From owner-freebsd-alpha Wed Jun 20 9:29:27 2001 Delivered-To: freebsd-alpha@freebsd.org Received: from technokratis.com (modemcable052.174-202-24.mtl.mc.videotron.ca [24.202.174.52]) by hub.freebsd.org (Postfix) with ESMTP id 6302937B409 for ; Wed, 20 Jun 2001 09:29:24 -0700 (PDT) (envelope-from bmilekic@technokratis.com) Received: (from bmilekic@localhost) by technokratis.com (8.11.3/8.11.3) id f5KGUTg34577; Wed, 20 Jun 2001 12:30:29 -0400 (EDT) (envelope-from bmilekic) Date: Wed, 20 Jun 2001 12:30:29 -0400 From: Bosko Milekic To: Terry Lambert Cc: Terry Lambert , freebsd-alpha@FreeBSD.ORG Subject: Re: vx, lge, nge, dc, rl, sf, sis, sk, vr, wb users please TEST Message-ID: <20010620123029.A34452@technokratis.com> References: <20010619191602.A28591@technokratis.com> <200106200224.TAA24251@usr05.primenet.com> <20010619232624.A29829@technokratis.com> <3B304ADF.C5131399@mindspring.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5i In-Reply-To: <3B304ADF.C5131399@mindspring.com>; from tlambert2@mindspring.com on Wed, Jun 20, 2001 at 12:03:59AM -0700 Sender: owner-freebsd-alpha@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Wed, Jun 20, 2001 at 12:03:59AM -0700, Terry Lambert wrote: [...] > > > Are these changes really necessary for the Alpha to work? > > > > Absolutely. > > I wouldn't exactly say "absolutely", unless you are actually > measuring significant faulting as a result; I would say that > they are harmless. Oh, I think I wasn't too clear above. When I said "page fault" I meant "fatal page fault" (i.e. the address space isn't even mapped, it may even sit in another submap of kmem_map). It's not a problem right now because the mbuf allocator allocates "sequentially" from the base of mb_map. So let's say we have a cluster in a page X, where X > mb_map_base. Then, we're guaranteed that all Y, where X > Y > mb_map_base consists of already wired-down pages, so we're safe. Actually, now that I think about it, if we just so happen to hit the mbuf on the first page in mb_map and the space before that is not mapped, then we may see this too - but it's very unlikely. As I mentionned previously, instead of just having `mb_map' where clusters and mbufs are allocated from, in the new allocator I have a `mbuf_map' and a `clust_map.' So, when the data being bcopy()'d comes from the first cluster of clust_map, and the previous space is unmapped, the fault is a sure thing and we'll end up crashing. > I was just a bit nervous, since I had a long conversation > with Bill on this and other nasty topics (e.g. I want to Yeah, hehe. As you mentionned above, Bill *is* the "network driver God." :-) > add a new function to the list of externally accessible > functions exported by all ethernet drivers; more on that > later, after the code is happy). Cool. > -- Terry Later, -- Bosko Milekic bmilekic@technokratis.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-alpha" in the body of the message