[2.6.36-rc regression] occasional complete system hangs on sparc64 SMP

[Mikael Pettersson]

On my Sun Blade 2500 (2 CPUs), post 2.6.35 kernels sometimes hang
completely without visible messages on either the console or in
the kernel logs.

The first two times (with -rc1 or -rc3) it happended during gcc
bootstraps + regression test runs, today (with -rc4) it happended
while compiling the 2.6.36-rc5 kernel.  It's very sporadic, perhaps
one of ten boots will eventually hang like this.

With 2.6.35 the machine is rock solid.

The 2.6.36-rc kernels do appear to be solid on a UP Ultra5, but that
one no longer does any gcc builds or tests, only kernel builds.

Any ideas, or do I have to try to bisect this?

/Mikael
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/