Format: <RDP>,<reset>,<pci_scan>,<verbosity> - isolcpus= [KNL,SMP] Isolate CPUs from the general scheduler. - The argument is a cpu list, as described above. - - This option can be used to specify one or more CPUs - to isolate from the general SMP balancing and scheduling - algorithms. You can move a process onto or off an - "isolated" CPU via the CPU affinity syscalls or cpuset. - <cpu number> begins at 0 and the maximum value is - "number of CPUs in system - 1". - - This option is the preferred way to isolate CPUs. The - alternative -- manually setting the CPU mask of all - tasks in the system -- can cause problems and - suboptimal load balancer performance. + isolcpus= [KNL,SMP] Isolate a given set of CPUs from disturbance. + Format: [flag-list,]<cpu-list> + + Specify one or more CPUs to isolate from disturbances + specified in the flag list (default: domain): + + nohz + Disable the tick when a single task runs. + domain + Isolate from the general SMP balancing and scheduling + algorithms. This option is the preferred way to isolate + CPUs from tasks. The alternative -- manually setting the + CPU mask of all tasks in the system, can cause problems + and suboptimal load balancer performance. You can move a + process onto or off an "isolated" CPU via the CPU + affinity syscalls or cpuset. <cpu number> begins at 0 + and the maximum value is "number of CPUs in system - 1". + + The format of <cpu-list> is described above. + + iucv= [HW,NET]
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation: Document the isolcpus= flags
sched/isolation: Document the isolcpus= flags
Commit-ID: 98a06af93784a6ae541e9fc6292ef26177832543 Gitweb: https://git.kernel.org/tip/98a06af93784a6ae541e9fc6292ef26177832543 Author: Frederic Weisbecker <[email protected]> AuthorDate: Fri, 27 Oct 2017 04:42:39 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 27 Oct 2017 09:55:32 +0200
sched/isolation: Document the isolcpus= flags
Signed-off-by Frederic Weisbecker <[email protected]>
Acked-by Thomas Gleixner <[email protected]>
Cc Chris Metcalf <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Luiz Capitulino <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Rik van Riel <[email protected]>
Cc Wanpeng Li <[email protected]>
Signed-off-by Ingo Molnar <[email protected]>
--- Documentation/admin-guide/kernel-parameters.txt | 33 +++++++++++++++---------- 1 file changed, 20 insertions(+), 13 deletions(-)
Documentation/admin-guide/kernel-parameters.txt +20 -13
@@ -1727,20 +1727,27 @@ isapnp= [ISAPNP] Format: <RDP>,<reset>,<pci_scan>,<verbosity> - isolcpus= [KNL,SMP] Isolate CPUs from the general scheduler. - The argument is a cpu list, as described above. + isolcpus= [KNL,SMP] Isolate a given set of CPUs from disturbance. + Format: [flag-list,]<cpu-list> + + Specify one or more CPUs to isolate from disturbances + specified in the flag list (default: domain): + + nohz + Disable the tick when a single task runs. + domain + Isolate from the general SMP balancing and scheduling + algorithms. This option is the preferred way to isolate + CPUs from tasks. The alternative -- manually setting the + CPU mask of all tasks in the system, can cause problems + and suboptimal load balancer performance. You can move a + process onto or off an "isolated" CPU via the CPU + affinity syscalls or cpuset. <cpu number> begins at 0 + and the maximum value is "number of CPUs in system - 1". + + The format of <cpu-list> is described above. + - This option can be used to specify one or more CPUs - to isolate from the general SMP balancing and scheduling - algorithms. You can move a process onto or off an - "isolated" CPU via the CPU affinity syscalls or cpuset. - <cpu number> begins at 0 and the maximum value is - "number of CPUs in system - 1". - - This option is the preferred way to isolate CPUs. The - alternative -- manually setting the CPU mask of all - tasks in the system -- can cause problems and - suboptimal load balancer performance. iucv= [HW,NET]
Peter Zijlstra
maintainerRe: [tip:sched/core] sched/isolation: Document the isolcpus= flags
Documentation/admin-guide/kernel-parameters.txt
Quoted 12 lines · tip-bot for Frederic Weisbecker
Documentation/admin-guide/kernel-parameters.txt +12
-0+ isolcpus= [KNL,SMP] Isolate a given set of CPUs from disturbance. + Format: [flag-list,]<cpu-list> + + Specify one or more CPUs to isolate from disturbances + specified in the flag list (default: domain): + + nohz + Disable the tick when a single task runs. + domain + Isolate from the general SMP balancing and scheduling + algorithms. This option is the preferred way to isolate + CPUs from tasks.
