Re: buffers vs. pages vs. kernel speed
Dr. Werner Fink (werner@suse.de)
Fri, 13 Jun 1997 10:34:47 +0200
> > Let's try this one... this has:
> >
> > 1) buffer cache clean buffer out of memory fixes
> > 2) handle multi-page allocations in low memory situations
> > (sans GFP_ATOMIC) more gracefully
> > 3) Matthias's state machine fix
> > 4) Debugging code added to try_to_free_page() for when it fails
>
> With that patch on pre-patch-2.0.31-2 this kind of command:
>
> gunzip -c largefile.gz | egrep 'regexp'
>
> made the system rather unresponsive. Without the patch the command does
> not affect the responsiveness.
>
> I have a 66 MHz 486, 16 megs of ram. The 'largefile' was on a local ide
> disk and the size of the (compressed) file was 17 megs. Nothing
> mentionable running at the same time.
>
Maybe you should follow the entire discussion :-) ... the buffer cache clean
fixes does only work if switch on. This one line change is simple missed.
Apply the following patch
------------------------------------------------------------------------
--- linux-2.0.31-clean/mm/page_alloc.c Sat Aug 17 20:19:29 1996
+++ linux/mm/page_alloc.c Thu Jun 12 20:15:31 1997
@@ -214,7 +214,7 @@
return 0;
}
restore_flags(flags);
- if (priority != GFP_BUFFER && try_to_free_page(priority, dma, 1))
+ if (try_to_free_page(priority, dma, 1))
goto repeat;
return 0;
}