Greetings: I've recently completed a series of tests with kernels patched for low-latency. Results were most impressive: under 2 msec with a patched 2.2.10 kernel (using Ingo's patch) and under 4 msec on 2.4.0-test9 (with Andrew Morton's patch). Consider the fact that engineers at Cakewalk have recently stated that 5 msec is a best-case scenario for Win2K. Consider also the drive towards the desktop that Linux appears to be making. *All* multimedia applications would benefit from a low-latency kernel, so I'm throwing in my $0.02US for the adoption of Andrew's work into the 2.4.x kernel track. I know this issue was "done in" on this list a while back, and I've read some of that traffic in the archives. But for those of us involved in Linux audio & video, this level of performance is a truly sweet development. We need to convince Steinberg, Cakewalk, Logic, and any other multimedia development houses that there are good solid technical reasons for them to port their software to Linux. The myth of "UNIX != multimedia" is effectively destroyed by these tests. I'm currently preparing an article to present my test results, but I'll be happy to share them with anyone who's interested. The low-latency work is *at least* as important as support for infrared, ham radio, telephony, and 8-way SMP. I'm interested in hearing from anyone else working in this domain, so feel free to write directly to me (I'm not currently a member of the linux-kernel list). I also realize that there was some acrimony regarding the issue. I'm definitely not interested in that, and flames will be politely ignored. The matter is serious, and I would like to convince Linus that it is to everyone's benefit to include low-latency as a kernel compile-time option (at least). Best regards, == Dave Phillips http://www.bright.net/~dlphilp/index.html http://www.bright.net/~dlphilp/linuxsound/ - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] Please read the FAQ at http://www.tux.org/lkml/