by tip-bot for Borislav Petkov

[permalink] [raw]

Subject: Re: PROBLEM: Can't boot a (HZ = 1000) kernel using an AMD Phenom-II processor

On Mon, Jan 26, 2009 at 01:26:58PM -0500, Mark Hounschell wrote:

[.. ]

> If there is anything else I can try, I'm at your disposal.

Ok, I just boot-tested a 1000 HZ kernel here and I can't reproduce
your problem. Can you please send the failing .config. And also where
exactly does your kernel hang during the boot process, can you capture
any output and/or enable SysRq to dump backtrace on all cores (SysRq-T)
if possible. Finally, what does 'cat /proc/timer_list' on the working
kernel say?

Thanks.

--
Regards/Gruss,
Boris.

Operating | Advanced Micro Devices GmbH
System | Karl-Hammerschmidt-Str. 34, 85609 Dornach b. M?nchen, Germany
Research | Gesch?ftsf?hrer: Jochen Polster, Thomas M. McCoy, Giuliano Meroni
Center | Sitz: Dornach, Gemeinde Aschheim, Landkreis M?nchen
(OSRC) | Registergericht M?nchen, HRB Nr. 43632

2009-01-28 00:30:47

Mark Hounschell wrote:
> Mark Hounschell wrote:
>> Borislav Petkov wrote:
>>> On Mon, Jan 26, 2009 at 01:26:58PM -0500, Mark Hounschell wrote:
>>>
>>> [.. ]
>>>
>>>> If there is anything else I can try, I'm at your disposal.
>>> Ok, I just boot-tested a 1000 HZ kernel here and I can't reproduce
>>> your problem. Can you please send the failing .config. And also where
>>> exactly does your kernel hang during the boot process, can you capture
>>> any output and/or enable SysRq to dump backtrace on all cores (SysRq-T)
>>> if possible. Finally, what does 'cat /proc/timer_list' on the working
>>> kernel say?
>>>
>>> Thanks.
>>>
>>
>> You test booted using a Phenom-II?
>>
>> The config file is attached. The timer_list while running the 250 Hz 2.6.26.8
>> kernel output is below. When it happens I have no keyboard at all. SysRq is not
>> functional at this time. Sorry.
>>
>> Sorry it took so long. I was out of town today.
>>
>> Timer List Version: v0.3
>> HRTIMER_MAX_CLOCK_BASES: 2
>> now at 675544989236 nsecs
>>
>> cpu: 0
>> clock 0:
>> .index: 0
>> .resolution: 1 nsecs
>> .get_time: ktime_get_real
>> .offset: 1233101890018929078 nsecs
>> active timers:
>> clock 1:
>> .index: 1
>> .resolution: 1 nsecs
>> .get_time: ktime_get
>> .offset: 0 nsecs
>> active timers:
>> #0: <f31ffec0>, tick_sched_timer, S:01, tick_setup_sched_timer, swapper/0
>> # expires at 675548000000 nsecs [in 3010764 nsecs]
>> .expires_next : 675548000000 nsecs
>> .hres_active : 1
>> .nr_events : 170138
>> .nohz_mode : 0
>> .idle_tick : 0 nsecs
>> .tick_stopped : 0
>> .idle_jiffies : 0
>> .idle_calls : 0
>> .idle_sleeps : 0
>> .idle_entrytime : 0 nsecs
>> .idle_waketime : 0 nsecs
>> .idle_exittime : 0 nsecs
>> .idle_sleeptime : 0 nsecs
>> .last_jiffies : 0
>> .next_jiffies : 0
>> .idle_expires : 0 nsecs
>> jiffies: 93886
>>
>> cpu: 1
>> clock 0:
>> .index: 0
>> .resolution: 1 nsecs
>> .get_time: ktime_get_real
>> .offset: 1233101890018929078 nsecs
>> active timers:
>> clock 1:
