Re: [PATCH] mm: stop kswapd's infinite loop at high orderallocation take2

[Mel Gorman]

On Thu, Jan 01, 2009 at 11:52:02PM +0900, KOSAKI Motohiro wrote:
> 
> > >                 /*
> > >                  * Fragmentation may mean that the system cannot be
> > >                  * rebalanced for high-order allocations in all zones.
> > >                  * At this point, if nr_reclaimed < SWAP_CLUSTER_MAX,
> > >                  * it means the zones have been fully scanned and are still
> > >                  * not balanced. For high-order allocations, there is 
> > >                  * little point trying all over again as kswapd may
> > >                  * infinite loop.
> > >                  *
> > >                  * Instead, recheck all watermarks at order-0 as they
> > >                  * are the most important. If watermarks are ok, kswapd will go
> > >                  * back to sleep. High-order users can still direct reclaim
> > >                  * if they wish.
> > >                  */
> > > 
> > > ?
> > 
> > Excellent. I strongly like this and I hope merge it to my patch.
> > I'll resend new patch.
> 
> Done.
> 

Looks good, thanks.

> 
> 
> ==
> From: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
> Subject: [PATCH] mm: kswapd stop infinite loop at high order allocation
> 
> Wassim Dagash reported following kswapd infinite loop problem.
> 
>   kswapd runs in some infinite loop trying to swap until order 10 of zone
>   highmem is OK.... kswapd will continue to try to balance order 10 of zone
>   highmem forever (or until someone release a very large chunk of highmem).
> 
> For non order-0 allocations, the system may never be balanced due to
> fragmentation but kswapd should not infinitely loop as a result. 
> 
> Instead, recheck all watermarks at order-0 as they are the most important. 
> If watermarks are ok, kswapd will go back to sleep. 
> 
> 
> Reported-by: wassim dagash <wassim.dagash@xxxxxxxxx>
> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
> Reviewed-by: Nick Piggin <npiggin@xxxxxxx>
> Signed-off-by: Mel Gorman <mel@xxxxxxxxx>,
> ---
>  mm/vmscan.c |   17 +++++++++++++++++
>  1 file changed, 17 insertions(+)
> 
> Index: b/mm/vmscan.c
> ===================================================================
> --- a/mm/vmscan.c	2008-12-25 08:26:37.000000000 +0900
> +++ b/mm/vmscan.c	2009-01-01 01:56:02.000000000 +0900
> @@ -1872,6 +1872,23 @@ out:
>  
>  		try_to_freeze();
>  
> +		/*
> +		 * Fragmentation may mean that the system cannot be
> +		 * rebalanced for high-order allocations in all zones.
> +		 * At this point, if nr_reclaimed < SWAP_CLUSTER_MAX,
> +		 * it means the zones have been fully scanned and are still
> +		 * not balanced. For high-order allocations, there is
> +		 * little point trying all over again as kswapd may
> +		 * infinite loop.
> +		 *
> +		 * Instead, recheck all watermarks at order-0 as they
> +		 * are the most important. If watermarks are ok, kswapd will go
> +		 * back to sleep. High-order users can still direct reclaim
> +		 * if they wish.
> +		 */
> +		if (nr_reclaimed < SWAP_CLUSTER_MAX)
> +			order = sc.order = 0;
> +
>  		goto loop_again;
>  	}
>  
> 
> 
> 

-- 
Mel Gorman
Part-time Phd Student                          Linux Technology Center
University of Limerick                         IBM Dublin Software Lab
--
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/