On 27/11/2020 14:40, Chris Wilson wrote:
Quoting Matthew Auld (2020-11-27 12:07:13)
From: Tvrtko Ursulin
Current code uses jiffie time to do the accounting and then does:
diff = jiffies - start;
msec = diff * 1000 / HZ;
...
atomic_long_add(msec, &i915->time_swap_out_ms);
If we
Quoting Matthew Auld (2020-11-27 12:07:13)
> From: Tvrtko Ursulin
>
> Current code uses jiffie time to do the accounting and then does:
>
> diff = jiffies - start;
> msec = diff * 1000 / HZ;
> ...
> atomic_long_add(msec, &i915->time_swap_out_ms);
>
> If we assume jiffie can be as non-gr
From: Tvrtko Ursulin
Current code uses jiffie time to do the accounting and then does:
diff = jiffies - start;
msec = diff * 1000 / HZ;
...
atomic_long_add(msec, &i915->time_swap_out_ms);
If we assume jiffie can be as non-granular as 10ms and that the current
accounting records all evic
