Messages in this thread | | | Date | Tue, 17 Aug 1999 19:48:32 -0400 | From | Wakko Warner <> | Subject | Re: hdd & sound |
| |
> Lets make some definitions. > > pitch problem (sounds analogue) > - (Wakkos) the sound changes pitch when hard disk is > accessed.
Not read, just write...
> hack problem (sounds digital) > - the sound drops out for short intervals since the sound > generating program do not get. Digital effect. > - time from waking of a higher priority process > to it gets CPU to keep the output buffer filled. > This can be somewhat avoided by sound application > writers by using ridiculous huge output buffers. > [ongoing work in this area is described on > http://www.gardena.net/benno/linux/audio/ > Ingo Molnar is involved. > Latest version (N6+) < 5 ms ... > ] > - enough IO to keep the input buffer filled. > [you would probably need something like the > described in thread "Prioritized IO", but you > need to fix the CPU problem first... ] > > stuck problem (sounds digital) > - (mine when trying to reproduce the pitch problem) after > several repeated runs of a process that stress disk write > the sound gets stuck in some strange output. > [Working with Alan to find this] > > So, where does your fit?
-- Lab tests show that use of micro$oft causes cancer in lab animals
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |