From owner-freebsd-hackers Thu Jan 7 19:02:13 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id TAA18700 for freebsd-hackers-outgoing; Thu, 7 Jan 1999 19:02:13 -0800 (PST) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from apollo.backplane.com (apollo.backplane.com [209.157.86.2]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id TAA18693 for ; Thu, 7 Jan 1999 19:02:11 -0800 (PST) (envelope-from dillon@apollo.backplane.com) Received: (from dillon@localhost) by apollo.backplane.com (8.9.1/8.9.1) id TAA36778; Thu, 7 Jan 1999 19:01:25 -0800 (PST) (envelope-from dillon) Date: Thu, 7 Jan 1999 19:01:25 -0800 (PST) From: Matthew Dillon Message-Id: <199901080301.TAA36778@apollo.backplane.com> To: Terry Lambert Cc: dyson@iquest.net, pfgiffun@bachue.usc.unal.edu.co, freebsd-hackers@FreeBSD.ORG Subject: Re: questions/problems with vm_fault() in Stable Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG :> :cylinder groups to "grow" the MFS. :> :> No it doesn't. Explain to me how it aggravates the fragmentation :> issue. Remember, we *don't* *care* how 'fragmented' the file data :> is in MFS's device namespace. We just care how fragmented it is on :> physical media - the swap backing store. The swapper automatically :> defragments anything over a page in size. : :Kernel VM space fragmentation. : :Try to load a quiccam driver KLD that need to malloccontig. What? That's your answer? That's a total bullshit answer and you know it. You are blaming the fragmentation of *physical* memory on subsystems that only use virtual mappings? Give me a break. MFS has nothing to do with physical memory fragmentation... that's a function of the fact that the VM page allocator doesn't give a damn about physical memory fragmentation. It has NOTHING whatsoever to do with MFS or any other VFS layer. Just doing a 'find /usr -type f | xargs md5' will fragment physical memory as badly as MFS might. If you need contiguous physical memory and can't preallocate it, then go and write a defragmenter that reassigns pages. It would not be too difficult - you just force the pager to cycle pages through the cache and organize the free queue to repack them. Right now the free queue's are a kind of LRUish design combined with the page-coloring code. This has NOTHING to do with MFS. Nada. Zilch. None. Zero. : Terry Lambert : terry@lambert.org :--- Matthew Dillon Engineering, HiWay Technologies, Inc. & BEST Internet Communications & God knows what else. (Please include original email in any response) To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message