Re: [Qemu-devel] [RFC PATCH 3/4] cpu_exec: Add sleeping algorithm

[Juan Quintela]

Sebastian Tanase <address@hidden> wrote:
> The goal is to sleep qemu whenever the guest clock
> is in advance compared to the host clock (we use
> the monotonic clocks). The amount of time to sleep
> is calculated in the execution loop in cpu_exec.
>
> Basically, using QEMU_CLOCK_REALTIME, we calculate
> the real time duration of the execution (meaning
> generating TBs and executing them) and using the
> the fields icount_decr.u16.low and icount_extra
> (from the CPUState structure) shifted by icount_time_shift
> we calculate the theoretical virtual time elapsed.
> Having these 2 values, we can determine if the
> guest is in advance and sleep.
>
> Signed-off-by: Sebastian Tanase <address@hidden>
> Tested-by: Camille Bégué <address@hidden>

...

> @@ -209,6 +210,26 @@ static void cpu_handle_debug_exception(CPUArchState *env)
>      }
>  }
>  
> +/* Allow the guest to have a max 300us advance.
> + * The difference between the 2 clocks could therefore
> + * oscillate around 0.
> + */
> +#define VM_CLOCK_ADVANCE 300000
> +
> +static int64_t diff_clk;

make this local to cpu_exec?


> +static void delay_host(void)
> +{


and

static int64_t delay_host(int64_t diff_clk)

> +    static struct timespec sleep_delay, rem_delay;
> +    sleep_delay.tv_sec = diff_clk / 1000000000LL;
> +    sleep_delay.tv_nsec = diff_clk % 1000000000LL;
> +    if (nanosleep(&sleep_delay, &rem_delay) < 0) {
> +        diff_clk -= (sleep_delay.tv_sec - rem_delay.tv_sec) * 1000000000LL;
> +        diff_clk -= sleep_delay.tv_nsec - rem_delay.tv_nsec;
> +    } else {
> +        diff_clk = 0;
> +    }
> +}
> +

> @@ -600,6 +633,11 @@ int cpu_exec(CPUArchState *env)
>                      }
>                  }
>                  if (unlikely(cpu->exit_request)) {
> +                    if (icount_align_option) {
> +                        if (diff_clk > VM_CLOCK_ADVANCE) {
> +                            delay_host();
> +                        }
> +                    }
>                      cpu->exit_request = 0;
>                      cpu->exception_index = EXCP_INTERRUPT;
>                      cpu_loop_exit(cpu);


I would move the if (diff_clk > VM_CLOCK_ADVANCE) test inside
delay_host(), but that is just personal style and taste.

Later, Juan.