Open MPI logo

Open MPI Development Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Development mailing list

Subject: Re: [OMPI devel] RFC: Resilient ORTE
From: Ralph Castain (rhc_at_[hidden])
Date: 2011-06-10 08:51:13


On Jun 10, 2011, at 6:38 AM, Josh Hursey wrote:

> Another problem with this patch, that I mentioned to Wesley and George
> off list, is that it does not handle the case when mpirun/HNP is also
> hosting processes that might fail. In my testing of the patch it
> worked fine if mpirun/HNP was -not- hosting any processes, but once it
> had to host processes then unexpected behavior occurred when a process
> failed. So for those just listening to this thread, Wesley is working
> on a revised patch to address this problem that he will post when it
> is ready.

See my other response to the patch - I think we need to understand why we are storing state in multiple places as it can create unexpected behavior when things are out-of-sync.

>
>
> As far as the RML issue, doesn't the ORTE state machine branch handle
> that case? If it does, then let's push the solution to that problem
> until that branch comes around instead of solving it twice.

No, it doesn't - in fact, it's what breaks the current method. Because we no longer allow event recursion, the RML message never gets out of the app. Hence my question.

I honestly don't think we need to have orte be aware of the distinction between "aborted by cmd" and "aborted by signal" as the only diff is in the error message. There ought to be some other way of resolving this?

