Messages in this thread | | | Date | Thu, 6 Mar 2008 15:24:15 -0800 | From | Andrew Morton <> | Subject | Re: 2.6.25-rc3-git3: Reported regressions from 2.6.24 |
| |
On Thu, 6 Mar 2008 15:13:31 -0800 Suresh Siddha <suresh.b.siddha@intel.com> wrote:
> > sd 1:0:0:0: [sdb] Stopping disk > > sd 0:0:0:0: [sda] Synchronizing SCSI cache > > sd 0:0:0:0: [sda] Stopping disk > > ACPI: PCI interrupt for device 0000:05:00.1 disabled > > ACPI: PCI interrupt for device 0000:05:00.0 disabled > > ACPI: Preparing to enter system sleep state S5 > > Disabling non-boot CPUs ... > > CPU 1 is now offline > > SysRq : Show State > > task PC stack pid father > > I have been looking into a similar issue, which stops my system going into > standy.
OK.
> > > > So CPU 1 is offline. But the comatose watchdog thread is pinned to CPU 1. > > Could this be related to the problem? By what means is a task which is > > pinned to a going-away CPU handled? How is this guy supposed to ever run > > again? > > move_task_off_dead_cpu() should move that thread to another online cpu. But > for some reason it isn't running.
hm. What guarantees that kernel/sched.c:migration_call(CPU_DEAD) is called before kernel/softlockup.c:cpu_callback(CPU_DEAD)? Just the ordering in do_pre_smp_initcalls(), and notifier-chain behaviour, I guess.
| |