On 2017-06-19 14:55:35 [+0200], Mike Galbraith wrote: > On Mon, 2017-06-19 at 13:50 +0200, Sebastian Andrzej Siewior wrote: > > > > rt20…rt21 is just > > > > https://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git/tree/patches/sched-Prevent-task-state-corruption-by-spurious-lock.patch?h=linux-4.9.y-rt-patches > > Yup. I got there via git checkout v4.9.x-rtx, build/test. > > > Let me verify that here and fire maybe the four socket box. > > One thing perhaps interesting about the DL980 is that it is 8 socket, > but with 7 memoryless nodes (poor thing). I wouldn't be surprised if > you had to try a lot harder than I. > DL980 now seems happy with master-rt21 fwtw. It's not virgin though, > not even considering continuous merge 4.9..today. > > Hopefully desktop will cease with the comatose widget business too, I > really don't want to go there. These things give tglx headaches, might > well blow the point clean off of my head.
I am suppressed that your desktop shows any symptoms on rt21. I tried my smaller AMD box (A10), an Intel two sockets and a four socket box. Each of them was fine with the run.sh and manual futex_wait invocation. Could you please send the config of your desktop box? > -Mike Sebastian
