>
> BTW, Linux has very bad interactive performance when the load is high. IIRC,
> it was much better in the past. I also tested prog1 on a Solaris 2.6 box, and
> it was MUCH more responsive with a load above 100 than the Linux box with only
> one prog1 running.
>
You're right. IMO it's concerned with ram eaten to hard by buffer cache.
A limitation in fs/buffer.c, function grow_buffers() fixes
it perfectly for me (good interactive performance under _heavy_ load).
I'v send my patch to the list a long time ago,
but it never made it into the code.
Here is it once more (should work for kernels up to 2.1.121 too):
- --- linux-2.1.105/fs/buffer.c Wed Jun 10 17:30:40 1998
+++ linux-2.1.105/fs/buffer.c.orig Fri Jun 5 07:53:50 1998
@@ -1590,10 +1590,6 @@
struct buffer_head * insert_point;
int isize;
- - if ( nr_free_pages < freepages.min * 2 ||
- - ( buffermem >> PAGE_SHIFT) * 100 >
- - buffer_mem.max_percent * num_physpages) return 0;
- -
if ((size & 511) || (size > PAGE_SIZE)) {
printk("VFS: grow_buffers: size = %d\n",size);
return 0;
Benoit, look if it's o.k. for you and tell me about.
Heinz
--=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
Systemmanagement Entwicklungsbereich 2 Deutsche Telekom AG Entwicklungszentrum Darmstadt Heinz Mauelshagen Otto-Roehm-Strasse 71c Postfach 10 05 41 mge@ez-darmstadt.telekom.de 64205 Darmstadt Germany +49 6151 886-425 FAX-386 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
- 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/faq.html