Re: Database regression due to scheduler changes ?

From: David Lang (david.lang_at_digitalinsight.com)
Date: 11/07/05

  • Next message: Guennadi Liakhovetski: "block requests from user space?" 
    To: Brian Twichell <tbrian@us.ibm.com>
Date:	Mon, 7 Nov 2005 14:35:33 -0800 (PST)

    Brian,
       If I am understanding the data you posted, it looks like you are useing
    sched_yield extensivly in your database. This is known to have significant
    problems on SMP machines, and even bigger ones on NUMA machines, in part
    becouse the process doing the sched_yield may get rescheduled immediatly
    and not allow other processes to run (to free up whatever resource it's
    waiting for). This causes the processor to look busy to the scheduler and
    therefor the scheduler doesn't migrate other processes to the CPU that's
    spinning on sched_yield. On NUMA machines this is even more noticable as
    processes now have to migrate through an additional layer of the
    scheduler.

    have to tried eliminating the sched_yield to see what difference it makes?

    David Lang 

    -- 
There are two ways of constructing a software design. One way is to make it so simple that there are obviously no deficiencies. And the other way is to make it so complicated that there are no obvious deficiencies.
  -- C.A.R. Hoare
-
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: Guennadi Liakhovetski: "block requests from user space?"

    Relevant Pages

    • Re: [Lhms-devel] [PATCH 0/7] Fragmentation Avoidance V19
      ... > I found hugetlb support in linux not very practical/usable on NUMA machines, ... > At least I can reboot it if needed, but I feel Andy pain. ... IBM Linux Technology Center ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: interruptible_sleep_on, interrupts and device drivers
      ... or just a simple semaphore ... OK, i'll not use, but the kernel has a lot of device drivers using it, that ... This is not a problem, because the scheduler will switch to another process, ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: [Lhms-devel] [PATCH 0/7] Fragmentation Avoidance V19
      ... I found hugetlb support in linux not very practical/usable on NUMA machines, ... With this single integer parameter, you cannot allocate 1000 4MB pages on one ... At least I can reboot it if needed, but I feel Andy pain. ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: Database regression due to scheduler changes ?
      ... This causes the processor to look busy to the scheduler and therefor ... On NUMA machines this is even more noticable as processes now ... One day I plan to extend this application across multiple CPUs using either SMP ... CPU in order to free up the critical section faster. ...
      (Linux-Kernel)
    • Re: 2.6.0-test9 - poor swap performance on low end machines
      ... > I suppose it will show some improvement but fail to get performance ... > working on a break-down of where we're losing it. ... I guess encoding a vm scheduler will help (and ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)