fe9959a275
The goal of this module is to profile synchronization primitives (i.e. mutexes, recursive mutexes and condition variables) so that scalability issues can be quickly diagnosed. Sync primitives are profiled by QSP based on the vaddr of the object accessed as well as the call site (file:line_nr). That means the same object called from two different call sites will be tracked in separate entries, which might be reported together or separately (see subsequent commit on call site coalescing). Some perf numbers: Host: Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz Command: taskset -c 0 tests/atomic_add-bench -d 5 -m - Before: 54.80 Mops/s - After: 54.75 Mops/s That is, a negligible slowdown due to the now indirect call to qemu_mutex_lock. Note that using a branch instead of an indirect call introduces a more severe slowdown (53.65 Mops/s, i.e. 2% slowdown). Enabling the profiler (with -p, added in this series) is more interesting: - No profiling: 54.75 Mops/s - W/ profiling: 12.53 Mops/s That is, a 4.36X slowdown. We can break down this slowdown by removing the get_clock calls or the entry lookup: - No profiling: 54.75 Mops/s - W/o get_clock: 25.37 Mops/s - W/o entry lookup: 19.30 Mops/s - W/ profiling: 12.53 Mops/s Signed-off-by: Emilio G. Cota <cota@braap.org> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
52 lines
934 B
C
52 lines
934 B
C
#ifndef QEMU_THREAD_POSIX_H
|
|
#define QEMU_THREAD_POSIX_H
|
|
|
|
#include <pthread.h>
|
|
#include <semaphore.h>
|
|
|
|
typedef QemuMutex QemuRecMutex;
|
|
#define qemu_rec_mutex_destroy qemu_mutex_destroy
|
|
#define qemu_rec_mutex_lock_impl qemu_mutex_lock_impl
|
|
#define qemu_rec_mutex_trylock_impl qemu_mutex_trylock_impl
|
|
#define qemu_rec_mutex_unlock qemu_mutex_unlock
|
|
|
|
struct QemuMutex {
|
|
pthread_mutex_t lock;
|
|
#ifdef CONFIG_DEBUG_MUTEX
|
|
const char *file;
|
|
int line;
|
|
#endif
|
|
bool initialized;
|
|
};
|
|
|
|
struct QemuCond {
|
|
pthread_cond_t cond;
|
|
bool initialized;
|
|
};
|
|
|
|
struct QemuSemaphore {
|
|
#ifndef CONFIG_SEM_TIMEDWAIT
|
|
pthread_mutex_t lock;
|
|
pthread_cond_t cond;
|
|
unsigned int count;
|
|
#else
|
|
sem_t sem;
|
|
#endif
|
|
bool initialized;
|
|
};
|
|
|
|
struct QemuEvent {
|
|
#ifndef __linux__
|
|
pthread_mutex_t lock;
|
|
pthread_cond_t cond;
|
|
#endif
|
|
unsigned value;
|
|
bool initialized;
|
|
};
|
|
|
|
struct QemuThread {
|
|
pthread_t thread;
|
|
};
|
|
|
|
#endif
|