Re: [RFC] Proposal for ptrace improvements

[Oleg Nesterov]

On 03/04, Oleg Nesterov wrote:
>
> On 03/04, Denys Vlasenko wrote:
> >
> > # time sh -c './strace -e trace=exit_group ls -lR /usr/share >/dev/null'
> > exit_group(0)                           = ?
> > real	0m47.695s
> > user	0m3.965s
> > sys	0m29.047s
> >
> > strace with PTRACE_GETSIGINFO:
> >
> > # time sh -c './strace -e trace=exit_group ls -lR /usr/share >/dev/null'
> > exit_group(0)                           = ?
> > real	0m51.958s
> > user	0m3.899s
> > sys	0m31.584s
>
> I am wondering how much ptrace_check_attach()->wait_task_inactive()
> contributes... it can sleep.
>
> And note that many ptrace requests do not really need this,
> PTRACE_GETSIGINFO in particular.

could you replace the extra PTRACE_GETSIGINFO by invalid request?

Oleg.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/