10c6db110d
When you do:
$ perf record -e cycles,cycles,cycles noploop 10
You expect about 10,000 samples for each event, i.e., 10s at
1000samples/sec. However, this is not what's happening. You
get much fewer samples, maybe 3700 samples/event:
$ perf report -D | tail -15
Aggregated stats:
TOTAL events: 10998
MMAP events: 66
COMM events: 2
SAMPLE events: 10930
cycles stats:
TOTAL events: 3644
SAMPLE events: 3644
cycles stats:
TOTAL events: 3642
SAMPLE events: 3642
cycles stats:
TOTAL events: 3644
SAMPLE events: 3644
On a Intel Nehalem or even AMD64, there are 4 counters capable
of measuring cycles, so there is plenty of space to measure those
events without multiplexing (even with the NMI watchdog active).
And even with multiplexing, we'd expect roughly the same number
of samples per event.
The root of the problem was that when the event that caused the buffer
to become full was not the first event passed on the cmdline, the user
notification would get lost. The notification was sent to the file
descriptor of the overflowed event but the perf tool was not polling
on it. The perf tool aggregates all samples into a single buffer,
i.e., the buffer of the first event. Consequently, it assumes
notifications for any event will come via that descriptor.
The seemingly straight forward solution of moving the waitq into the
ringbuffer object doesn't work because of life-time issues. One could
perf_event_set_output() on a fd that you're also blocking on and cause
the old rb object to be freed while its waitq would still be
referenced by the blocked thread -> FAIL.
Therefore link all events to the ringbuffer and broadcast the wakeup
from the ringbuffer object to all possible events that could be waited
upon. This is rather ugly, and we're open to better solutions but it
works for now.
Reported-by: Stephane Eranian <eranian@google.com>
Finished-by: Stephane Eranian <eranian@google.com>
Reviewed-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20111126014731.GA7030@quad
Signed-off-by: Ingo Molnar <mingo@elte.hu>
99 lines
2.3 KiB
C
99 lines
2.3 KiB
C
#ifndef _KERNEL_EVENTS_INTERNAL_H
|
|
#define _KERNEL_EVENTS_INTERNAL_H
|
|
|
|
#define RING_BUFFER_WRITABLE 0x01
|
|
|
|
struct ring_buffer {
|
|
atomic_t refcount;
|
|
struct rcu_head rcu_head;
|
|
#ifdef CONFIG_PERF_USE_VMALLOC
|
|
struct work_struct work;
|
|
int page_order; /* allocation order */
|
|
#endif
|
|
int nr_pages; /* nr of data pages */
|
|
int writable; /* are we writable */
|
|
|
|
atomic_t poll; /* POLL_ for wakeups */
|
|
|
|
local_t head; /* write position */
|
|
local_t nest; /* nested writers */
|
|
local_t events; /* event limit */
|
|
local_t wakeup; /* wakeup stamp */
|
|
local_t lost; /* nr records lost */
|
|
|
|
long watermark; /* wakeup watermark */
|
|
/* poll crap */
|
|
spinlock_t event_lock;
|
|
struct list_head event_list;
|
|
|
|
struct perf_event_mmap_page *user_page;
|
|
void *data_pages[0];
|
|
};
|
|
|
|
extern void rb_free(struct ring_buffer *rb);
|
|
extern struct ring_buffer *
|
|
rb_alloc(int nr_pages, long watermark, int cpu, int flags);
|
|
extern void perf_event_wakeup(struct perf_event *event);
|
|
|
|
extern void
|
|
perf_event_header__init_id(struct perf_event_header *header,
|
|
struct perf_sample_data *data,
|
|
struct perf_event *event);
|
|
extern void
|
|
perf_event__output_id_sample(struct perf_event *event,
|
|
struct perf_output_handle *handle,
|
|
struct perf_sample_data *sample);
|
|
|
|
extern struct page *
|
|
perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff);
|
|
|
|
#ifdef CONFIG_PERF_USE_VMALLOC
|
|
/*
|
|
* Back perf_mmap() with vmalloc memory.
|
|
*
|
|
* Required for architectures that have d-cache aliasing issues.
|
|
*/
|
|
|
|
static inline int page_order(struct ring_buffer *rb)
|
|
{
|
|
return rb->page_order;
|
|
}
|
|
|
|
#else
|
|
|
|
static inline int page_order(struct ring_buffer *rb)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
static unsigned long perf_data_size(struct ring_buffer *rb)
|
|
{
|
|
return rb->nr_pages << (PAGE_SHIFT + page_order(rb));
|
|
}
|
|
|
|
static inline void
|
|
__output_copy(struct perf_output_handle *handle,
|
|
const void *buf, unsigned int len)
|
|
{
|
|
do {
|
|
unsigned long size = min_t(unsigned long, handle->size, len);
|
|
|
|
memcpy(handle->addr, buf, size);
|
|
|
|
len -= size;
|
|
handle->addr += size;
|
|
buf += size;
|
|
handle->size -= size;
|
|
if (!handle->size) {
|
|
struct ring_buffer *rb = handle->rb;
|
|
|
|
handle->page++;
|
|
handle->page &= rb->nr_pages - 1;
|
|
handle->addr = rb->data_pages[handle->page];
|
|
handle->size = PAGE_SIZE << page_order(rb);
|
|
}
|
|
} while (len);
|
|
}
|
|
|
|
#endif /* _KERNEL_EVENTS_INTERNAL_H */
|