On Sun, 2007-06-17 at 14:11 +0300, Yevgeny Kliteynik wrote: > Yevgeny Kliteynik wrote: > > Sasha Khapyorsky wrote: > >> On 16:57 Fri 15 Jun , Hal Rosenstock wrote: > >>> On Fri, 2007-06-15 at 16:59, Sasha Khapyorsky wrote: > >>>> On 16:39 Fri 15 Jun , Hal Rosenstock wrote: > >>>>> On Thu, 2007-06-14 at 09:45, Sasha Khapyorsky wrote: > >>>>>> On 15:36 Thu 14 Jun , Yevgeny Kliteynik wrote: > >>>>>>> Sasha Khapyorsky wrote: > >>>>>>>> Hi Yevgeny, > >>>>>>>> On 11:19 Thu 14 Jun , Yevgeny Kliteynik wrote: > >>>>>>>>> The following three patches are adding root and compute node > >>>>>>>>> guid files > >>>>>>>>> options for fat-tree routing, > >>>>>>>> Is there any reason to not share root guids file option with > >>>>>>>> up/down? > >>>>>>> There are two new options for fat-tree: roots and compute nodes > >>>>>>> (CN). > >>>>>>> These two will be very "tightly coupled" and would have more > >>>>>>> implication > >>>>>>> on the routing than in case of up/dn roots. For instance, having > >>>>>>> root > >>>>>>> file but not CN file means that the topology doesn't have to be > >>>>>>> pure fat-tree, > >>>>>>> but all the CAs are considered CNs and have to be on the same > >>>>>>> level of the tree. > >>>>>>> And there is similar implication of all the combinations of > >>>>>>> these two options. > >>>>>>> > >>>>>>> Because of this coupling I wanted to differentiate these two > >>>>>>> options from > >>>>>>> the up/dn roots. > >>>>>>> > >>>>>>> Thoughts? > >>>>>> I still not have strong option about two options against common one. > >>>>> Me neither. > >>>>> > >>>>>> Hypothetically if in some days we will implement routing engine > >>>>>> chains > >>>>>> (so failed algo will fallback to next in chain and not just to > >>>>>> default) > >>>>>> separate options could be useful. > >>>>> So is this a(nother) reason to keep the roots separate or would > >>>>> that be > >>>>> dealt with when the routing fallback strategy changes ? > >>>> It is yet hypothetical. Currently I don't see a strong practical > >>>> reasons > >>>> to have two separate root guids file options for up/down and fat-tree, > >>>> but guess this is minor and not showstopper. > >>> Wouldn't a current practical reason be switching between up/down and fat > >>> tree and they each have different roots ? Is that a real scenario ? > >> > >> Sure (but guess in many cases selected roots will be same for both > >> algos). > > > > I think that selected roots will always be same for both algos. > > I can't think of any topology that will require different set of roots > > for two algorithms that see the fabric as tree with routes going up and > > then down. > > > >> I think this scenario will be handled well with single shared > >> option, like: > >> > >> opensm -R ftree --roots-file ftree-roots-file > >> > >> , and > >> > >> opensm -R updn --roots-file updn-roots-file > > > > I agree with this. > > I will rework the patch and replace the updn_guid_file with root_guid_file, > > and add cn_guid_file. > > > > This also means that the OSM command line options -a or --add_guid_file > > will be replaced with -O or --root_guid_file, and we will have additional > > options for CN file: -C or --cn_guid_file > > Sorry, -C is already taken. I'm running out of letters here... :) > Suggesting leaving 'a' for roots, and using 'u' for CNs: > > -a or --root_guid_file > -u or --cn_guid_file
Looks perfect for me. Sasha _______________________________________________ general mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
