Just returned from vacation...sorry for delayed response In the past, I have expressed three concerns about the RSL. I'll aggregate them here for those who haven't seen them before - and apologize in advance for the long note.
For those wanting it in short, the concerns (somewhat related) are: 1. What problem are we really trying to solve? 2. Who is going to maintain old RTE versions, and why? 3. Are we constraining ourselves from further improvements in startup performance? My bottom line recommendation: I have no philosophical issue with the RSL concept. However, I recommend holding off until the next version of ORTE is completed and then re-evaluating to see how valuable the RSL might be, as that next version will include memory footprint reduction and framework consolidation that may yield much of the RSL's value without the extra work. Long version: 1. What problem are we really trying to solve? If the RSL is intended to solve the Cray support problem (where the Cray OS really just wants to see OMPI, not ORTE), then it may have some value. The issue to date has revolved around the difficulty of maintaining the Cray port in the face of changes to ORTE - as new frameworks are added, special components for Cray also need to be created to provide a "do-nothing" capability. In addition, the Cray is memory constrained, and the ORTE library occupies considerable space while providing very little functionality. The degree of value provide by the RSL will therefore depend somewhat on the efficacy of the changes in development within ORTE. Those changes will, among other things, significantly consolidate and reduce the number of frameworks, and reduce the memory footprint. The expectation is that the result will require only a single CNOS component in one framework. It isn't clear, therefore, that the RSL will provide a significant value in that environment. If the RSL is intended to aid in ORTE development, as hinted at in the RFC, then I believe that is questionable. Developing ORTE in a tmp branch has proven reasonably effective as changes to the MPI layer are largely invisible to ORTE. Creating another layer to the system that would also have to be maintained seems like a non-productive way of addressing any problems in that area. If the RSL is intended as a means of "freezing" the MPI-RTE interface, then I believe we could better attain that objective by simply defining a set of requirements for the RTE. As I'll note below, freezing the interface at an API level could negatively impact other Open MPI objectives. 2. Who is going to maintain old RTE versions, and why? It isn't clear to me why anyone would want to do this - are we seriously proposing that we maintain support for the ORTE layer that shipped with Open MPI 1.0?? Can someone explain why we would want to do that? Given what I know of ORTE, it seems questionable that, for example, one could have RSL components for both the ORTE that shipped with Open MPI 1.0 and the ORTE that is currently in the trunk without writing a great deal of RSL code. Creating an RSL component for the ORTE intended for Open MPI 1.3 would seem like even greater work as the flow of control is very different (see below). I'm sure one could overcome this with considerable code in the respective RSL components - but I have difficulty understanding the value in doing all that coding. Can someone explain that, and can we identify the personnel (and/or their organization) that are willing to perform that function? 3. Are we constraining ourselves from further improvements in startup performance? This is my biggest area of concern. The RSL has been proposed as an API-level definition. However, the MPI-RTE interaction really is defined in terms of a flow-of-control - although each point of interaction is instantiated as an API, the fact is that what happens at that point is not independent of all prior interactions. As an example of my concern, consider what we are currently doing with ORTE. The latest change in requirements involves the need to significantly improve startup time, reduce memory footprint, and reduce ORTE complexity. What we are doing to meet that requirement is to review the delineation of responsibilities between the MPI and RTE layers. The current delineation evolved over time, with many of the decisions made at a very early point in the program. For example, we instituted RTE-level stage gates in the MPI layer because, at the time they were needed, the MPI developers didn't want to deal with them on their side (e.g., ensuring that failure of one proc wouldn't hang the system). Given today's level of maturity in the MPI layer, we are now planning on moving the stage gates to the MPI layer, implemented as an "all-to-all" - this will remove several thousand lines of code from ORTE and make it easier for the MPI layer to operate on non-ORTE environments. Similar efforts are underway to reduce ORTE involvement in the modex operation and other parts of the MPI application lifecycle. We are able to do these things because we