Messages in this thread | | | Subject | Re: [PATCH 4/4][RFC] perf_counter: Allow sharing of output channels | From | Peter Zijlstra <> | Date | Wed, 19 Aug 2009 18:24:28 +0200 |
| |
On Wed, 2009-08-19 at 18:19 +0200, Frederic Weisbecker wrote: > On Wed, Aug 19, 2009 at 11:18:27AM +0200, Peter Zijlstra wrote: > > Provide the ability to configure a counter to send its output to > > another (already existing) counter's output stream. > > > > [ compile tested only ] > > > > Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> > > Cc: stephane eranian <eranian@googlemail.com> > > +int perf_counter_set_output(struct perf_counter *counter, int output_fd) > > +{ > > + struct perf_counter *output_counter = NULL; > > + struct file *output_file = NULL; > > + struct perf_counter *old_output; > > + int fput_needed = 0; > > + int ret = -EINVAL; > > + > > + if (!output_fd) > > + goto set; > > + > > + output_file = fget_light(output_fd, &fput_needed); > > + if (!output_file) > > + return -EBADF; > > + > > + if (output_file->f_op != &perf_fops) > > + goto out; > > + > > + output_counter = output_file->private_data; > > + > > + /* Don't chain output fds */ > > + if (output_counter->output) > > + goto out; > > > > If you don't chain them, how do you propagate more than one > path of output redirected?
you mean, fd2->fd1->fd0 ?
You don't, that sounds like a silly thing to do, do fd1->fd0, fd2->fd0 instead.
| |