Hi Steven,
On Tue, 14 Feb 2017 14:28:48 -0500
"Steven Rostedt (VMware)" <rost...@goodmis.org> wrote:
> I was testing Daniel's changes with his test case, and tweaked it a
> little. Instead of having the runtime equal to the deadline, I
> increased the deadline ten fold.
>
> Daniel's test case had:
>
> attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms
> */ attr.sched_deadline = 2 * 1000 * 1000; /* 2 ms */
> attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */
>
> To make it more interesting, I changed it to:
>
> attr.sched_runtime = 2 * 1000 * 1000; /* 2
> ms */ attr.sched_deadline = 20 * 1000 * 1000; /* 20 ms
> */ attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */
>
>
> The results were rather surprising. The behavior that Daniel's patch
> was fixing came back. The task started using much more than .1% of the
> CPU. More like 20%.
>
> Looking into this I found that it was due to the dl_entity_overflow()
> constantly returning true. That's because it uses the relative period
> against relative runtime vs the absolute deadline against absolute
> runtime.
>
> runtime / (deadline - t) > dl_runtime / dl_period
I agree that there is an inconsistency here (again, using equations
from the "period=deadline" case with a relative deadline different from
period).
I am not sure about the correct fix (wouldn't
"runtime / (deadline - t) > dl_runtime / dl_deadline" allow the task to
use a fraction of CPU time equal to dl_runtime / dl_deadline?)
The current code is clearly wrong (as shown by Daniel), but I do not
understand how the current check can allow the task to consume more
than dl_runtime / dl_period... I need some more time to think about
this issue.
Luca
>
> There's even a comment mentioning this, and saying that when relative
> deadline equals relative period, that the equation is the same as
> using deadline instead of period. That comment is backwards! What we
> really want is:
>
> runtime / (deadline - t) > dl_runtime / dl_deadline
>
> We care about if the runtime can make its deadline, not its period.
> And then we can say "when the deadline equals the period, the
> equation is the same as using dl_period instead of dl_deadline".
>
> After correcting this, now when the task gets enqueued, it can
> throttle correctly, and Daniel's fix to the throttling of sleeping
> deadline tasks works even when the runtime and deadline are not the
> same.
>
> Signed-off-by: Steven Rostedt (VMware) <rost...@goodmis.org>
> ---
> Index: linux-trace.git/kernel/sched/deadline.c
> ===================================================================
> --- linux-trace.git.orig/kernel/sched/deadline.c
> +++ linux-trace.git/kernel/sched/deadline.c
> @@ -445,13 +445,13 @@ static void replenish_dl_entity(struct s
> *
> * This function returns true if:
> *
> - * runtime / (deadline - t) > dl_runtime / dl_period ,
> + * runtime / (deadline - t) > dl_runtime / dl_deadline ,
> *
> * IOW we can't recycle current parameters.
> *
> - * Notice that the bandwidth check is done against the period. For
> + * Notice that the bandwidth check is done against the deadline. For
> * task with deadline equal to period this is the same of using
> - * dl_deadline instead of dl_period in the equation above.
> + * dl_period instead of dl_deadline in the equation above.
> */
> static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
> struct sched_dl_entity *pi_se, u64 t)
> @@ -476,7 +476,7 @@ static bool dl_entity_overflow(struct sc
> * of anything below microseconds resolution is actually
> fiction
> * (but still we want to give the user that illusion >;).
> */
> - left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >>
> DL_SCALE);
> + left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >>
> DL_SCALE); right = ((dl_se->deadline - t) >> DL_SCALE) *
> (pi_se->dl_runtime >> DL_SCALE);
>
