[OMPI devel] Open MPI BTL TCP interface mapping
Hello devel, Can I get a review (not from Brian) for this patch: https://github.com/open-mpi/ompi/pull/7134 These PR’s fix common matching bugs that users utilizing the tcp btl encounter. It has been proven to fix issue https://github.com/open-mpi/ompi/issues/7115 – it’s also the first utilization of the Reachability framework, which can provide valuable reference material. Thanks, William Zhang P.S. I will start increasing the frequency of these reminders, since these PR’s are 2+ months old.
Re: [OMPI devel] Open MPI BTL TCP interface mapping
Hello George, Are you referring to OMPI_MCA_btl_tcp_links parameter? If so, the graph matching will have no issue matching the increased links (It will just increase the time it takes for each process to do so – refer to the graph in the PR (Total Time Spent in add_procs per Process). Theoretically, there is no difference in increasing the num links compared to not having any additional links – since this only increases the scale of the bipartite flow problem. If the matching logic is sound, this should still select the best interfaces. The tests I performed to gather the graph data for the first graph was simulated using the num links variable. Please let me know if I misunderstood something. Thanks, William Zhang From: George Bosilca Date: Thursday, January 9, 2020 at 12:02 PM To: Open MPI Developers Cc: "Zhang, William" Subject: Re: [OMPI devel] Open MPI BTL TCP interface mapping Will, The 7134 issue is complex in its interactions with the rest of the TCP BTL, and I could not find the time to look at it careful enough (or test it on AWS). But maybe you can address my main concern here. #7134 interfaces selection will have an impact on the traffic distribution among the different sockets by altering the interfaces selection on the links we have in the TCP BTL (that allows us to increase the bandwidth by multiplexing the streams between peers). I have the feeling they are not nicely collaborating to increase the total bandwidth, but that instead they will prevent each other from functioning efficiently. George. On Thu, Jan 9, 2020 at 2:36 PM Zhang, William via devel mailto:devel@lists.open-mpi.org>> wrote: Hello devel, Thanks George for reviewing: https://github.com/open-mpi/ompi/pull/7167 Can I get a review (not from Brian) for this patch as well: https://github.com/open-mpi/ompi/pull/7134 These PR’s fix common matching bugs that users utilizing the tcp btl encounter. It has been proven to fix issue https://github.com/open-mpi/ompi/issues/7115 – it’s also the first utilization of the Reachability framework, which can provide valuable reference material. Thanks, William Zhang P.S. I will start increasing the frequency of these reminders, since these PR’s are 2+ months old.
Re: [OMPI devel] Open MPI BTL TCP interface mapping
Will, The 7134 issue is complex in its interactions with the rest of the TCP BTL, and I could not find the time to look at it careful enough (or test it on AWS). But maybe you can address my main concern here. #7134 interfaces selection will have an impact on the traffic distribution among the different sockets by altering the interfaces selection on the links we have in the TCP BTL (that allows us to increase the bandwidth by multiplexing the streams between peers). I have the feeling they are not nicely collaborating to increase the total bandwidth, but that instead they will prevent each other from functioning efficiently. George. On Thu, Jan 9, 2020 at 2:36 PM Zhang, William via devel < devel@lists.open-mpi.org> wrote: > Hello devel, > > > > Thanks George for reviewing: https://github.com/open-mpi/ompi/pull/7167 > > > > Can I get a review (not from Brian) for this patch as well: > https://github.com/open-mpi/ompi/pull/7134 > > > > These PR’s fix common matching bugs that users utilizing the tcp btl > encounter. It has been proven to fix issue > https://github.com/open-mpi/ompi/issues/7115 – it’s also the first > utilization of the Reachability framework, which can provide valuable > reference material. > > > > Thanks, > > William Zhang > > > > P.S. > > I will start increasing the frequency of these reminders, since these PR’s > are 2+ months old. >
Re: [OMPI devel] Open MPI BTL TCP interface mapping
Hello devel, Thanks George for reviewing: https://github.com/open-mpi/ompi/pull/7167 Can I get a review (not from Brian) for this patch as well: https://github.com/open-mpi/ompi/pull/7134 These PR’s fix common matching bugs that users utilizing the tcp btl encounter. It has been proven to fix issue https://github.com/open-mpi/ompi/issues/7115 – it’s also the first utilization of the Reachability framework, which can provide valuable reference material. Thanks, William Zhang P.S. I will start increasing the frequency of these reminders, since these PR’s are 2+ months old.
[OMPI devel] Open MPI BTL TCP interface mapping
Hello devel, Can someone (not Brian – he’s already reviewed it and this is a big enough change that I’d like others in the community to provide feedback), review the two patches https://github.com/open-mpi/ompi/pull/7167 https://github.com/open-mpi/ompi/pull/7167 These PR’s fix common matching bugs that users utilizing the tcp btl encounter. It has been proven to fix issue https://github.com/open-mpi/ompi/issues/7115 – it’s also the first utilization of the Reachability framework, which can provide valuable reference material. Thanks, William Zhang P.S. I will start increasing the frequency of these reminders, since these PR’s are 2+ months old.
Re: [OMPI devel] Open MPI BTL TCP interface mapping review request
Oh sorry, https://github.com/open-mpi/ompi/pull/7167 https://github.com/open-mpi/ompi/pull/7134 Thanks for pointing it out 😊 From: "Heinz, Michael William" Date: Tuesday, December 17, 2019 at 11:19 AM To: Open MPI Developers Cc: "Zhang, William" Subject: RE: Open MPI BTL TCP interface mapping review request William, You seem to have posted the same pull request twice? From: devel On Behalf Of Zhang, William via devel Sent: Tuesday, December 17, 2019 2:16 PM To: devel@lists.open-mpi.org Cc: Zhang, William Subject: [OMPI devel] Open MPI BTL TCP interface mapping review request Hello devel, Can somebody review these two patches before they get lost in the mires of time? https://github.com/open-mpi/ompi/pull/7167 https://github.com/open-mpi/ompi/pull/7167 These PR’s fix some common issues with Open MPI TCP BTL Thanks, William Zhang
Re: [OMPI devel] Open MPI BTL TCP interface mapping review request
William, You seem to have posted the same pull request twice? From: devel On Behalf Of Zhang, William via devel Sent: Tuesday, December 17, 2019 2:16 PM To: devel@lists.open-mpi.org Cc: Zhang, William Subject: [OMPI devel] Open MPI BTL TCP interface mapping review request Hello devel, Can somebody review these two patches before they get lost in the mires of time? https://github.com/open-mpi/ompi/pull/7167 https://github.com/open-mpi/ompi/pull/7167 These PR’s fix some common issues with Open MPI TCP BTL Thanks, William Zhang
[OMPI devel] Open MPI BTL TCP interface mapping review request
Hello devel, Can somebody review these two patches before they get lost in the mires of time? https://github.com/open-mpi/ompi/pull/7167 https://github.com/open-mpi/ompi/pull/7167 These PR’s fix some common issues with Open MPI TCP BTL Thanks, William Zhang
[OMPI devel] Open MPI BTL TCP interface mapping
Hello devel, Can someone (not Brian – since he has already reviewed the patches internally), review the two patches https://github.com/open-mpi/ompi/pull/7167 https://github.com/open-mpi/ompi/pull/7167 These PR’s fix common matching bugs that users utilizing the tcp btl encounter. It has been proven to fix issue https://github.com/open-mpi/ompi/issues/7115 Thanks, William Zhang
