Subject: [linux-audio-dev] Re: bad latency benchmark results with SMP kernel
From: Maarten de Boer (maarten.deboer_AT_iua.upf.es)
Date: ke syys 15 1999 - 11:49:11 EDT
On Wed, 15 Sep 1999, pbd_AT_op.net wrote:
> I would like to point out that the latency issues are not anywhere
> near as much of a problem on an MP system. I can get hardware-level
> latency (limited by the DMA transfer size - typically about 0.2ms) on
> my system, by just binding to the processor and blocking interrupts
> from that processor (oh, and using mmap(2)).
Yeah, I used that method before to. Without mmap but with nonblocking
read/write. But now I am using both processors at hi load, because I
have to do a lot of calculation in between the sound read and sound
write. So in that case, your method doesn't work.
> Even so, I will make an effort to move up to 2.2.10(N6) over the next
> week or so, and see what I find out.
Great! Please let me know what you experience.
Maarten
This archive was generated by hypermail 2b28 : pe maalis 10 2000 - 07:27:12 EST