Re: [PATCH] vhand-2.1.63

Joe Fouche (jf@ugcs.caltech.edu)
Sat, 15 Nov 1997 12:17:32 -0800

You wrote
>
> The vhand patch degraded performance on my system:
> 486DX2, 8MB memory, 250MB on my only mounted partition (/).
>
> It caused gravitywars to run noticably slower. My guess is
> some problem with the self-tuning: I'll try to look into it
> soon.

It looks to me like the code in kswapd to wake vhand up is being called too
often. After commenting out the following in vmscan.c (swap_tick):

/*
if (jiffies > next_scan_jiffies) {
if (!vhand_awake) {
wake_up(&vhand_wait);
need_resched = 1;
}
}
*/

vhand no longer uses an appreciable amount of CPU. Performance still seems
improved. Comments?

-- 
    _ ____  Joe Fouche (jf@ugcs.caltech.edu)  
 ___| |---       Deranged College Student