are now moving towards a tight integration of ORTE and OMPI layers - i.e., ORTE can be simplified because we can take advantage of our knowledge of what is happening on the MPI side of the equation. In order to accomplish this, however, we need to change the points-of-contact between the MPI and RTE layers, and redefine what happens at those points. If we require via the RSL that we" those points and what happens at those points, then making these changes will either prove impossible or at least will require considerable RSL code. On the other hand, if we revise the RSL to support the new ORTE/OMPI functionality, then we will have to write considerable code to make old versions of ORTE work with the new system. Hence, my concern is that we not let RSL implementation prevent us from moving forward with ORTE. The current work is required to meet scaling demands, and hopefully will resolve much of the Cray issue. I see no value in creating RSL just to support old versions of ORTE, nor for supporting ORTE development. It would be nice if we could re-evaluate this after the next ORTE version becomes solidified to see how the cost/benefit analysis has changed, and whether the RSL remains a desirable option. Ralph On 8/16/07 7:47 PM, "Tim Prins" <tpr...@cs.indiana.edu> wrote: > WHAT: Solicitation of feedback on the possibility of adding a runtime > services layer to Open MPI to abstract out the runtime. > > WHY: To solidify the interface between OMPI and the runtime environment, > and to allow the use of different runtime systems, including different > versions of ORTE. > > WHERE: Addition of a new framework to OMPI, and changes to many of the > files in OMPI to funnel all runtime request through this framework. Few > changes should be required in OPAL and ORTE. > > WHEN: Development has started in tmp/rsl, but is still in its infancy. We hope > to have a working system in the next month. > > TIMEOUT: 8/29/07 > > ------ > Short version: > > I am working on creating an interface between OMPI and the runtime system. > This would make a RSL framework in OMPI which all runtime services would be > accessed from. Attached is a graphic depicting this. > > This change would be invasive to the OMPI layer. Few (if any) changes > will be required of the ORTE and OPAL layers. > > At this point I am soliciting feedback as to whether people are > supportive or not of this change both in general and for v1.3. > > > Long version: > > The current model used in Open MPI assumes that one runtime system is > the best for all environments. However, in many environments it may be > beneficial to have specialized runtime systems. With our current system this > is not easy to do. > > With this in mind, the idea of creating a 'runtime services layer' was > hatched. This would take the form of a framework within OMPI, through which > all runtime functionality would be accessed. This would allow new or > different runtime systems to be used with Open MPI. Additionally, with such a > system it would be possible to have multiple versions of open rte coexisting, > which may facilitate development and testing. Finally, this would solidify the > interface between OMPI and the runtime system, as well as provide > documentation and side effects of each interface function. > > However, such a change would be fairly invasive to the OMPI layer, and > needs a buy-in from everyone for it to be possible. > > Here is a summary of the changes required for the RSL (at least how it is > currently envisioned): > > 1. Add a framework to ompi for the rsl, and a component to support orte. > 2. Change ompi so that it uses the new interface. This involves: > a. Moving runtime specific code into the orte rsl component. > b. Changing the process names in ompi to an opaque object. > c. change all references to orte in ompi to be to the rsl. > 3. Change the configuration code so that open-rte is only linked where needed. > > Of course, all this would happen on a tmp branch. > > The design of the rsl is not solidified. I have been playing in a tmp branch > (located at https://svn.open-mpi.org/svn/ompi/tmp/rsl) which everyone is > welcome to look at and comment on, but be advised that things here are > subject to change (I don't think it even compiles right now). There are > some fairly large open questions on this, including: > > 1. How to handle mpirun (that is, when a user types 'mpirun', do they > always get ORTE, or do they sometimes get a system specific runtime). Most > likely mpirun will always use ORTE, and alternative launching programs would > be used for other runtimes. > 2. Whether there will be any performance implications. My guess is not, > but am not quite sure of this yet. > > Again, I am interested in people's comments on whether they think adding > such abstraction is good or not, and whether it is reasonable to do such a > thing for v1.3. > > Thanks, > > Tim Prins > _______________________________________________ > devel mailing list > de...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/devel
