Re: spindown [was Re: 2.4.6-pre2, pre3 VM Behavior]

[Daniel Phillips]

On Saturday 16 June 2001 23:54, Rik van Riel wrote:
> On Sat, 16 Jun 2001, Daniel Phillips wrote:
> > > Does the patch below do anything good for your laptop? ;)
> >
> > I'll wait for the next one ;-)
>
> OK, here's one which isn't reversed and should work ;))
>
> --- fs/buffer.c.orig	Sat Jun 16 18:05:29 2001
> +++ fs/buffer.c	Sat Jun 16 18:05:15 2001
> @@ -2550,7 +2550,8 @@
>  			   if the current bh is not yet timed out,
>  			   then also all the following bhs
>  			   will be too young. */
> -			if (time_before(jiffies, bh->b_flushtime))
> +			if (++flushed > bdf_prm.b_un.ndirty &&
> +					time_before(jiffies, bh->b_flushtime))
>  				goto out_unlock;
>  		} else {
>  			if (++flushed > bdf_prm.b_un.ndirty)

No, it doesn't, because some way of knowing the disk load is required and 
there's nothing like that here.

There are two components to what I was talking about:

  1) Early flush when load is light
  2) Preemptive cleaning when load is light

Both are supposed to be triggered by other disk activity, swapout or file 
writes, and are supposed to be triggered when the disk activity eases up.

--
Daniel