Re: [PATCH] Do not force shutdown/reboot to boot cpu.

[Robin Holt <holt@sgi.com>]

> > I'm proposing to make 'reboot' overhead profilable, via a debug hack:
> > 
> >         echo 1 > /proc/sys/kernel/magic_dont_fully_reboot_flag
> > 
> > 	perf record reboot
> > 
> > perf is using NMIs to profile - and since much of cpu_down() is with irqs 
> > disabled, NMI profiling would be needed to see inside the overhead.
> > 
> > (Assuming the 240 msecs is CPU overhead, not waiting for some IRQ/IPI event.)


I had the machine booted as 512 cpus.
I tweaked the kernel like this:

diff --git a/kernel/sys.c b/kernel/sys.c
index 39c9c4a..b42bd4f 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -368,8 +368,10 @@ EXPORT_SYMBOL(unregister_reboot_notifier);
  */
 void kernel_restart(char *cmd)
 {
-       kernel_restart_prepare(cmd);
+       // kernel_restart_prepare(cmd);
        disable_nonboot_cpus();
+       enable_nonboot_cpus();
+       return;
        if (!cmd)
                printk(KERN_EMERG "Restarting system.\n");
        else

perf record -a /sbin/reboot -d -f -n

The top of 'perf report' has:
Events: 14M cycles
    22.58%          swapper  [kernel.kallsyms]           [k] update_cfs_rq_blocked_load
    10.52%          swapper  [kernel.kallsyms]           [k] load_balance
     4.96%          swapper  [kernel.kallsyms]           [k] ktime_get
     4.12%          swapper  [kernel.kallsyms]           [k] update_blocked_averages
     3.55%          swapper  [kernel.kallsyms]           [k] idle_cpu
     1.97%          swapper  [kernel.kallsyms]           [k] uv_read_rtc
     0.98%          swapper  [kernel.kallsyms]           [k] rcu_process_gp_end
     0.84%          swapper  [kernel.kallsyms]           [k] apic_timer_interrupt
     0.84%          swapper  [kernel.kallsyms]           [k] __lock_text_start
     0.84%          swapper  [kernel.kallsyms]           [k] _raw_spin_lock_irqsave
     0.73%          swapper  [kernel.kallsyms]           [k] native_safe_halt
     0.56%          swapper  [kernel.kallsyms]           [k] rcu_check_callbacks
     0.56%          swapper  [kernel.kallsyms]           [k] native_write_msr_safe
     0.44%          swapper  [kernel.kallsyms]           [k] cpumask_next_and
     0.42%           reboot  [kernel.kallsyms]           [k] kmem_cache_alloc_node

The perf data is 676 MB.  I don't know how well it compresses, but the
lzma task has been running for a while.

Thanks,
Robin