I _strongly_ object to this statement, isolcpus is _not_ the preferred way, cpusets are.
And yes, while cpusets suffers some problems, we _should_ really fix those and not promote this piece of shit isolcpus crap.
Quoted 9 lines
The alternative -- manually setting the
Documentation/admin-guide/kernel-parameters.txt +8
-0+ CPU mask of all tasks in the system, can cause problems + and suboptimal load balancer performance. You can move a + process onto or off an "isolated" CPU via the CPU + affinity syscalls or cpuset. <cpu number> begins at 0 + and the maximum value is "number of CPUs in system - 1". + + The format of <cpu-list> is described above. +
Frederic Weisbecker
maintainerRe: [tip:sched/core] sched/isolation: Document the isolcpus= flags
2017-10-27 15:58 UTC+02:00, Peter Zijlstra <[email protected]>:
Quoted 18 lines
Documentation/admin-guide/kernel-parameters.txt
Quoted 12 lines · tip-bot for Frederic Weisbecker
Documentation/admin-guide/kernel-parameters.txt +12
-0+ isolcpus= [KNL,SMP] Isolate a given set of CPUs from disturbance. + Format: [flag-list,]<cpu-list> + + Specify one or more CPUs to isolate from disturbances + specified in the flag list (default: domain): + + nohz + Disable the tick when a single task runs. + domain + Isolate from the general SMP balancing and scheduling + algorithms. This option is the preferred way to isolate + CPUs from tasks.I _strongly_ object to this statement, isolcpus is _not_ the preferred way, cpusets are.
Quoted 2 lines
And yes, while cpusets suffers some problems, we _should_ really fix those and not promote this piece of shit isolcpus crap.
I definitely agree with that so your position is a relief :-) This patch only indented the existing parameter documentation so fixing its content was beyond its scope. I'll send a patch to correct the text.
Thanks.
Ingo Molnar
maintainerRe: [tip:sched/core] sched/isolation: Document the isolcpus= flags
Quoted 19 lines · Frederic Weisbecker
2017-10-27 15:58 UTC+02:00, Peter Zijlstra <[email protected]>:
Quoted 18 lines
Documentation/admin-guide/kernel-parameters.txt
Quoted 12 lines · tip-bot for Frederic Weisbecker
Documentation/admin-guide/kernel-parameters.txt +12
-0+ isolcpus= [KNL,SMP] Isolate a given set of CPUs from disturbance. + Format: [flag-list,]<cpu-list> + + Specify one or more CPUs to isolate from disturbances + specified in the flag list (default: domain): + + nohz + Disable the tick when a single task runs. + domain + Isolate from the general SMP balancing and scheduling + algorithms. This option is the preferred way to isolate + CPUs from tasks.I _strongly_ object to this statement, isolcpus is _not_ the preferred way, cpusets are.
Quoted 6 lines
Quoted 2 lines
And yes, while cpusets suffers some problems, we _should_ really fix those and not promote this piece of shit isolcpus crap.
I definitely agree with that so your position is a relief :-) This patch only indented the existing parameter documentation so fixing its content was beyond its scope. I'll send a patch to correct the text.
Since it was the last commit in tip:sched/core that was pushed out just hours ago I zapped that last commit, please send an updated patch which we can apply and get a clean series.
Thanks,
Ingo
Frederic Weisbecker
maintainerRe: [tip:sched/core] sched/isolation: Document the isolcpus= flags
2017-10-27 19:06 UTC+02:00, Ingo Molnar <[email protected]>:
Quoted 30 lines · Frederic Weisbecker
Quoted 21 lines
2017-10-27 15:58 UTC+02:00, Peter Zijlstra <[email protected]>:
Quoted 19 lines
Documentation/admin-guide/kernel-parameters.txt
Quoted 12 lines · tip-bot for Frederic Weisbecker
Documentation/admin-guide/kernel-parameters.txt +12
-0+ isolcpus= [KNL,SMP] Isolate a given set of CPUs from disturbance. + Format: [flag-list,]<cpu-list> + + Specify one or more CPUs to isolate from disturbances + specified in the flag list (default: domain): + + nohz + Disable the tick when a single task runs. + domain + Isolate from the general SMP balancing and scheduling + algorithms. This option is the preferred way to isolate + CPUs from tasks.I _strongly_ object to this statement, isolcpus is _not_ the preferred way, cpusets are.
Quoted 6 lines
Quoted 2 lines
And yes, while cpusets suffers some problems, we _should_ really fix those and not promote this piece of shit isolcpus crap.
I definitely agree with that so your position is a relief :-) This patch only indented the existing parameter documentation so fixing its content was beyond its scope. I'll send a patch to correct the text.
Quoted 7 lines
Since it was the last commit in tip:sched/core that was pushed out just hours ago
I zapped that last commit, please send an updated patch which we can apply and get
a clean series.Thanks,
Note the issue was there before that patch. But nevermind I'll resend an updated version of the patch.
Thanks.
Ingo Molnar
maintainerRe: [tip:sched/core] sched/isolation: Document the isolcpus= flags
Quoted 37 lines · Frederic Weisbecker
2017-10-27 19:06 UTC+02:00, Ingo Molnar <[email protected]>:
Quoted 36 lines · Frederic Weisbecker
Quoted 21 lines
2017-10-27 15:58 UTC+02:00, Peter Zijlstra <[email protected]>:
Quoted 19 lines
Documentation/admin-guide/kernel-parameters.txt
Quoted 12 lines · tip-bot for Frederic Weisbecker
Documentation/admin-guide/kernel-parameters.txt +12
-0+ isolcpus= [KNL,SMP] Isolate a given set of CPUs from disturbance. + Format: [flag-list,]<cpu-list> + + Specify one or more CPUs to isolate from disturbances + specified in the flag list (default: domain): + + nohz + Disable the tick when a single task runs. + domain + Isolate from the general SMP balancing and scheduling + algorithms. This option is the preferred way to isolate + CPUs from tasks.I _strongly_ object to this statement, isolcpus is _not_ the preferred way, cpusets are.
Quoted 6 lines
Quoted 2 lines
And yes, while cpusets suffers some problems, we _should_ really fix those and not promote this piece of shit isolcpus crap.
I definitely agree with that so your position is a relief :-) This patch only indented the existing parameter documentation so fixing its content was beyond its scope. I'll send a patch to correct the text.
Since it was the last commit in tip:sched/core that was pushed out just hours ago
I zapped that last commit, please send an updated patch which we can apply and get
a clean series.
Quoted 4 lines
Quoted 1 line
Thanks,
Note the issue was there before that patch. But nevermind I'll resend an updated version of the patch.
Yeah - so we get a single 'improve documentation' commit.
Thanks,
Ingo
Frederic Weisbecker
maintainerRe: [tip:sched/core] sched/isolation: Document the isolcpus= flags
2017-10-27 20:21 UTC+02:00, Ingo Molnar <[email protected]>:
Quoted 42 lines · Frederic Weisbecker
Quoted 40 lines
2017-10-27 19:06 UTC+02:00, Ingo Molnar <[email protected]>:
Quoted 38 lines · Frederic Weisbecker
Quoted 22 lines
2017-10-27 15:58 UTC+02:00, Peter Zijlstra <[email protected]>:
Quoted 20 lines
Documentation/admin-guide/kernel-parameters.txt
Quoted 12 lines · tip-bot for Frederic Weisbecker
Documentation/admin-guide/kernel-parameters.txt +12
-0+ isolcpus= [KNL,SMP] Isolate a given set of CPUs from disturbance. + Format: [flag-list,]<cpu-list> + + Specify one or more CPUs to isolate from disturbances + specified in the flag list (default: domain): + + nohz + Disable the tick when a single task runs. + domain + Isolate from the general SMP balancing and scheduling + algorithms. This option is the preferred way to isolate + CPUs from tasks.I _strongly_ object to this statement, isolcpus is _not_ the preferred
way, cpusets are.Quoted 6 lines
Quoted 2 lines
And yes, while cpusets suffers some problems, we _should_ really fix those and not promote this piece of shit isolcpus crap.
I definitely agree with that so your position is a relief :-) This patch only indented the existing parameter documentation so fixing its content was beyond its scope. I'll send a patch to correct the text.
