> --- linux/mm/vmscan.c:1.1.1.3 Sat Oct 24 15:42:52 1998
> +++ linux/mm/vmscan.c Sat Oct 24 19:55:47 1998
> /* Give kswapd a realtime priority. */
> - current->policy = SCHED_FIFO;
> current->rt_priority = 32; /* Fixme --- we need to standardise our
This effectively removes realtime priority from kswapd
-- this is plain wrong because we need to rely on kswapd
even in triple-digit loads...
> /*
> + * Stop carefully if we could eat all CPU power. -arca
> + */
> + if (!do_try_to_free_page(0))
> + break;
I wouldn't call this 'carefully' at all. The reason
we do multiple tries in kswapd is because we _can't_
give up on the first failure. The rest of the system
relies on us!
The danger in this patch might be masqueraded somewhat
by all the added wake_up(&kswapd) calls, but it really
isn't a sane thing to do...
It would be better to have kswapd figure out if it is
failing because it is OOM (--> give up and kill something)
or because all pages are aged high (--> continue because
we will be able to find something).
You've seen my patch, you know that is trivial. There's
not much of a reason to put this dangerous piece of code
into the kernel...
Rik.
+-------------------------------------------------------------------+
| Linux memory management tour guide. H.H.vanRiel@phys.uu.nl |
| Scouting Vries cubscout leader. http://www.phys.uu.nl/~riel/ |
+-------------------------------------------------------------------+
-
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/