Re: 24 lost ticks with 2.6.20.10 kernel
- From: Chuck Ebbert <cebbert@xxxxxxxxxx>
- Date: Tue, 01 May 2007 11:34:28 -0400
Michel Lespinasse wrote:
I'm having an issue with lost ticks, runnign linux 2.6.20.10 on an
intel DQ965GF motherboard. For some reason this occurs with clock-like
regularity, always exactly 24 lost ticks, about every two seconds.
This is running with 250-HZ ticks, and the small pause every two seconds
is also noticeable when using the console.
running with report_lost_ticks, I see the following:
May 1 12:58:57 server kernel: time.c: Lost 24 timer tick(s)! rip _spin_unlock_irqrestore+0x8/0x9)
May 1 12:58:59 server kernel: time.c: Lost 24 timer tick(s)! rip _spin_unlock_irqrestore+0x8/0x9)
May 1 12:59:01 server kernel: time.c: Lost 25 timer tick(s)! rip _spin_unlock_irqrestore+0x8/0x9)
May 1 12:59:03 server kernel: time.c: Lost 24 timer tick(s)! rip _spin_unlock_irqrestore+0x8/0x9)
May 1 12:59:07 server last message repeated 2 times
May 1 12:59:10 server kernel: time.c: Lost 24 timer tick(s)! rip handle_IRQ_event+0x19/0x55)
May 1 12:59:12 server kernel: time.c: Lost 24 timer tick(s)! rip handle_IRQ_event+0x19/0x55)
May 1 12:59:14 server kernel: time.c: Lost 24 timer tick(s)! rip _spin_unlock_irqrestore+0x8/0x9)
May 1 12:59:16 server kernel: time.c: Lost 24 timer tick(s)! rip _spin_unlock_irqrestore+0x8/0x9)
May 1 12:59:18 server kernel: time.c: Lost 24 timer tick(s)! rip handle_IRQ_event+0x19/0x55)
May 1 12:59:20 server kernel: time.c: Lost 24 timer tick(s)! rip _spin_unlock_irqrestore+0x8/0x9)
May 1 12:59:52 server last message repeated 15 times
May 1 13:00:51 server last message repeated 28 times
May 1 13:01:47 server last message repeated 27 times
May 1 13:01:50 server kernel: time.c: Lost 25 timer tick(s)! rip _spin_unlock_irqrestore+0x8/0x9)
May 1 13:01:56 server last message repeated 3 times
May 1 13:01:58 server kernel: time.c: Lost 24 timer tick(s)! rip _spin_unlock_irqrestore+0x8/0x9)
Since the rip often mentions _spin_unlock_irqrestore, I figured maybe
someone sleeps for 25 ticks with the interrupts disabled. I tried
running with CONFIG_DEBUG_SPINLOCK_SLEEP but this did not uncover anything.
I also noticed this code in arch/x86_64/kernel/time.c. I'm not sure if it
has anything to do with my issue, but it might since I get lost_count==24...
I could not figure out what this code is trying to do though.
#ifdef CONFIG_CPU_FREQ
/* In some cases the CPU can change frequency without us noticing
Give cpufreq a change to catch up. */
if ((lost_count+1) % 25 == 0)
cpufreq_delayed_get();
#endif
I'm not sure where to go from here. Additional information about my system:
Try disabling CONFIG_CPU_FREQ?
One last thing: I have another box which is fairly similar, with a
DG965RY motherboard. That other box does *not* seem to lose any ticks,
running the same kernel that works so poorly on the DQ965GF board.
Does that point to a hardware/bios issue then ?????
Is it running the exact same kernel, with the same cpufreq settings at
runtime (governor, controller, etc?)
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
- Follow-Ups:
- Re: 24 lost ticks with 2.6.20.10 kernel
- From: Michel Lespinasse
- Re: 24 lost ticks with 2.6.20.10 kernel
- References:
- 24 lost ticks with 2.6.20.10 kernel
- From: Michel Lespinasse
- 24 lost ticks with 2.6.20.10 kernel
- Prev by Date: Re: AF_RXRPC depends on KEYS?
- Next by Date: Re: [AF_RXRPC]: Make the in-kernel AFS filesystem use AF_RXRPC.
- Previous by thread: 24 lost ticks with 2.6.20.10 kernel
- Next by thread: Re: 24 lost ticks with 2.6.20.10 kernel
- Index(es):
Relevant Pages
|