Re: Benchmark: NetBSD 2.0 [allegedly] beats FreeBSD 5.3 in server performance

From: Robert Watson (rwatson_at_freebsd.org)
Date: 01/06/05

  • Next message: Michael Nottebrock: "Re: Benchmark: NetBSD 2.0 [allegedly] beats FreeBSD 5.3 in server performance" 
    Date: Thu, 6 Jan 2005 19:36:49 +0000 (GMT)
To: stheg olloydson <stheg_olloydson@yahoo.com>

    On Thu, 6 Jan 2005, stheg olloydson wrote:

    > it was said by Phil Brennan:
    >
    > >What about the context switch time? Are there any plans to improve
    > >this, and also to reduce the number of context switches needed?
    >
    > See Robert Watson's reply to this thread. An unfortunate number of
    > problems exist in threading and scheduling. Most are well-understood and
    > are being worked on and 5.4 should see measurable improvement.
    > Personally, I am more concerned with network and scheduler perfomance.
    > I know the former is being addressed, but I don't hear anything about
    > how work on SCHED_ULE is progressing.

    FWIW, one of the reasons that there hasn't been as much interest in
    SCHED_ULE lately is likely that several of the features previously only
    present in SCHED_ULE are now also present in SCHED_4BSD -- for example,
    making more effective uses of IPIs in reducing latency during
    inter-process communication across processors. While SCHED_ULE does
    contain a number of interesting things not present in SCHED_4BSD, the 4BSD
    scheduler has hardly gone un-improved in that time. However, Jeff
    Robserson does seem to have picked up recently on both VFS SMP locking and
    ULE. The scheduler tracing and visualization tools he committed a couple
    of weeks ago are really quite neat tools.

    Robert N M Watson

    _______________________________________________
    freebsd-performance@freebsd.org mailing list
    http://lists.freebsd.org/mailman/listinfo/freebsd-performance
    To unsubscribe, send any mail to "freebsd-performance-unsubscribe@freebsd.org"

  • Next message: Michael Nottebrock: "Re: Benchmark: NetBSD 2.0 [allegedly] beats FreeBSD 5.3 in server performance"

    Relevant Pages

    • Re: [PATCH]O14int
      ... > renders the thing vaguely timeout-based like 2.4.x. ... Does the scheduler ever intend to delay a context ... The SMP issues addressed by the algorithmic improvements in the ... as its context switch rates are excessive there. ...
      (Linux-Kernel)
    • Regarding taskLock() and tasUnlock()
      ... taskLock() is called the scheduler will be disabled". ... When a scheduler is explicitly blocked because of calling ... variable "lockCnt" which is part of task's TCB. ... kernel able to disable the task context switch with the help of this ...
      (comp.os.vxworks)
    • Re: N Process --> (potentially) N cores
      ... correct regardless of what the scheduler does. ... read or write its memory. ... object to be able to easily destroy work being done for other clients. ... The logic is that a context switch between two threads is less ...
      (comp.unix.programmer)
    • Re: Regarding taskLock() and tasUnlock()
      ... taskLock() prevents a higher priority task from getting the CPU ... the scheduler checks the status of this variable before ... variable "lockCnt" which is part of task's TCB. ... kernel able to disable the task context switch with the help of this ...
      (comp.os.vxworks)
    • Re: Context Switch Time
      ... resemblence to context switch time. ... Actually, it's more like an exception than an interrupt, in that it's ... syscall exception handler simply doesn't need to save all registers (and ...
      (comp.programming.threads)