On Mon, Aug 27, 2018 at 09:16:55PM +0300, Alexey Budankov wrote:
>
> Trace file offset are linearly calculated by perf_mmap__push() code
> for the next possible write operation, but file position is updated by
> the kernel only in the second lseek() syscall after the loop.
> The first lseek() syscall reads that file position for
> the next loop iterations.
>
> record__mmap_read_sync implements sort of a barrier between spilling
> ready profiling data to disk.
>
> Signed-off-by: Alexey Budankov <alexey.budan...@linux.intel.com>
> ---
> Changes in v3:
> - written comments about nanosleep(0.5ms) call prior aio_suspend()
> to cope with intrusiveness of its implementation in glibc;
> - written comments about rationale behind coping profiling data
> into mmap->data buffer;
> ---
> tools/perf/builtin-record.c | 125
> +++++++++++++++++++++++++++++++++++++++++---
> tools/perf/util/mmap.c | 36 ++++++++-----
> tools/perf/util/mmap.h | 2 +-
> 3 files changed, 143 insertions(+), 20 deletions(-)
>
> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> index 22ebeb92ac51..4ac61399a09a 100644
> --- a/tools/perf/builtin-record.c
> +++ b/tools/perf/builtin-record.c
> @@ -53,6 +53,7 @@
> #include <sys/mman.h>
> #include <sys/wait.h>
> #include <linux/time64.h>
> +#include <aio.h>
>
> struct switch_output {
> bool enabled;
> @@ -121,6 +122,23 @@ static int record__write(struct record *rec, void *bf,
> size_t size)
> return 0;
> }
>
> +static int record__aio_write(int trace_fd, struct aiocb *cblock,
> + void *buf, size_t size, off_t off)
> +{
> + cblock->aio_fildes = trace_fd;
> + cblock->aio_buf = buf;
> + cblock->aio_nbytes = size;
> + cblock->aio_offset = off;
> + cblock->aio_sigevent.sigev_notify = SIGEV_NONE;
> +
> + if (aio_write(cblock) == -1) {
> + pr_err("failed to queue perf data, error: %m\n");
> + return -1;
> + }
> +
> + return 0;
> +}
> +
> static int process_synthesized_event(struct perf_tool *tool,
> union perf_event *event,
> struct perf_sample *sample __maybe_unused,
> @@ -130,12 +148,14 @@ static int process_synthesized_event(struct perf_tool
> *tool,
> return record__write(rec, event, event->header.size);
> }
>
> -static int record__pushfn(void *to, void *bf, size_t size)
> +static int record__pushfn(void *to, void *bf, size_t size, off_t off)
> {
> struct record *rec = to;
> + struct perf_mmap *map = bf;
the argument needs to change for record__pushfn,
now with your changes, it's no longer 'void *bf',
but 'struct perf_mmap *map'
also I'm little confused why we have '*to' and cast
it back to 'struct record', but so be it ;-)
thanks,
jirka
