mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-25 09:52:03 +07:00
9a46ad6d6d
I'm testing swapout workload in a two-socket Xeon machine. The workload has 10 threads, each thread sequentially accesses separate memory region. TLB flush overhead is very big in the workload. For each page, page reclaim need move it from active lru list and then unmap it. Both need a TLB flush. And this is a multthread workload, TLB flush happens in 10 CPUs. In X86, TLB flush uses generic smp_call)function. So this workload stress smp_call_function_many heavily. Without patch, perf shows: + 24.49% [k] generic_smp_call_function_interrupt - 21.72% [k] _raw_spin_lock - _raw_spin_lock + 79.80% __page_check_address + 6.42% generic_smp_call_function_interrupt + 3.31% get_swap_page + 2.37% free_pcppages_bulk + 1.75% handle_pte_fault + 1.54% put_super + 1.41% grab_super_passive + 1.36% __swap_duplicate + 0.68% blk_flush_plug_list + 0.62% swap_info_get + 6.55% [k] flush_tlb_func + 6.46% [k] smp_call_function_many + 5.09% [k] call_function_interrupt + 4.75% [k] default_send_IPI_mask_sequence_phys + 2.18% [k] find_next_bit swapout throughput is around 1300M/s. With the patch, perf shows: - 27.23% [k] _raw_spin_lock - _raw_spin_lock + 80.53% __page_check_address + 8.39% generic_smp_call_function_single_interrupt + 2.44% get_swap_page + 1.76% free_pcppages_bulk + 1.40% handle_pte_fault + 1.15% __swap_duplicate + 1.05% put_super + 0.98% grab_super_passive + 0.86% blk_flush_plug_list + 0.57% swap_info_get + 8.25% [k] default_send_IPI_mask_sequence_phys + 7.55% [k] call_function_interrupt + 7.47% [k] smp_call_function_many + 7.25% [k] flush_tlb_func + 3.81% [k] _raw_spin_lock_irqsave + 3.78% [k] generic_smp_call_function_single_interrupt swapout throughput is around 1400M/s. So there is around a 7% improvement, and total cpu utilization doesn't change. Without the patch, cfd_data is shared by all CPUs. generic_smp_call_function_interrupt does read/write cfd_data several times which will create a lot of cache ping-pong. With the patch, the data becomes per-cpu. The ping-pong is avoided. And from the perf data, this doesn't make call_single_queue lock contend. Next step is to remove generic_smp_call_function_interrupt() from arch code. Signed-off-by: Shaohua Li <shli@fusionio.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
231 lines
5.8 KiB
C
231 lines
5.8 KiB
C
#ifndef __LINUX_SMP_H
|
|
#define __LINUX_SMP_H
|
|
|
|
/*
|
|
* Generic SMP support
|
|
* Alan Cox. <alan@redhat.com>
|
|
*/
|
|
|
|
#include <linux/errno.h>
|
|
#include <linux/types.h>
|
|
#include <linux/list.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/init.h>
|
|
|
|
extern void cpu_idle(void);
|
|
|
|
typedef void (*smp_call_func_t)(void *info);
|
|
struct call_single_data {
|
|
struct list_head list;
|
|
smp_call_func_t func;
|
|
void *info;
|
|
u16 flags;
|
|
u16 priv;
|
|
};
|
|
|
|
/* total number of cpus in this system (may exceed NR_CPUS) */
|
|
extern unsigned int total_cpus;
|
|
|
|
int smp_call_function_single(int cpuid, smp_call_func_t func, void *info,
|
|
int wait);
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
#include <linux/preempt.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/thread_info.h>
|
|
#include <asm/smp.h>
|
|
|
|
/*
|
|
* main cross-CPU interfaces, handles INIT, TLB flush, STOP, etc.
|
|
* (defined in asm header):
|
|
*/
|
|
|
|
/*
|
|
* stops all CPUs but the current one:
|
|
*/
|
|
extern void smp_send_stop(void);
|
|
|
|
/*
|
|
* sends a 'reschedule' event to another CPU:
|
|
*/
|
|
extern void smp_send_reschedule(int cpu);
|
|
|
|
|
|
/*
|
|
* Prepare machine for booting other CPUs.
|
|
*/
|
|
extern void smp_prepare_cpus(unsigned int max_cpus);
|
|
|
|
/*
|
|
* Bring a CPU up
|
|
*/
|
|
extern int __cpu_up(unsigned int cpunum, struct task_struct *tidle);
|
|
|
|
/*
|
|
* Final polishing of CPUs
|
|
*/
|
|
extern void smp_cpus_done(unsigned int max_cpus);
|
|
|
|
/*
|
|
* Call a function on all other processors
|
|
*/
|
|
int smp_call_function(smp_call_func_t func, void *info, int wait);
|
|
void smp_call_function_many(const struct cpumask *mask,
|
|
smp_call_func_t func, void *info, bool wait);
|
|
|
|
void __smp_call_function_single(int cpuid, struct call_single_data *data,
|
|
int wait);
|
|
|
|
int smp_call_function_any(const struct cpumask *mask,
|
|
smp_call_func_t func, void *info, int wait);
|
|
|
|
void kick_all_cpus_sync(void);
|
|
|
|
/*
|
|
* Generic and arch helpers
|
|
*/
|
|
#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
|
|
void __init call_function_init(void);
|
|
void generic_smp_call_function_single_interrupt(void);
|
|
#define generic_smp_call_function_interrupt \
|
|
generic_smp_call_function_single_interrupt
|
|
#else
|
|
static inline void call_function_init(void) { }
|
|
#endif
|
|
|
|
/*
|
|
* Call a function on all processors
|
|
*/
|
|
int on_each_cpu(smp_call_func_t func, void *info, int wait);
|
|
|
|
/*
|
|
* Call a function on processors specified by mask, which might include
|
|
* the local one.
