Re: [PATCH] Dynamic tick for x86 version 050609-2

From: Srivatsa Vaddagiri (vatsa_at_in.ibm.com)
Date: 06/13/05

  • Next message: Hans Korneder: "alarms do not get fired when booting thru pxelinux"
    Date:	Mon, 13 Jun 2005 22:39:41 +0530
    To: Tony Lindgren <tony@atomide.com>
    
    

    Hi Tony,
            I went through the dynamic-tick patch on your website
    (patch-dynamic-tick-2.6.12-rc6-050610-1) and was having some
    questions about it:

    1. dyn_tick->skip is set to the number of ticks that have
       to be skipped. This is set on the CPU which is the last
       (in online_map) to go idle and is based on when that
       CPU's next timer is set to expire.

       Other CPUs also seem to use the same interval
       to skip ticks. Shouldnt other CPU check their nearest timer
       rather than blindly skipping dyn_tick->skip number of ticks?

    2. reprogram_apic_timer seems to reprogram the count-down
       APIC timer (APIC_TMICT) with an integral number of apic_timer_val.
       How accurate will this be? Shouldnt this take into account
       that we may not be reprogramming the timer on exactly "jiffy"
       boundary?

    3. Is there any strong reason why you reprogram timers only when
       _all_ CPUs are idle?

    4. In what aspects you think does your patch differ from VST (other
       than not relying on HRT!)?

    -- 
    Thanks and Regards,
    Srivatsa Vaddagiri,
    Linux Technology Center,
    IBM Software Labs,
    Bangalore, INDIA - 560017
    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at  http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at  http://www.tux.org/lkml/
    

  • Next message: Hans Korneder: "alarms do not get fired when booting thru pxelinux"

    Relevant Pages

    • Re: 2.6.16-rc6-mm2
      ... CPU: Trace cache: 12K uops, ... Calibrating delay using timer specific routine.. ... # ACPI Support ...
      (Linux-Kernel)
    • [PATCH 2.6.27-rc5] Fix itimer/many thread hang.
      ... a profiling timer in a process with a large number of threads. ... struct thread_group_cputime { ... the structure corresponding to the running CPU, ... from all threads in the thread group now use thread_group_cputimeto ...
      (Linux-Kernel)
    • Re: [RFC] (How to) Let idle CPUs sleep
      ... I did some measurements on the average interval that a idle CPU is allowed to ... The external jiffie timer keeps waking it every jiffy] ... Time taken to find the 30 prime numbers was used as a benchmark ...
      (Linux-Kernel)
    • WARNING: at kernel/smp.c:369 smp_call_function_many+0x52/0x1b3() [2.6.30-01557-gb640f04]
      ... spurious 8259A interrupt: IRQ7. ... 3 timers in total, 0 timers will be used for per-cpu timer ... # CPU Frequency scaling ... # Bus options (PCI etc.) ...
      (Linux-Kernel)
    • [GIT PULL] s390 patches for 2.6.30-rc2
      ... stp synchronization retry timer ... struct vtimer_list *timer; ... * CPU type and hardware bug flags. ... void restart_int_handler; ...
      (Linux-Kernel)