RE: Industry db benchmark result on recent 2.6 kernels

From: Chen, Kenneth W (kenneth.w.chen_at_intel.com)
Date: 03/31/05

  • Next message: Maximilian Engelhardt: "Re: Call for help: list of machines with working S3" 
    To: "'Ingo Molnar'" <mingo@elte.hu>
Date:	Thu, 31 Mar 2005 11:53:50 -0800

    Ingo Molnar wrote on Thursday, March 31, 2005 6:15 AM
    > is there any idle time on the system, in steady state (it's a sign of
    > under-balancing)? Idle balancing (and wakeup balancing) is one of the
    > things that got tuned back and forth alot. Also, do you know what the
    > total number of context-switches is during the full test on each kernel?
    > Too many context-switches can be an indicator of over-balancing. Another
    > sign of migration gone bad can be relative increase of userspace time
    > vs. system time. (due to cache trashing, on DB workloads, where most of
    > the cache contents are userspace's.)

    No, there are no idle time on the system. If system become I/O bound, we
    would do everything we can to remove that bottleneck, i.e., throw a couple
    hundred GB of memory to the system, or add a couple hundred disk drives,
    etc. Believe it or not, we are currently CPU bound and that's the reason
    why I care about every single cpu cycle being spend in the kernel code.

    -
    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: Maximilian Engelhardt: "Re: Call for help: list of machines with working S3"

    Relevant Pages

    • Re: Where is the performance bottleneck?
      ... There's plenty of idle time. ... feels like the problem is elsewhere (driver, ... But lets gather some more info first, ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: [PATCH] Nicks scheduler policy v10
      ... one of Con's patches caused a lot of idle time on volanomark. ... > Anyway, in the process of looking at the load balancing, we found ... > This did cure most of the idle problems. ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: 2.6.4-mm2
      ... Thanks to Nick and Ingo. ... There is considerably more idle time in the bad run: ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • RE: [patch] sched: auto-tune migration costs [was: Re: Industry db benchmark result on recent 2.6 ke
      ... > multiple migration-cost settings could be tried? ... shows that the sweet spot was 12.5ms. ... to tune/optimize the scheduler and reap these extra idle time. ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: 2.6.4-mm2
      ... On Tue, 2004-03-23 at 11:32, Andrew Morton wrote: ... There is considerably more idle time in the bad run: ... Mary Edie Meredith ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)