|
|
*/
|
|
void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
|
|
void *info, bool wait);
|
|
|
|
/*
|
|
* Call a function on each processor for which the supplied function
|
|
* cond_func returns a positive value. This may include the local
|
|
* processor.
|
|
*/
|
|
void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
|
|
smp_call_func_t func, void *info, bool wait,
|
|
gfp_t gfp_flags);
|
|
|
|
/*
|
|
* Mark the boot cpu "online" so that it can call console drivers in
|
|
* printk() and can access its per-cpu storage.
|
|
*/
|
|
void smp_prepare_boot_cpu(void);
|
|
|
|
extern unsigned int setup_max_cpus;
|
|
extern void __init setup_nr_cpu_ids(void);
|
|
extern void __init smp_init(void);
|
|
|
|
#else /* !SMP */
|
|
|
|
static inline void smp_send_stop(void) { }
|
|
|
|
/*
|
|
* These macros fold the SMP functionality into a single CPU system
|
|
*/
|
|
#define raw_smp_processor_id() 0
|
|
static inline int up_smp_call_function(smp_call_func_t func, void *info)
|
|
{
|
|
return 0;
|
|
}
|
|
#define smp_call_function(func, info, wait) \
|
|
(up_smp_call_function(func, info))
|
|
#define on_each_cpu(func,info,wait) \
|
|
({ \
|
|
local_irq_disable(); \
|
|
func(info); \
|
|
local_irq_enable(); \
|
|
0; \
|
|
})
|
|
/*
|
|
* Note we still need to test the mask even for UP
|
|
* because we actually can get an empty mask from
|
|
* code that on SMP might call us without the local
|
|
* CPU in the mask.
|
|
*/
|
|
#define on_each_cpu_mask(mask, func, info, wait) \
|
|
do { \
|
|
if (cpumask_test_cpu(0, (mask))) { \
|
|
local_irq_disable(); \
|
|
(func)(info); \
|
|
local_irq_enable(); \
|
|
} \
|
|
} while (0)
|
|
/*
|
|
* Preemption is disabled here to make sure the cond_func is called under the
|
|
* same condtions in UP and SMP.
|
|
*/
|
|
#define on_each_cpu_cond(cond_func, func, info, wait, gfp_flags)\
|
|
do { \
|
|
void *__info = (info); \
|
|
preempt_disable(); \
|
|
if ((cond_func)(0, __info)) { \
|
|
local_irq_disable(); \
|
|
(func)(__info); \
|
|
local_irq_enable(); \
|
|
} \
|
|
preempt_enable(); \
|
|
} while (0)
|
|
|
|
static inline void smp_send_reschedule(int cpu) { }
|
|
#define smp_prepare_boot_cpu() do {} while (0)
|
|
#define smp_call_function_many(mask, func, info, wait) \
|
|
(up_smp_call_function(func, info))
|
|
static inline void call_function_init(void) { }
|
|
|
|
static inline int
|
|
smp_call_function_any(const struct cpumask *mask, smp_call_func_t func,
|
|
void *info, int wait)
|
|
{
|
|
return smp_call_function_single(0, func, info, wait);
|
|
}
|
|
|
|
static inline void kick_all_cpus_sync(void) { }
|
|
|
|
#endif /* !SMP */
|
|
|
|
/*
|
|
* smp_processor_id(): get the current CPU ID.
|
|
*
|
|
* if DEBUG_PREEMPT is enabled then we check whether it is
|
|
* used in a preemption-safe way. (smp_processor_id() is safe
|
|
* if it's used in a preemption-off critical section, or in
|
|
* a thread that is bound to the current CPU.)
|
|
*
|
|
* NOTE: raw_smp_processor_id() is for internal use only
|
|
* (smp_processor_id() is the preferred variant), but in rare
|
|
* instances it might also be used to turn off false positives
|
|
* (i.e. smp_processor_id() use that the debugging code reports but
|
|
* which use for some reason is legal). Don't use this to hack around
|
|
* the warning message, as your code might not work under PREEMPT.
|
|
*/
|
|
#ifdef CONFIG_DEBUG_PREEMPT
|
|
extern unsigned int debug_smp_processor_id(void);
|
|
# define smp_processor_id() debug_smp_processor_id()
|
|
#else
|
|
# define smp_processor_id() raw_smp_processor_id()
|
|
#endif
|
|
|
|
#define get_cpu() ({ preempt_disable(); smp_processor_id(); })
|
|
#define put_cpu() preempt_enable()
|
|
|
|
/*
|
|
* Callback to arch code if there's nosmp or maxcpus=0 on the
|
|
* boot command line:
|
|
*/
|
|
extern void arch_disable_smp_support(void);
|
|
|
|
void smp_setup_processor_id(void);
|
|
|
|
#endif /* __LINUX_SMP_H */
|