>
> -- Josh
>
>
> On Fri, Jun 10, 2011 at 8:22 AM, Ralph Castain <rhc_at_[hidden]> wrote:
>> Something else you might want to address in here: the current code sends an RML message from the proc calling abort to its local daemon telling the daemon that we are exiting due to the app calling "abort". We needed to do this because we wanted to flag the proc termination as one induced by the app itself as opposed to something like a segfault or termination by signal.
>>
>> However, the problem is that the app may be calling abort from within an event handler. Hence, the RML send (which is currently blocking) will never complete once we no longer allow event lib recursion (coming soon). If we use a non-blocking send, then we can't know for sure that the message has been sent before we terminate.
>>
>> What we need is a non-messaging way of communicating that this was an ordered abort as opposed to a segfault or other failure. Prior to the current method, we had the app drop a file that the daemon looked for as an "abort marker", but that was ugly as it sometimes caused us to not properly cleanup the session directory tree.
>>
>> I'm open to suggestion - perhaps it isn't actually all that critical for us to distinguish "aborted by call to abort" from "aborted by signal", and we can just have the app commit suicide via self-imposed SIGKILL? It is only the message output to the user at the end of the job that differs - and since MPI_Abort already provides a message indicating "we called abort", is it really necessary that we have orte aware of that distinction?
>>
>>
>> On Jun 9, 2011, at 6:12 PM, Joshua Hursey wrote:
>>
>>>
>>> On Jun 9, 2011, at 6:47 PM, George Bosilca wrote:
>>>
>>>> Well, you're way to trusty. ;)
>>>
>>> It's the midwestern boy in me :)
>>>
>>>>
>>>> This only works if all component play the game, and even then there it is difficult if you want to allow components to deregister themselves in the middle of the execution. The problem is that a callback will be previous for some component, and that when you want to remove a callback you have to inform the "next" component on the callback chain to change its previous.
>>>
>>> This is a fair point. I think hiding the ordering of callbacks in the errmgr could be dangerous since it takes control from the upper layers, but, conversely, trusting the upper layers to 'do the right thing' with the previous callback is probably too optimistic, esp. for layers that are not designed together.
>>>
>>> To that I would suggest that you leave the code as is - registering a callback overwrites the existing callback. That will allow me to replace the default OMPI callback when I am able to in MPI_Init, and, if I need to, swap back in the default version at MPI_Finalize.
>>>
>>> Does that sound like a reasonable way forward on this design point?
>>>
>>> -- Josh
>>>
>>>>
>>>> george.
>>>>
>>>> On Jun 9, 2011, at 13:21 , Josh Hursey wrote:
>>>>
>>>>> So the "Resilient ORTE" patch has a registration in ompi_mpi_init.c:
>>>>> -------------
>>>>> orte_errmgr.set_fault_callback(&ompi_errhandler_runtime_callback);
>>>>> -------------
>>>>>
>>>>> Which is a callback that just calls abort (which is what we want to do
>>>>> by default):
>>>>> -------------
>>>>> void ompi_errhandler_runtime_callback(orte_process_name_t *proc) {
>>>>> ompi_mpi_abort(MPI_COMM_WORLD, 1, false);
>>>>> }
>>>>> -------------
>>>>>
>>>>> This is what I want to replace. I do -not- want ompi to abort just
>>>>> because a process failed. So I need a way to replace or remove this
>>>>> callback, and put in my own callback that 'does the right thing'.
>>>>>
>>>>> The current patch allows me to overwrite the callback when I call:
>>>>> -------------
>>>>> orte_errmgr.set_fault_callback(&my_callback);
>>>>> -------------
>>>>> Which is fine with me.
>>>>>
>>>>> At the point I do not want my_callback to be active any more (say in
>>>>> MPI_Finalize) I would like to replace it with the old callback. To do
>>>>> so, with the patch's interface, I would have to know what the previous
>>>>> callback was and do:
>>>>> -------------
>>>>> orte_errmgr.set_fault_callback(&ompi_errhandler_runtime_callback);
>>>>> -------------
>>>>>
>>>>> This comes at a slight maintenance burden since now there will be two
>>>>> places in the code that must explicitly reference
>>>>> 'ompi_errhandler_runtime_callback' - if it ever changed then both
>>>>> sites would have to be updated.
>>>>>
>>>>>
>>>>> If you use the 'sigaction-like' interface then upon registration I
>>>>> would get the previous handler back (which would point to
>>>>> 'ompi_errhandler_runtime_callback), and I can store it for later:
>>>>> -------------
>>>>> orte_errmgr.set_fault_callback(&my_callback, prev_callback);
>>>>> -------------
>>>>>
>>>>> And when it comes time to deregister my callback all I need to do is
>>>>> replace it with the previous callback - which I have a reference to,
>>>>> but do not need the explicit name of (passing NULL as the second
>>>>> argument tells the registration function that I don't care about the
>>>>> current callback):
>>>>> -------------
>>>>> orte_errmgr.set_fault_callback(&prev_callback, NULL);
>>>>> -------------
>>>>>
