>new implementation gets rid of the per-task timer and per-task timeout
>value. This effectively puts both of them onto the stack and thus probably
>improves performance even in the timeout case. And for the common
For some reason I am not sure if removing the timeout from the stack is
been a good idea.
My kernel is just running without tsk->timeout and using
schedule_timeout() though. I can' t produce a patch right now because I
need to clean tons of garbage and to do that I have to review all the
patch (if you want the patch with the garbage ask and I' ll sent to you).
If I boot with jiffies = 0 everything seems OK. If I boot with jiffies =
-120*HZ and timer_jiffies = -120*HZ the timer code became messy (before
and after the jiffies wrap). I don' t understand at all yet the details of
the timer code, but it seems that I can' t choose a random jiffies value
to start (I am complelty wrong on this?).
Andrea Arcangeli
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/