Re: [PATCH] vmscan: make kswapd use a correct order

[Minchan Kim]

On Fri, Dec 10, 2010 at 7:13 AM, Andrew Morton
<akpm@xxxxxxxxxxxxxxxxxxxx> wrote:
> On Fri,  3 Dec 2010 01:00:49 +0900
> Minchan Kim <minchan.kim@xxxxxxxxx> wrote:
>
>> +static bool kswapd_try_to_sleep(pg_data_t *pgdat, int order)
>
> OT: kswapd_try_to_sleep() does a
> trace_mm_vmscan_kswapd_sleep(pgdat->node_id) if it sleeps for a long
> time, but doesn't trace anything at all if it does a short sleep.
> Where's the sense in that?
>

AFAIU, short sleep is _sleep_ but that trace's goal is to count only long sleep.
In addition, short sleep is a just ready to go or not long sleep so I
think we don't need short sleep trace.
And for knowing short sleep count, we can use
KSWAPD_{LOW|HIGH}_WMARK_HIT_QUICKLY.

-- 
Kind regards,
Minchan Kim
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/