Messages in this thread | | | Date | Mon, 28 Jan 2008 12:38:17 +0300 | From | Pavel Emelyanov <> | Subject | Re: [RFC] Per-thread getrusage |
| |
Andrew Morton wrote: > On Mon, 28 Jan 2008 10:48:23 +0300 Pavel Emelyanov <xemul@openvz.org> wrote: > >> Andrew Morton wrote: >>> On Thu, 17 Jan 2008 13:57:05 +0530 Vinay Sridhar <vinay@linux.vnet.ibm.com> wrote: >>> >>>> Hi All, >>>> >>>> Last year, there was discussion about per-thread getrusage by adding >>>> RUSAGE_THREAD flag to getrusage(). Please refer to the thread >>>> http://lkml.org/lkml/2007/4/4/308. Ulrich had suggested that we should >>>> design a better user-space API. Specifically, we need a >>>> pthread_getrusage interface in the thread library, which accepts >>>> pthread_t, converts pthread_t into the corresponding tid and passes it >>>> down to the syscall. >>>> >>>> There are two ways to implement this in the kernel: >>>> 1) Introduce an additional parameter 'tid' to sys_getrusage() and put >>>> code in glibc to handle getrusage() and pthread_getrusage() calls >>>> correctly. >>>> 2) Introduce a new system call to handle pthread_getrusage() and leave >>>> sys_getrusage() untouched. >>>> >>>> We implemented the second idea above, simply because it avoids touching >>>> any existing code. We have implemented a new syscall, thread_getrusage() >>>> and we have exposed pthread_getrusage() API to applications. >>>> >>>> Could you please share your thoughts on this? Does the approach look >>>> alright? The code is hardly complete. It is just a prototype that works >>>> on IA32 at the moment. >>>> >>>> ... >>>> >>>> +asmlinkage long sys_thread_getrusage(int tid, struct rusage __user *ru); >>> What happens if `tid' refers to a thread in a different pid namespace? >>> >> That's impossible. I explicitly deny namespace creation in case the >> CLONE_THREAD is specified. So all threads of a single process always >> live in one pid namespace. >> > > If the code was using find_task_by_vpid() then OK (I guess). But it is
Yup, find_task_by_vpid() will find the proper (i.e. in your namespace) task.
> looking the tids up in the init_pid_ns. Which I assume means that if it's > in a new namespace and is looking up a sibling thread it will simply fail?
If it looks in the init_pid_ns, then it can either fail or obtain a task from different namespace. The find_task_by_pid_ns() was intended to be used in proc mainly, to get tasks from the namespace pointed by the super-block being explored.
Please excuse my lamentable ignorance, but which code does such things with init_pid_ns? I followed the 'per-thread rusage' thread and didn't find any.
> Or am I missing something? >
Thanks, Pavel
| |