[PATCH 10/12] smp: Optimize Simple SMP scheduler

Chris Johns chrisj at rtems.org
Wed Aug 14 19:51:37 UTC 2013


Gedare Bloom wrote:
> On Wed, Aug 14, 2013 at 2:52 PM, Chris Johns<chrisj at rtems.org>  wrote:
>> Gedare Bloom wrote:
>>> On Tue, Aug 13, 2013 at 9:42 AM, Sebastian Huber
>>> <sebastian.huber at embedded-brains.de>   wrote:
>>>>
>>>>      /**
>>>> +   * @brief This field is true if the thread is in the air.
>>>> +   *
>>>> +   * A thread is in the air if it is in a transient state.  The extract
>>>> +   * operation on a scheduled thread will produce threads in the air.
>>>> Such
>>>> +   * threads are no longer on the scheduled chain, but are still
>>>> allocated to a
>>>> +   * processor.  The next enqueue or schedule operation will decide what
>>>> to do.
>>>> +   */
>>>> +  bool                                  is_in_the_air;
>>>> +
>>> At first I did not like this term "in the air" but I cannot think of a
>>> better term right now.
>>>
>> What about 'is_bound_and_transient' ?
>>
> the term we use now is "allocated" for a thread that has been assigned
> to a specific core for execution. So it would be
> "is_allocated_and_transient" to be precise, or change the "allocated"
> to "bound" to mean a thread on a core...
>

Allocated is a rather overloaded term.

Chris



More information about the devel mailing list