Re: [PATCH v1 1/2] tools api: Add simple timeout to io read

[Arnaldo Carvalho de Melo]

Em Wed, Jun 14, 2023 at 10:36:47AM -0700, Ian Rogers escreveu:
> On Wed, Jun 7, 2023 at 11:20 PM Ian Rogers <irogers@xxxxxxxxxx> wrote:
> >
> > In situations like reading from a pipe it can be useful to have a
> > timeout so that the caller doesn't block indefinitely. Implement a
> > simple one based on poll.
> >
> > Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
> 
> There is overlap in what these patches aim to fix with the 2 submitted
> patches making addr2line more robust:
> https://lore.kernel.org/all/20230613034817.1356114-2-irogers@xxxxxxxxxx/
> 
> I think it could be pragmatic to take both of them. Be robust but
> timeout if addr2line doesn't respond for 1s. What do you think?

Agreed, fixed up a minor conflict and applied.

- Arnaldo
 
> Thanks,
> Ian
> 
> > ---
> >  tools/lib/api/io.h | 28 +++++++++++++++++++++++++++-
> >  1 file changed, 27 insertions(+), 1 deletion(-)
> >
> > diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h
> > index d5e8cf0dada0..9fc429d2852d 100644
> > --- a/tools/lib/api/io.h
> > +++ b/tools/lib/api/io.h
> > @@ -8,6 +8,7 @@
> >  #define __API_IO__
> >
> >  #include <errno.h>
> > +#include <poll.h>
> >  #include <stdlib.h>
> >  #include <string.h>
> >  #include <unistd.h>
> > @@ -23,6 +24,8 @@ struct io {
> >         char *end;
> >         /* Currently accessed data pointer. */
> >         char *data;
> > +       /* Read timeout, 0 implies no timeout. */
> > +       int timeout_ms;
> >         /* Set true on when the end of file on read error. */
> >         bool eof;
> >  };
> > @@ -35,6 +38,7 @@ static inline void io__init(struct io *io, int fd,
> >         io->buf = buf;
> >         io->end = buf;
> >         io->data = buf;
> > +       io->timeout_ms = 0;
> >         io->eof = false;
> >  }
> >
> > @@ -47,7 +51,29 @@ static inline int io__get_char(struct io *io)
> >                 return -1;
> >
> >         if (ptr == io->end) {
> > -               ssize_t n = read(io->fd, io->buf, io->buf_len);
> > +               ssize_t n;
> > +
> > +               if (io->timeout_ms != 0) {
> > +                       struct pollfd pfds[] = {
> > +                               {
> > +                                       .fd = io->fd,
> > +                                       .events = POLLIN,
> > +                               },
> > +                       };
> > +
> > +                       n = poll(pfds, 1, io->timeout_ms);
> > +                       if (n == 0)
> > +                               errno = ETIMEDOUT;
> > +                       if (n > 0 && !(pfds[0].revents & POLLIN)) {
> > +                               errno = EIO;
> > +                               n = -1;
> > +                       }
> > +                       if (n <= 0) {
> > +                               io->eof = true;
> > +                               return -1;
> > +                       }
> > +               }
> > +               n = read(io->fd, io->buf, io->buf_len);
> >
> >                 if (n <= 0) {
> >                         io->eof = true;
> > --
> > 2.41.0.rc0.172.g3f132b7071-goog
> >

-- 

- Arnaldo