Re: incorrect ping(8) interval with powerd(8)

From: M. Warner Losh (imp_at_bsdimp.com)
Date: 06/16/05

  • Next message: Marcin Jessa: "Re: HEADSUP: OpenBSD dhclient incoming"
    Date: Thu, 16 Jun 2005 01:23:02 -0600 (MDT)
    To: jeremie@le-hen.org
    
    

    In message: <20050616070445.GD2239@obiwan.tataz.chchile.org>
                Jeremie Le Hen <jeremie@le-hen.org> writes:
    : Hi Warner,
    :
    : > : %%%
    : > : jarjarbinks:root# sysctl hw.acpi.acline
    : > : hw.acpi.acline: 1
    : > : jarjarbinks:root# sysctl dev.cpu.0.freq
    : > : dev.cpu.0.freq: 1735
    : > : jarjarbinks:root# time ping -qc 2 192.168.1.1
    : > : PING 192.168.1.1 (192.168.1.1): 56 data bytes
    : > :
    : > : --- 192.168.1.1 ping statistics ---
    : > : 2 packets transmitted, 2 packets received, 0% packet loss
    : > : round-trip min/avg/max/stddev = 0.266/0.269/0.271/0.002 ms
    : > :
    : > : real 0m1.003s
    : > : user 0m0.001s
    : > : sys 0m0.001s
    : > :
    : > : jarjarbinks:root# sysctl hw.acpi.acline
    : > : hw.acpi.acline: 0
    : > : jarjarbinks:root# sysctl dev.cpu.0.freq
    : > : dev.cpu.0.freq: 216
    : > : jarjarbinks:root# time ping -qc 2 192.168.1.1
    : > : PING 192.168.1.1 (192.168.1.1): 56 data bytes
    : > :
    : > : --- 192.168.1.1 ping statistics ---
    : > : 2 packets transmitted, 2 packets received, 0% packet loss
    : > : round-trip min/avg/max/stddev = 0.637/0.814/0.991/0.177 ms
    : > :
    : > : real 0m2.252s
    : > : user 0m0.004s
    : > : sys 0m0.021s
    : > : %%%
    : > :
    : > : I check ping(8) source code and it appears it uses select(8) to wait
    : > : the desired amount of time. I don't think this is the intended
    : > : behaviour. Where does this bug (feature?) come from ?
    : >
    : > Those numbers look about right for a 200MHz CPU.
    :
    : May you delve into this a little bit more please ? The ping(8) manual
    : page states that the -i flags makes ping(8) to wait a given couple of
    : seconds. If I use the flags "-i 1", I expect ECHO Requests to be sent
    : with one second between each, whatever the AC line status is.
    : (Note that I didn't explicitely specified "-i 1" in the above example,
    : but this doesn't change the behaviour.)

    Well, the rount trip times went way up (3x longer). That's normal for
    a 200MHz CPU... My 333MHz EISA machine can't do much better than
    that.

    But the 2.252s run time is a little longish. Do you see this
    consistantly? If you ran it a second time would you get identical
    results. I've seen ARP take a while... What else do you have running
    on the system? Maybe a daemon that takes almost no time at 1.7GHz
    takes a lot longer at 200Mhz and that's starving the ping process...
    Or some driver has gone insane...

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


  • Next message: Marcin Jessa: "Re: HEADSUP: OpenBSD dhclient incoming"

    Relevant Pages

    • Re: RELENG_5 installworld fails
      ... > I just can't link problems with GCC optimization flags, ... killing the CPU and FLAGS are a place to start. ... Kent Stewart ...
      (freebsd-questions)
    • Re: [patch 05/10] Text Edit Lock - Alternative code for i386 and x86_64
      ... The common code should be in a common function. ... flags argument is passed without &. ... Should disable interrupts too just to be safer? ... interrupt handler will run with WP flag cleared on the CPU. ...
      (Linux-Kernel)
    • Cpu jammed up after sp2 install
      ... okay, here's the deal - I installed sp2 twice, the second time I ... random processes would be slurping up all available cpu cycles, ... cpu hemmed up at 100% usage. ...
      (microsoft.public.windowsupdate)
    • [PATCH] PPC/PPC64: Introduce CPU_HAS_FEATURE() macro
      ... This also takes care of the differences between PPC and PPC64 cpu ... unsigned int real_instr; ... unsigned long flags; ...
      (Linux-Kernel)
    • RE: cpu architecture
      ... Look at the flags. ... processor as well as the CPU family. ... clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt lm 3dnowext ... can any one tell me how i check my processor arch or cpu arch. ...
      (RedHat)