>> .index: 1
>> .resolution: 1 nsecs
>> .get_time: ktime_get
>> .offset: 0 nsecs
>> active timers:
>> #0: <f31ffec0>, tick_sched_timer, S:01, tick_setup_sched_timer, swapper/0
>> # expires at 675548500000 nsecs [in 3510764 nsecs]
>> #1: <f31ffec0>, it_real_fn, S:01, do_setitimer, ntpd/4446
>> # expires at 676081032589 nsecs [in 536043353 nsecs]
>> #2: <f31ffec0>, hrtimer_wakeup, S:01, futex_wait, nscd/4456
>> # expires at 683136927993 nsecs [in 7591938757 nsecs]
>> #3: <f31ffec0>, hrtimer_wakeup, S:01, do_nanosleep, cron/4539
>> # expires at 711791265959 nsecs [in 36246276723 nsecs]
>> #4: <f31ffec0>, it_real_fn, S:01, do_setitimer, qmgr/4549
>> # expires at 1001716635269 nsecs [in 326171646033 nsecs]
>> #5: <f31ffec0>, it_real_fn, S:01, do_setitimer, master/4517
>> # expires at 1001716661669 nsecs [in 326171672433 nsecs]
>> #6: <f31ffec0>, hrtimer_wakeup, S:01, futex_wait, nscd/4459
>> # expires at 28868136987269 nsecs [in 28192591998033 nsecs]
>> .expires_next : 675548500000 nsecs
>> .hres_active : 1
>> .nr_events : 169510
>> .nohz_mode : 0
>> .idle_tick : 0 nsecs
>> .tick_stopped : 0
>> .idle_jiffies : 0
>> .idle_calls : 0
>> .idle_sleeps : 0
>> .idle_entrytime : 0 nsecs
>> .idle_waketime : 0 nsecs
>> .idle_exittime : 0 nsecs
>> .idle_sleeptime : 0 nsecs
>> .last_jiffies : 0
>> .next_jiffies : 0
>> .idle_expires : 0 nsecs
>> jiffies: 93886
>>
>> cpu: 2
>> clock 0:
>> .index: 0
>> .resolution: 1 nsecs
>> .get_time: ktime_get_real
>> .offset: 1233101890018929078 nsecs
>> active timers:
>> clock 1:
>> .index: 1
>> .resolution: 1 nsecs
>> .get_time: ktime_get
>> .offset: 0 nsecs
>> active timers:
>> #0: <f31ffec0>, tick_sched_timer, S:01, tick_setup_sched_timer, swapper/0
>> # expires at 675549000000 nsecs [in 4010764 nsecs]
>> #1: <f31ffec0>, it_real_fn, S:01, do_setitimer, Xorg/3325
>> # expires at 675563416492 nsecs [in 18427256 nsecs]
>> #2: <f31ffec0>, hrtimer_wakeup, S:01, do_nanosleep, kwrapper/4982
>> # expires at 676109815468 nsecs [in 564826232 nsecs]
>> #3: <f31ffec0>, hrtimer_wakeup, S:01, futex_wait, nscd/4458
>> # expires at 683435589386 nsecs [in 7890600150 nsecs]
>> #4: <f31ffec0>, it_real_fn, S:01, do_setitimer, pickup/4548
>> # expires at 1001716659224 nsecs [in 326171669988 nsecs]
>> .expires_next : 675549000000 nsecs
>> .hres_active : 1
>> .nr_events : 172253
>> .nohz_mode : 0
>> .idle_tick : 0 nsecs
>> .tick_stopped : 0
>> .idle_jiffies : 0
>> .idle_calls : 0
>> .idle_sleeps : 0
>> .idle_entrytime : 0 nsecs
>> .idle_waketime : 0 nsecs
>> .idle_exittime : 0 nsecs
>> .idle_sleeptime : 0 nsecs
>> .last_jiffies : 0
>> .next_jiffies : 0
>> .idle_expires : 0 nsecs
>> jiffies: 93886
>>
>> cpu: 3
>> clock 0:
>> .index: 0
>> .resolution: 1 nsecs
>> .get_time: ktime_get_real
>> .offset: 1233101890018929078 nsecs
>> active timers:
>> clock 1:
>> .index: 1
>> .resolution: 1 nsecs
>> .get_time: ktime_get
>> .offset: 0 nsecs
>> active timers:
>> #0: <f31ffec0>, tick_sched_timer, S:01, tick_setup_sched_timer, swapper/0
