Messages in this thread | | | Date | Sun, 5 Feb 2012 23:04:42 -0800 | From | "Paul E. McKenney" <> | Subject | Re: [PATCH RFC 0/41] RCU commits for 3.4 |
| |
On Fri, Feb 03, 2012 at 11:54:40AM -0800, Kevin Hilman wrote: > "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> writes: > > > On Thu, Feb 02, 2012 at 02:47:14PM -0800, Kevin Hilman wrote: > >> Hi Paul, > >> > >> "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> writes: > >> > >> > This patchset makes RCU more aggressive about entering dyntick-idle mode > >> > in order to improve energy efficiency, > >> > >> I gave this series a spin on an ARM/SMP platform (OMAP4) and the boot > >> hung (tail end of boot log below.) I then realized that had isolcpus=1 > >> on the cmdline from a previous experiment. Removing isolcpus from the > >> cmdline got me back to a working boot. > >> > >> IIRC, some want to remove isolcpus, so I'm not sure if it's expected to > >> work with your series, but thought you'd want to know. > > > > Not expected behavior, thank you for testing! > > > > Could you please share your .config? > > Sure, attached.
Interesting...
Could you please try to reproduce with CONFIG_RCU_CPU_STALL_INFO=y?
That will give me some additional diagnostic information.
Thanx, Paul
| |