Since it was the last commit in tip:sched/core that was pushed out just hours ago
I zapped that last commit, please send an updated patch which we can apply
and get
a clean series.
Quoted 6 lines
Quoted 4 lines
Quoted 1 line
Thanks,
Note the issue was there before that patch. But nevermind I'll resend an updated version of the patch.
Yeah - so we get a single 'improve documentation' commit.
Ah ok I see. No problem I'll resend.
Thanks.
Ingo Molnar
maintainerRe: [tip:sched/core] sched/isolation: Document the isolcpus= flags
Quoted 43 lines · Frederic Weisbecker
2017-10-27 20:21 UTC+02:00, Ingo Molnar <[email protected]>:
Quoted 42 lines · Frederic Weisbecker
Quoted 40 lines
2017-10-27 19:06 UTC+02:00, Ingo Molnar <[email protected]>:
Quoted 38 lines · Frederic Weisbecker
Quoted 22 lines
2017-10-27 15:58 UTC+02:00, Peter Zijlstra <[email protected]>:
Quoted 20 lines
Review
Quoted 12 lines · tip-bot for Frederic Weisbecker
(quoted diff) +12
-0+ isolcpus= [KNL,SMP] Isolate a given set of CPUs from disturbance. + Format: [flag-list,]<cpu-list> + + Specify one or more CPUs to isolate from disturbances + specified in the flag list (default: domain): + + nohz + Disable the tick when a single task runs. + domain + Isolate from the general SMP balancing and scheduling + algorithms. This option is the preferred way to isolate + CPUs from tasks.I _strongly_ object to this statement, isolcpus is _not_ the preferred
way, cpusets are.Quoted 6 lines
Quoted 2 lines
And yes, while cpusets suffers some problems, we _should_ really fix those and not promote this piece of shit isolcpus crap.
I definitely agree with that so your position is a relief :-) This patch only indented the existing parameter documentation so fixing its content was beyond its scope. I'll send a patch to correct the text.
Since it was the last commit in tip:sched/core that was pushed out just hours ago
I zapped that last commit, please send an updated patch which we can apply
and get
a clean series.
Quoted 8 lines
Quoted 6 lines
Quoted 4 lines
Quoted 1 line
Thanks,
Note the issue was there before that patch. But nevermind I'll resend an updated version of the patch.
Yeah - so we get a single 'improve documentation' commit.
Ah ok I see. No problem I'll resend.
Thanks!
Ingo
Re: [tip:sched/core] sched/isolation: Document the isolcpus= flags
In reply to Peter ZijlstraQuoted 17 lines · Peter Zijlstra
Documentation/admin-guide/kernel-parameters.txt
Quoted 12 lines · tip-bot for Frederic Weisbecker
Documentation/admin-guide/kernel-parameters.txt +12
-0+ isolcpus= [KNL,SMP] Isolate a given set of CPUs from disturbance. + Format: [flag-list,]<cpu-list> + + Specify one or more CPUs to isolate from disturbances + specified in the flag list (default: domain): + + nohz + Disable the tick when a single task runs. + domain + Isolate from the general SMP balancing and scheduling + algorithms. This option is the preferred way to isolate + CPUs from tasks.I _strongly_ object to this statement, isolcpus is _not_ the preferred way, cpusets are.
Quoted 2 lines
And yes, while cpusets suffers some problems, we _should_ really fix those and not promote this piece of shit isolcpus crap.
+1, isolcpus is the dinosaur that just won't frickn' die.
-Mike
Re: [tip:sched/core] sched/isolation: Document the isolcpus= flags
In reply to Peter ZijlstraQuoted 5 lines · Peter Zijlstra
I _strongly_ object to this statement, isolcpus is _not_ the preferred way, cpusets are.
And yes, while cpusets suffers some problems, we _should_ really fix those and not promote this piece of shit isolcpus crap.
Well low level control at the processor level is important and this allows controlling activities on a processor that is supposed to be dedicated to certain activities without OS interaction.
isolcpus is the *right* approach here because you are micromanaging the OS and are putting dedicated pieces of software on each core.
A cgroup suggests that threads would be scheduled over multiple cores which is *not* what you want. cgroup has to do something with containers etc which is inherently more noisy and needed if you want to do different things with your processing resources.
