[ofa-general] Re: [PATCH 4/5] infiniband-diags/libibnetdisc: Introduce a context object.
Hey Sasha, On Sun, 23 Aug 2009 15:06:09 +0300 Sasha Khapyorsky wrote: > Hi Ira, > > On 08:30 Mon 17 Aug , Ira Weiny wrote: > > > > The immediate benefit is coming with the multi-threaded implementation where > > I plan on adding the following function.[*] The discussion on the list has digressed from this patch. I still think this patch is valid and adds a level of flexibility which is needed regardless of what is decided about libibmad. Do you agree? Also, the last patch in the series ([PATCH 5/5] infiniband-diags/libibnetdisc: remove members of the fabric struct which are used in the scan only) cleans up some stuff from the external interface. If you really don't want to introduce a context object, then I can regenerate that final patch without the context. Ira > > Ok, but could we discuss first how will multithreading architecture be > implemented with libibnetdisc: goals (in particular is it support for > multithreaded apps or just multithreaded discovery function), interaction > with caller application, etc.? > > One of the desired feature of this I could think would be to keep API > simple for single threaded stuff. > > Sasha -- Ira Weiny Math Programmer/Computer Scientist Lawrence Livermore National Lab 925-423-8008 [email protected] ___ 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
[ofa-general] Re: [PATCH 4/5] infiniband-diags/libibnetdisc: Introduce a context object.
Hi Ira, On 08:30 Mon 17 Aug , Ira Weiny wrote: > > The immediate benefit is coming with the multi-threaded implementation where > I plan on adding the following function.[*] Ok, but could we discuss first how will multithreading architecture be implemented with libibnetdisc: goals (in particular is it support for multithreaded apps or just multithreaded discovery function), interaction with caller application, etc.? One of the desired feature of this I could think would be to keep API simple for single threaded stuff. 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
[ofa-general] Re: [PATCH 4/5] infiniband-diags/libibnetdisc: Introduce a context object.
On Sun, 16 Aug 2009 14:02:00 +0300 Sasha Khapyorsky wrote: > On 20:43 Thu 13 Aug , Ira Weiny wrote: > > > > From: Ira Weiny > > Date: Thu, 13 Aug 2009 20:16:01 -0700 > > Subject: [PATCH] infiniband-diags/libibnetdisc: Introduce a context object. > > > > This object must be created before query functions can be used and is > > used to control the functionality of the queries. > > Why is it needed? I see that it complicates API, but what is a benefits? The immediate benefit is coming with the multi-threaded implementation where I plan on adding the following function.[*] ibnd_set_num_threads(ibnd_ctx_t *ctx, int num); Set/get functions can be added for anything which we need to pass to discover without changing the discover (or other query) functionality and breaking the API. This also allows us to keep some state for the library private. For example, I might persist threads across calls to discover and only destroy them on a ibnd_destroy_ctx call. Ira [*] and the reason behind this function is that I feel the proper number of threads is going to be variable depending on the size and layout of the fabric being processed as well as the number of CPU's available on the node. > > Sasha -- Ira Weiny Math Programmer/Computer Scientist Lawrence Livermore National Lab 925-423-8008 [email protected] ___ 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
[ofa-general] Re: [PATCH 4/5] infiniband-diags/libibnetdisc: Introduce a context object.
On 20:43 Thu 13 Aug , Ira Weiny wrote: > > From: Ira Weiny > Date: Thu, 13 Aug 2009 20:16:01 -0700 > Subject: [PATCH] infiniband-diags/libibnetdisc: Introduce a context object. > > This object must be created before query functions can be used and is > used to control the functionality of the queries. Why is it needed? I see that it complicates API, but what is a benefits? 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
