Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 20 Jul 2011 18:02:12 +0100
From:      "Steven Hartland" <killing@multiplay.co.uk>
To:        "Jack Vogel" <jfvogel@gmail.com>
Cc:        freebsd-net@freebsd.org, "Michael W. Lucas" <mwlucas@blackhelicopters.org>
Subject:   Re: kern/152828: [em] poor performance on 8.1, 8.2-PRE
Message-ID:  <2976D84B193E4D7DAE6F4C4E28B8F909@multiplay.co.uk>
References:  <201107201550.p6KFo9rH032569@freefall.freebsd.org><54AEE240C5F8411A9D4274605DBD14BC@multiplay.co.uk> <CAFOYbckYazC0D4qjK__vv5eGOE_y01qYWgY4T5zz%2BET=ru1ORg@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
Apologies, thought it might be worth a shot, but clearly not thanks for clarifying :)

You absolutely correct with the msix masking the issue, we've just this minute had it stall again even with MSIX disabled :(

I agree we have many machines using igb and em without issue even under lots of load.

Not wishing to hijack this thread, but any advise on what else to try to diagnose this stalling issue would be gratefully received.

    Regards
    Steve
  ----- Original Message -----=20
  From: Jack Vogel=20
  To: Steven Hartland=20
  Cc: Michael W. Lucas ; freebsd-net@freebsd.org=20
  Sent: Wednesday, July 20, 2011 5:38 PM
  Subject: Re: kern/152828: [em] poor performance on 8.1, 8.2-PRE


  This is an em bug, igb does not share interrupt code with em, furthermore the adapter
  the filer of the bug is using doesn't use MSIX, only one type in the em driver does,
  and I might add lots of heavy users on that adapter have MSIX on without issues.

  I believe turning MSIX off is just masking whatever your real issue is, if you wish to
  run that way that's fine, but please don't advertise that as a 'fix' in some general way.

  Regards,

  Jack



  On Wed, Jul 20, 2011 at 9:07 AM, Steven Hartland <killing@multiplay.co.uk> wrote:

    We're seeing tcp stalls under igb under 8.2-RELEASE and 8-STABLE (which shares
    some code with em) and the workaround for use is currently adding the following
    to /boot/loader.conf
    hw.igb.enable_msix=3D0

    Might be worth trying that.

      Regards
      Steve

    ----- Original Message ----- From: "Michael W. Lucas" <mwlucas@blackhelicopters.org>
    To: <freebsd-net@FreeBSD.org>
    Sent: Wednesday, July 20, 2011 4:50 PM

    Subject: Re: kern/152828: [em] poor performance on 8.1, 8.2-PRE



      The following reply was made to PR kern/152828; it has been noted by GNATS.

      From: "Michael W. Lucas" <mwlucas@blackhelicopters.org>
      To: bug-followup@FreeBSD.org
      Cc: rick@sloservers.com
      Subject: Re: kern/152828: [em] poor performance on 8.1, 8.2-PRE
      Date: Wed, 20 Jul 2011 11:49:08 -0400

      I'm seeing the exact same problem here as the original poster. Is
      anybody looking at this?

      Running FreeBSD 8.2-RELEASE-p1 amd64, from FreeNAS 8.0

      sysctls:
      dev.em.0.%desc: Intel(R) PRO/1000 Network Connection 7.1.9
      dev.em.0.%driver: em
      dev.em.0.%location: slot=3D0 function=3D0
      dev.em.0.%pnpinfo: vendor=3D0x8086 device=3D0x108b subvendor=3D0x8086 subdevice=3D0x0000 class=3D0x020000
      dev.em.0.%parent: pci1
      dev.em.0.nvm: -1
      dev.em.0.debug: -1
      ...

      ifconfig:
      em0: flags=3D8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500
             options=3D219b<RXCSUM,TXCSUM,VLAN_MTU,VLAN_HWTAGGING,VLAN_HWCSUM,TSO4,WOL_MAGIC>
             ether 00:15:17:31:c8:fe
             inet 139.171.199.13 netmask 0xffffff00 broadcast 139.171.199.255
             media: Ethernet autoselect (1000baseT <full-duplex>)
             status: active

      dmesg | grep em0
      em0: <Intel(R) PRO/1000 Network Connection 7.1.9> port 0xbc00-0xbc1f mem 0xff6e0000-0xff6fffff irq 16 at device 0.0 on pci1
      em0: Using an MSI interrupt
      em0: [FILTER]
      em0: Ethernet address: 00:15:17:31:c8:fe




      --=20
      Michael W. Lucas http://www.MichaelWLucas.com/, http://blather.MichaelWLucas.com/
      Latest book: Network Flow Analysis http://www.networkflowanalysis.com/
      mwlucas@BlackHelicopters.org, Twitter @mwlauthor
      _______________________________________________
      freebsd-net@freebsd.org mailing list
      http://lists.freebsd.org/mailman/listinfo/freebsd-net
      To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org"




    =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
    This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it.=20
    In the event of misdirection, illegible or incomplete transmission please telephone +44 845 868 1337
    or return the E.mail to postmaster@multiplay.co.uk.


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




=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it.=20

In the event of misdirection, illegible or incomplete transmission please telephone +44 845 868 1337
or return the E.mail to postmaster@multiplay.co.uk.



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?2976D84B193E4D7DAE6F4C4E28B8F909>