>>>>>
>>>>> So the API in the patch is fine, and I can work with it. I just
>>>>> suggested that it might be slightly better to return the previous
>>>>> callback (as is done in other standard interfaces - e.g., sigaction)
>>>>> in case we wanted to do something with it later.
>>>>>
>>>>>
>>>>> What seems to be proposed now is making the errmgr keep a list of all
>>>>> registered callbacks and call them in some order. This seems odd, and
>>>>> definitely more complex. Maybe it was just not well explained.
>>>>>
>>>>> Maybe that is just the "computer scientist" in me :)
>>>>>
>>>>> -- Josh
>>>>>
>>>>>
>>>>> On Thu, Jun 9, 2011 at 1:05 PM, Ralph Castain <rhc_at_[hidden]> wrote:
>>>>>> You mean you want the abort API to point somewhere else, without using a new
>>>>>> component?
>>>>>> Perhaps a telecon would help resolve this quicker? I'm available tomorrow or
>>>>>> anytime next week, if that helps.
>>>>>>
>>>>>> On Thu, Jun 9, 2011 at 11:02 AM, Josh Hursey <jjhursey_at_[hidden]> wrote:
>>>>>>>
>>>>>>> As long as there is the ability to remove and replace a callback I'm
>>>>>>> fine. I personally think that forcing the errmgr to track ordering of
>>>>>>> callback registration makes it a more complex solution, but as long as
>>>>>>> it works.
>>>>>>>
>>>>>>> In particular I need to replace the default 'abort' errmgr call in
>>>>>>> OMPI with something else. If both are called, then this does not help
>>>>>>> me at all - since the abort behavior will be activated either before
>>>>>>> or after my callback. So can you explain how I would do that with the
>>>>>>> current or the proposed interface?
>>>>>>>
>>>>>>> -- Josh
>>>>>>>
>>>>>>> On Thu, Jun 9, 2011 at 12:54 PM, Ralph Castain <rhc_at_[hidden]> wrote:
>>>>>>>> I agree - let's not get overly complex unless we can clearly articulate
>>>>>>>> a
>>>>>>>> requirement to do so.
>>>>>>>>
>>>>>>>> On Thu, Jun 9, 2011 at 10:45 AM, George Bosilca <bosilca_at_[hidden]>
>>>>>>>> wrote:
>>>>>>>>>
>>>>>>>>> This will require exactly opposite registration and de-registration
>>>>>>>>> order,
>>>>>>>>> or no de-registration at all (aka no way to unload a component). Or
>>>>>>>>> some
>>>>>>>>> even more complex code to deal with internally.
>>>>>>>>>
>>>>>>>>> If the error manager handle the callbacks it can use the registration
>>>>>>>>> ordering (which will be what the the approach can do), and can enforce
>>>>>>>>> that
>>>>>>>>> all callbacks will be called. I would rather prefer this approach.
>>>>>>>>>
>>>>>>>>> george.
>>>>>>>>>
>>>>>>>>> On Jun 9, 2011, at 08:36 , Josh Hursey wrote:
>>>>>>>>>
>>>>>>>>>> I would prefer returning the previous callback instead of relying on
>>>>>>>>>> the errmgr to get the ordering right. Additionally, when I want to
>>>>>>>>>> unregister (or replace) a call back it is easy to do that with a
>>>>>>>>>> single interface, than introducing a new one to remove a particular
>>>>>>>>>> callback.
>>>>>>>>>> Register:
>>>>>>>>>> ompi_errmgr.set_fault_callback(my_callback, prev_callback);
>>>>>>>>>> Deregister:
>>>>>>>>>> ompi_errmgr.set_fault_callback(prev_callback, old_callback);
>>>>>>>>>> or to eliminate all callbacks (if you needed that for somme reason):
>>>>>>>>>> ompi_errmgr.set_fault_callback(NULL, old_callback);
>>>>>>>>>
>>>>>>>>>
>>>>>>>>> _______________________________________________
>>>>>>>>> devel mailing list
>>>>>>>>> devel_at_[hidden]
>>>>>>>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>>>>>>>
>>>>>>>>
>>>>>>>> _______________________________________________
>>>>>>>> devel mailing list
>>>>>>>> devel_at_[hidden]
>>>>>>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>> --
>>>>>>> Joshua Hursey
>>>>>>> Postdoctoral Research Associate
>>>>>>> Oak Ridge National Laboratory
>>>>>>> http://users.nccs.gov/~jjhursey
>>>>>>>
>>>>>>> _______________________________________________
>>>>>>> devel mailing list
>>>>>>> devel_at_[hidden]
>>>>>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>>>>>
>>>>>>
>>>>>> _______________________________________________
>>>>>> devel mailing list
>>>>>> devel_at_[hidden]
>>>>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>>>>>
>>>>>
>>>>>
>>>>>
>>>>> --
>>>>> Joshua Hursey
>>>>> Postdoctoral Research Associate
>>>>> Oak Ridge National Laboratory
>>>>> http://users.nccs.gov/~jjhursey
>>>>>
>>>>> _______________________________________________
>>>>> devel mailing list
>>>>> devel_at_[hidden]
>>>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>>>
>>>>
>>>> _______________________________________________
>>>> devel mailing list
>>>> devel_at_[hidden]
>>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>>>
>>>
>>>
>>> _______________________________________________
>>> devel mailing list
>>> devel_at_[hidden]
>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>
>>
>> _______________________________________________
>> devel mailing list
>> devel_at_[hidden]
>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>
>>
>
>
>
> --
> Joshua Hursey
> Postdoctoral Research Associate
> Oak Ridge National Laboratory
> http://users.nccs.gov/~jjhursey
>
> _______________________________________________
> devel mailing list
> devel_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/devel