[ofa-general] Re: [RFC] OpenSM and IPv6 Scalability Proposal

Hal Rosenstock hal.rosenstock at gmail.com
Sat May 9 05:26:05 PDT 2009


On Sat, May 9, 2009 at 7:31 AM, Eli Dorfman <dorfman.eli at gmail.com> wrote:
> On Sat, May 9, 2009 at 1:41 PM, Hal Rosenstock <hal.rosenstock at gmail.com> wrote:
>> On Sat, May 9, 2009 at 6:32 AM, Eli Dorfman <dorfman.eli at gmail.com> wrote:
>>> On Fri, May 8, 2009 at 4:57 PM, Hal Rosenstock <hal.rosenstock at gmail.com> wrote:
>>>> On Wed, May 6, 2009 at 6:24 AM, Slava Strebkov <slavas at voltaire.com> wrote:
>>>>>
>>>>> In addition to the original proposal we suggest allocating special MLID
>>>>> for the following MGIDs:
>>>>>  1. FF12401bxxxx000000000000FFFFFFFF - All Nodes
>>>>>  2. FF12401bxxxx00000000000000000001 - All hosts
>>>>>  3. FF12401bffff0000000000000000004d  - all Gateways
>>>>>  4. FF12401bxxxx00000000000000000002 - all routers
>>>>>  5. FF12601bABCD000000000001ffxxxxxx - IPv6 SNM
>>>>
>>>> It turns out that collapsing multicast groups across PKeys on a single
>>>> MLID may not be such a good idea unless partition enforcement
>>>> enforcement by switches is disabled. There should be different modes
>>>> of collapsing based on this based on whether this is enabled or not.
>>>
>>> The idea is to allocate a different MLID per each of the above special MGIDs.
>>
>> So one MLID per PKey in the MGID ?
> yes
>
>> What's the difference between xxxx's and ABCD in the syntax above ?
> none. should be the same.

Doesn't the xxxxxx for IPv6 mean mask these nibbles though ?

>
>> IPv6 is being collapsed per PKey too, right ?
> yes
>
>>>>> For all other cases we suggest that same MLID will be assigned to
>>>>> different MGIDs if:
>>>>>  1. They share the same P Key
>>>>>  2. Same signature - for IPoIB only
>>>>>  3. Same LSB bits - bitmask configurable by user (default  10 bits)
>>>>>        for example, the following are the same:
>>>>>        MGID1:  FF12401bABCD000000000000xxxxx755
>>>>>        MGID2:  FF12401bABCD000000000000yyyyyB55
>>>>
>>>> Jason's approach to this was in a thread entitled "IPv6 and IPoIB
>>>> scalability issue":
>>>> http://lists.openfabrics.org/pipermail/general/2006-November/029621.html
>>>> in which he proposed an MGID range (MGID/prefix syntax) for collapsing
>>>> IPv6 SNM groups. Additionally, there was the potential to distribute
>>>> the matched groups across some number of MLIDs. See also thread "[RFC]
>>>> OpenSM and IPv6 Scalability Proposal":
>>>> http://lists.openfabrics.org/pipermail/general/2008-June/051226.html
>>>>
>>>>>  Implementation.
>>>>>  Since there will be many mgroups shared same mlid, mlid-array entry
>>>>> will contain
>>>>>  fleximap holding mgroups.
>>>>>  Searching of mgroup will be performed by mlid (index in the array) and
>>>>> mgid -
>>>>>  key in the fleximap.
>>>>
>>>> Sasha proposed using an array rather than fleximap for this:
>>>> http://lists.openfabrics.org/pipermail/general/2008-June/051525.html
>>>>
>>>> -- Hal
>>>>
>>>>>
>>>>>
>>>>>  Slava Strebkov
>>>>> _______________________________________________
>>>>> general mailing list
>>>>> general at lists.openfabrics.org
>>>>> http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
>>>>>
>>>>> To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
>>>>>
>>>> _______________________________________________
>>>> general mailing list
>>>> general at lists.openfabrics.org
>>>> http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
>>>>
>>>> To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
>>>>
>>>
>>
>



More information about the general mailing list