Messages in this thread | | | Date | Sun, 12 Jul 1998 08:48:37 +0200 | From | Andi Kleen <> | Subject | Re: Strange interrupt behaviour |
| |
On Sun, Jul 12, 1998 at 07:35:25AM +0200, Linus Torvalds wrote: > So the sligtly uglier version of this is to do all page allocations as 8kB > chunks, and then the memory management layer has its own "sub-buddy" to > split a 8kB page into two hardware pages. The sparc already does something > like this for some of its page table pages, which are partial pages rather > than a full page like on a normal architecture. It wouldn't be too painful > to do this generically.
The disadvantage of that is that all the kernel parts using __get_fee_page() [especially select() comes to mind which uses 2 pages per waiting process] would waste an awful lot of memory.
> However, I'd prefer to still try out some other ways of handling this. For > example, "__get_free_pages()" currently only re-tries once. It shouldn't > be hard to make it re-try a few more times, and it might well be enough to > make the problem go away.
Or it might not. This is just "randomly throwing pages away, maybe we have luck". Does not look like a good reliable strategy.
> 2.1.x is not going to be usable on 4MB machines. I didn't even have to > change the kernel for that - the distributions have made that abundantly > clear anyway. It may be that we will simply say that "hey, if you have a > 486-8MB, then 2.0.x works better, and the new features of 2.1.x aren't > worth it for you".
This is correct (I said 8MB :), but I would be worried if it was not usable on a 16MB machine.
> > One of the reasons I disliked Minix back when I used it was that it was > designed for a machine that was no longer current. I want new versions of > Linux to be optimized for new hardware, and I also think that it should be > acceptable to But that's no excuse to waste memory except for very good reasons. The 5% rule applies (5% here, 5% there, the result is something as bloated as Solaris or NT)
-Andi
- 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.altern.org/andrebalsa/doc/lkml-faq.html
| |