>> # expires at 675545500000 nsecs [in 510764 nsecs]
>> #1: <f31ffec0>, sched_rt_period_timer, S:01, enqueue_task_rt, swapper/1
>> # expires at 676000000000 nsecs [in 455010764 nsecs]
>> #2: <f31ffec0>, hrtimer_wakeup, S:01, futex_wait, thunderbird-bin/5123
>> # expires at 689314480389 nsecs [in 13769491153 nsecs]
>> #3: <f31ffec0>, hrtimer_wakeup, S:01, futex_wait, thunderbird-bin/5209
>> # expires at 689361744389 nsecs [in 13816755153 nsecs]
>> #4: <f31ffec0>, hrtimer_wakeup, S:01, futex_wait, nscd/4457
>> # expires at 3668136917342 nsecs [in 2992591928106 nsecs]
>> .expires_next : 675545500000 nsecs
>> .hres_active : 1
>> .nr_events : 171267
>> .nohz_mode : 0
>> .idle_tick : 0 nsecs
>> .tick_stopped : 0
>> .idle_jiffies : 0
>> .idle_calls : 0
>> .idle_sleeps : 0
>> .idle_entrytime : 0 nsecs
>> .idle_waketime : 0 nsecs
>> .idle_exittime : 0 nsecs
>> .idle_sleeptime : 0 nsecs
>> .last_jiffies : 0
>> .next_jiffies : 0
>> .idle_expires : 0 nsecs
>> jiffies: 93886
>>
>>
>> Tick Device: mode: 1
>> Clock Event Device: hpet
>> max_delta_ns: 2147483647
>> min_delta_ns: 5000
>> mult: 61496114
>> shift: 32
>> mode: 3
>> next_event: 9223372036854775807 nsecs
>> set_next_event: hpet_legacy_next_event
>> set_mode: hpet_legacy_set_mode
>> event_handler: tick_handle_oneshot_broadcast
>> tick_broadcast_mask: 00000000
>> tick_broadcast_oneshot_mask: 00000000
>>
>>
>> Tick Device: mode: 1
>> Clock Event Device: lapic
>> max_delta_ns: 671091850
>> min_delta_ns: 1200
>> mult: 53686828
>> shift: 32
>> mode: 3
>> next_event: 675548000000 nsecs
>> set_next_event: lapic_next_event
>> set_mode: lapic_timer_setup
>> event_handler: hrtimer_interrupt
>>
>> Tick Device: mode: 1
>> Clock Event Device: lapic
>> max_delta_ns: 671091850
>> min_delta_ns: 1200
>> mult: 53686828
>> shift: 32
>> mode: 3
>> next_event: 675548500000 nsecs
>> set_next_event: lapic_next_event
>> set_mode: lapic_timer_setup
>> event_handler: hrtimer_interrupt
>>
>> Tick Device: mode: 1
>> Clock Event Device: lapic
>> max_delta_ns: 671091850
>> min_delta_ns: 1200
>> mult: 53686828
>> shift: 32
>> mode: 3
>> next_event: 675549000000 nsecs
>> set_next_event: lapic_next_event
>> set_mode: lapic_timer_setup
>> event_handler: hrtimer_interrupt
>>
>> Tick Device: mode: 1
>> Clock Event Device: lapic
>> max_delta_ns: 671091850
>> min_delta_ns: 1200
>> mult: 53686828
>> shift: 32
>> mode: 3
>> next_event: 675545500000 nsecs
>> set_next_event: lapic_next_event
>> set_mode: lapic_timer_setup
>> event_handler: hrtimer_interrupt
>>
>>
>>
>> Regards
>> Mark
>>
>
> Oh I Forgot. The last thing I see on the screen is.
>
> Checking if this processor honours the WP bit even in hypervisor mode... OK.
> SLUB: Genslabs=12, HWalign=64, Order=0,3, MinObjects=0, CPUs=4, Nodes=1
>
> Mark
> --

So were you able to reproduce this with my .config. Has anyone booted a Hz=1000
kernel on an AMD Phenom-II? Is there something wrong with my .config? Is there
anything else I can do?

Thanks
Mark