Messages in this thread | | | Date | Wed, 18 Oct 2006 17:21:39 -0700 | From | Andrew Morton <> | Subject | Re: 2.6.19-rc2-mm1 |
| |
On Wed, 18 Oct 2006 17:07:59 -0700 Badari Pulavarty <pbadari@us.ibm.com> wrote:
> > What does it say in /proc/interrupts? > > > > The x86_64 nmi watchdog handling looks rather complex. > > > > <checks a couple of x86-64 machines> > > > > The /proc/interrutps NMI count seems to be going up by about > > one-per-minute. How odd. Maybe you just need to wait longer. > > > While the soft lock up messages are getting printed.. > (waited for 5 min for these messages).. > > # while :; do grep NMI /proc/interrupts; sleep 30; done > NMI: 265 73 41 47 > NMI: 265 81 62 47 > NMI: 265 81 71 69 > NMI: 265 81 93 77 > NMI: 265 81 101 99 > NMI: 288 82 101 107 > NMI: 296 82 131 129 > NMI: 296 82 153 137 > NMI: 296 82 161 160 > NMI: 296 105 161 167 > NMI: 296 112 184 167 > > Looking at the messages, I don't think trace all cpus > is working ..
nfi what's going on there. On my Conroe machine each CPU's NMI count goes up by what apepars to be one-per-second when the CPUs are flat out busy, but the count increases by random small amounts (like yours) when the machine is idle.
Did you try setting nmi_watchdog=? - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |