Am 05.07.2018 um 09:36 hat Fam Zheng geschrieben:
> A few trace points that can help reveal what is happening in a copy
> offloading I/O path.
> 
> Signed-off-by: Fam Zheng <f...@redhat.com>
> ---
>  block/file-posix.c | 2 ++
>  block/io.c         | 2 ++
>  block/iscsi.c      | 3 +++
>  block/trace-events | 6 ++++++
>  4 files changed, 13 insertions(+)
> 
> diff --git a/block/file-posix.c b/block/file-posix.c
> index 829ee538d8..d3b1609410 100644
> --- a/block/file-posix.c
> +++ b/block/file-posix.c
> @@ -1488,6 +1488,8 @@ static ssize_t handle_aiocb_copy_range(RawPosixAIOData 
> *aiocb)
>          ssize_t ret = copy_file_range(aiocb->aio_fildes, &in_off,
>                                        aiocb->aio_fd2, &out_off,
>                                        bytes, 0);
> +        trace_copy_file_range(aiocb->bs, aiocb->aio_fildes, in_off,
> +                              aiocb->aio_fd2, out_off, bytes, 0, ret);

I think it's preferable to have a common prefix for all trace points in
a driver, so they can be enabled with a glob.

paio_* is the existing one for thread pool based file-posix trace
points. Not sure if we like it or want to replace it with something
else.

Kevin

Reply via email to