At 05 Oct 2001 06:57:51 -0700, Josh Green wrote: > > On Fri, 2001-10-05 at 06:32, Takashi Iwai wrote: > > At 05 Oct 2001 05:20:40 -0700, > > > > A good news: after several tries and hacks, I got 1msec latency. > > You need to add rescheduling checks in sync_buffers() loop (in > > fs/buffer.c). In my case I added the checks in write_some_buffers() > > and wait_for_buffers(), which are called from sync_buffers(). > > > > My results are shown in > > http://www.alsa-project.org/~iwai/latency-results/ > > The subdirectory rf-ll2-alsa contains the latest (almost perfect) > > result with 2.4.10 + LL + my patch + ALSA 0.9.0 + reiserfs. > > (No explanatory html, sorry.) > > > > Cool! Those graphs are sweeeeet! So are you using Andrew Morton's LL > patch (I notice there is one up on his site now for 2.4.10)? + your > sync_buffers() resched checks. I'll probably give it a try tomorrow > (actually it is tomorrow already, must go to sleep, sun is making things > brighter).
Oh I didn't know 2.4.10 and even 2.4.11-pre3 patches are available. It seems that the resched check is still missing in sync_buffers() loop, though. Anyway i'll try it too. Thanks. Well, in my case, I used 2.4.9-LL patch (rejection resolved by myself), and added resched checks in write_some_buffers(), wait_for_buffers() and __invalidate_buffers() (all in fs/buffer.c) loops. Takashi _______________________________________________ Alsa-devel mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/alsa-devel
