home *** CD-ROM | disk | FTP | other *** search
- Path: nntp.teleport.com!sschaem
- From: sschaem@teleport.com (Stephan Schaem)
- Newsgroups: comp.sys.amiga.programmer
- Subject: Re: Amiga programmers in deep shit...
- Date: 13 Jan 1996 17:32:11 GMT
- Organization: Teleport - Portland's Public Access (503) 220-1016
- Distribution: world
- Message-ID: <4d8qar$79q@maureen.teleport.com>
- References: <john.hendrikx.4606@grafix.xs4all.nl>
- NNTP-Posting-Host: julie.teleport.com
- X-Newsreader: TIN [version 1.2 PL2]
-
- John Hendrikx (john.hendrikx@grafix.xs4all.nl) wrote:
- : In a message of 10 Jan 96 Stephan Schaem wrote to All:
-
- : SS> Get the system time in tick before the read() and after:
-
- : SS> Because its possible that the ~14% happen once every 60 frame. 14% of
- : SS> 60*262 = 2200 scanline...
-
- : Well, maybe it helps if I told you that my HD led was flashing at about 25 Hz
- : (maybe more, hard to tell :-)))
-
- In a way thats pretty bad, but not for this case :) I really expected a
- read() the return pomptly after a read that small, a bit like a cache
- prefill. maybe thats why on my A1000 reading with small buffer was as slow
- has a floppy :)
-
- : SS> From your test result I see it take 14% of the system time not 14% of
- : SS> a frame wich is very diferent for what you want to do.
-
- : Yes, but this isn't what was happening, the HD led definitely flashed really
- : rapidly, it reminded me of running interlaced (so that's where I got that 25 Hz
- : figure from).
-
- What can I say.. I never would have thought every single read() did a HW
- access to the HD.
-
- : >> As you can see above it ain't really necessary, if you can spare a bit of
- : >> CPU time. Even with 1K or 2K block reads every frame you still beat
- : >> floppies by a long way, and without any noticeable slow-downs.
-
- : SS> It will work if you are garantied 80% of the frame for 'rendering'.
-
- : It will also work if you do the disk reading at a lower pri, so it will take
- : whatever time is left to do the reading. You will have to use a seperate task
- : anyway to do good asynchronous reading IMO (or use packets, but I wouldn't
- : recommend going that low-level).
-
- I will defenetly try that...
-
- Stephan
-
-