home *** CD-ROM | disk | FTP | other *** search
-
- In article <2365.6671T6T1540@stud.uni-frankfurt.de> raftopou@stud.uni-frankfurt.de (Joerg Raftopoulos) writes:
- >
- > KCL> Mark Worden (mworden@public.compusult.nf.ca) writes:
- > >>
- > >> Mask: 0x7ffffffe
- >
- > KCL> This tells the file system where data cannot be transfer directly from t
- > KCL> driver directly. XXXe means data is word aligned and XXXc means it is
- > KCL> long word aligned. So if you set it to long, and your program give it a
- > KCL> word aligned address, the file system have to do an extra level of
- > KCL> copying, hence slowing it down. Take a lot at the difference of
- > KCL> your HD performance under long/word/byte aligned tests in DiskSpeed 4.1.
- >
- > may i quote from the original post?
- >
- > MW> Can anyone tell me what the proper mask, transfer rate, etc. should be on
- > MW> my A3000 with 100MB Quantum hard drive and a Zip drive? Both drives have
- > MW> been formatted with the Fast File System (I have Workbench v2.1).
- >
- > so we are talking about the amiga 3000 scsi dma hostadapter. an extreme
- > efficient design that has nothing in common with those crappy a1200/4000 pio
- > ide implementations. the correct values are shown in amiga 3000`s manual (us
- > edition) in chapter 6 (using a harddisk) on page 66 a screenshot labeled
- > "setting file system characteristics" says: mask = 0xfffffffc and
- > maxtransfer = 0xffffff
-
- Actually, the 3000 users manual has no such reference. You must be talking
- about the section in the 2.04 Workbench manuals, which pertains to all
- machines, not just the 3000 (BTW, it's section 6-87 in the 2.1 manual).
-
- You're correct about the value shown in the screen shot, it is a "c".
- However, the default value in HDToolBox has always been 0x7ffffffe, up to
- and including 3.1, AFAIK. That is just a couple of bytes shy of 2 Gigs,
- which is the limit of the filesystems addressing. Anything larger is
- invalid. The manual is obviously wrong, and anyway, I'd trust the
- programmers before the manual writer anyday.
-
- As a matter of interest, I once ran some DiskSpeed tests with both a "c"
- and an "e" mask. The differences were so small as to be within the
- variation in numbers between successive tests with no changes. However, as
- usual, your mileage may vary, I'll stick with the default, it works.
-
- --
- Cheers,
- ---
- + _ ____________ tm Dale Currie ____ ___ _ +
- | /.\ .. | __ \ / dalec@amitrix.com / __[___]__ T tm |
- | /___\ /\/\ | | |_) | X support@amitrix.com / (o.o) | |
- | / \/ ^^ \ | | | \ | / \ Edmonton AB Canada / `-^-' | |
- |/ - D E V E L O P M E N T - \ AmiTrix /___ Z O R R O I N K !|
- + --------------------- Technical Support ---------------- +
-