Peter Zijlstra
maintainerRe: [tip:sched/core] sched/isolation: Document the isolcpus= flags
Quoted 8 lines · Christopher Lameter
Quoted 5 lines · Peter Zijlstra
I _strongly_ object to this statement, isolcpus is _not_ the preferred way, cpusets are.
And yes, while cpusets suffers some problems, we _should_ really fix those and not promote this piece of shit isolcpus crap.
Quoted 6 lines
Well low level control at the processor level is important and this allows controlling activities on a processor that is supposed to be dedicated to certain activities without OS interaction.
isolcpus is the *right* approach here because you are micromanaging the OS and are putting dedicated pieces of software on each core.
That is what you want, and cpusets should allow for that just fine.
Quoted 2 lines
A cgroup suggests that threads would be scheduled over multiple cores which is *not* what you want.
No, that suggestion is false. cpusets should allow you to isolate individual CPUs just fine.
Quoted 1 line
cgroup has to do something with containers
Sod containers. That's just modern group think. cpusets existed long before all that wankery and it should very well retain the original use cases.
That said, I know there's problems with cpusets, and those should be fixed. But that doesn't mean isolcpus is anything other than a vile hack.
Re: [tip:sched/core] sched/isolation: Document the isolcpus= flags
Quoted 4 lines · Peter Zijlstra
Quoted 2 lines
isolcpus is the *right* approach here because you are micromanaging the OS and are putting dedicated pieces of software on each core.
That is what you want, and cpusets should allow for that just fine.
Well yes a cpuset of one processor I guess.
Quoted 11 lines
Quoted 2 lines
A cgroup suggests that threads would be scheduled over multiple cores which is *not* what you want.
No, that suggestion is false. cpusets should allow you to isolate individual CPUs just fine.
Quoted 1 line
cgroup has to do something with containers
Sod containers. That's just modern group think. cpusets existed long before all that wankery and it should very well retain the original use cases.
Historically cpusets were not used for cpu isolation. They were used to restrict applications threads to sets of cpus for performance reasons. And we are here dealing with individual processors.
Quoted 3 lines
That said, I know there's problems with cpusets, and those should be fixed. But that doesn't mean isolcpus is anything other than a vile hack.
Controlling the way an individual processor works would be best done with some kind of configuration in sysfs. I.e. /sys/cpu/<xx>/no_sched or so.
In lieu of that I think isolcpus is definitely better than a cpuset and it is the only way that traditionally processor handling of the OS has been restricted.
Peter Zijlstra
maintainerRe: [tip:sched/core] sched/isolation: Document the isolcpus= flags
Quoted 3 lines · Christopher Lameter
Historically cpusets were not used for cpu isolation. They were used to restrict applications threads to sets of cpus for performance reasons. And we are here dealing with individual processors.
The HPC workloads very much disabled load-balancing across most CPUs. If you disable "sched_load_balance" the thing creates NULL sched_domains, the exact thing isolcpus ends up doing.
This is something cpusets have done for a _long_ time, if not from the very start.
Yes, you can also create smaller sched_domains which is useful for other cases and you can even mix the lot, by creating a small set of load-balanced CPUs for the system tasks while giving a bunch of unbalanced CPUs to your application.
Re: [tip:sched/core] sched/isolation: Document the isolcpus= flags
In reply to Peter ZijlstraQuoted 16 lines · Peter Zijlstra
Quoted 8 lines · Christopher Lameter
Quoted 5 lines · Peter Zijlstra
I _strongly_ object to this statement, isolcpus is _not_ the preferred way, cpusets are.
And yes, while cpusets suffers some problems, we _should_ really fix those and not promote this piece of shit isolcpus crap.
Quoted 6 lines
Well low level control at the processor level is important and this allows controlling activities on a processor that is supposed to be dedicated to certain activities without OS interaction.
isolcpus is the *right* approach here because you are micromanaging the OS and are putting dedicated pieces of software on each core.
Quoted 7 lines
That is what you want, and cpusets should allow for that just fine.
Quoted 2 lines
A cgroup suggests that threads would be scheduled over multiple cores which is *not* what you want.
No, that suggestion is false. cpusets should allow you to isolate individual CPUs just fine.
It does. I do RT jitter testing with it regularly. If it didn't work, my 8 socket box would let me know instantly, by completely sucking :)
-Mike