home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.unix.bsd
- Path: sparky!uunet!paladin.american.edu!howland.reston.ans.net!bogus.sura.net!pandora.pix.com!stripes
- From: stripes@pix.com (Josh Osborne)
- Subject: Re: Does 386BSD work on systems with 20 megabytes of memory! HELP!
- Message-ID: <C08LKB.w7@pix.com>
- Sender: news@pix.com (The News Subsystem)
- Nntp-Posting-Host: pandora.pix.com
- Organization: Pix Technologies -- The company with no adult supervision
- References: <1992Dec29.165705.28771@Informatik.TU-Muenchen.DE> <1992Dec30.084905.17453@convex.com> <1992Dec31.201347.12419@netcom.com>
- Distribution: comp.unix.bsd
- Date: Sat, 2 Jan 1993 17:21:46 GMT
- Lines: 17
-
- In article <1992Dec31.201347.12419@netcom.com> thinman@netcom.com (Technically Sweet) writes:
- >It should be feasible to hack the standard I/O library to get
- >always get disk buffers below the 16 meg mark. Maybe the
- >mmap() call can help here? [...]
-
- You can't fix this from the user level for 2 reasons. First, memory addresses
- seen at teh user level are VM addresses, the 16M boundry is a physical boundry.
- So if stdio attempts to do a write from 0x00f000 the memory could really be at
- 0xf0f000! Second, you don't even care what address the user wants I/O done
- to/from, you do it all to/from the buffer cache (or bounce buffers, if the
- 16M hack worked).
- --
- stripes@pix.com "Security for Unix is like
- Josh_Osborne@Real_World,The Multitasking for MS-DOS"
- "The dyslexic porgramer" - Kevin Lockwood
- We all agree on the necessity of compromise. We just can't agree on
- when it's necessary to compromise. - Larry Wall
-