> 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
>
Your patch is already in 2.1.119 and 2.1.122 unless the above is not
your complete patch. We tried with 2.1.122 and unfortunately, the
performance loss is still there...
I am downloading 2.1.120 to try it with Andrea's patch.
Claude
-- Claude Gamache, CAE Electronique Ltee, 8585 Cote-de-Liesse Saint-Laurent, Quebec, Canada H4T 1G6 Email: cgamache@cae.ca Tel.: (514) 341-2000 x3194- 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