On Thu, Oct 22, 2009 at 9:50 AM, Sasha Khapyorsky <[email protected]> wrote:
> On 08:56 Thu 22 Oct     , Hal Rosenstock wrote:
>> >
>> > Why do you need this?
>>
>> It is useful in some clusters where the default behavior is
>> insufficient
>
> I would suppose that by itself this may indicate some external issues
> like bad connectivity (cabling) or similar and some investigation would
> be helpful there (regardless to number of retries).
>
>> and control over the number of retries helps and there is
>> no vendor API support for this.
>>
>> > And why did you choose to use environment variable and not command
>> > line/config option? I think that it is less obvious.
>>
>> It was modeled after OSM_UMAD_MAX_PENDING.
>
> It was internal libvendor hack (which is also not 100% clean :))
> controlling ibumad implementation specific parameter. Unlike this a
> number of MAD retries (similar to MAD response timeout value) has more
> generic meaning.
>
>> It could be made a command
>> line/options file item. Is that your preference ?
>
> I think command line/config option is a way to do it.

Do you see a way to do this without changing the vendor API ? I was
trying to add this without doing that.

-- Hal

>
> Sasha
>
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to