netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Zoltan Kiss <zoltan.kiss@citrix.com>
To: Andrew Cooper <andrew.cooper3@citrix.com>,
	Michael Chan <mchan@broadcom.com>
Cc: linux-kernel@vger.kernel.org, Carolyn, Tushar,
	e1000-devel@lists.sourceforge.net,
	Bruce Allan <bruce.w.allan@intel.com>,
	Jesse Brandeburg <jesse.brandeburg@intel.com>,
	"David S. Miller" <davem@davemloft.net>,
	John Ronciak <john.ronciak@intel.com>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"xen-devel@lists.xenproject.org" <xen-devel@lists.xenproject.org>,
	Peter
Subject: Re: igb and bnx2: "NETDEV WATCHDOG: transmit queue timed out" when skb has huge linear buffer
Date: Thu, 6 Feb 2014 09:58:25 +0000	[thread overview]
Message-ID: <52F35CC1.60401@citrix.com> (raw)
In-Reply-To: <52F2A282.5040502@citrix.com>

On 05/02/14 20:43, Andrew Cooper wrote:
> On 05/02/2014 20:23, Zoltan Kiss wrote:
>> On 04/02/14 19:47, Michael Chan wrote:
>>> On Fri, 2014-01-31 at 14:29 +0100, Zoltan Kiss wrote:
>>>> [ 5417.275472] WARNING: at net/sched/sch_generic.c:255
>>>> dev_watchdog+0x156/0x1f0()
>>>> [ 5417.275474] NETDEV WATCHDOG: eth1 (bnx2): transmit queue 2 timed out
>>>
>>> The dump shows an internal IRQ pending on MSIX vector 2 which matches
>>> the the queue number that is timing out.  I don't know what happened to
>>> the MSIX and why the driver is not seeing it.  Do you see an IRQ error
>>> message from the kernel a few seconds before the tx timeout message?
>>
>> I haven't seen any IRQ related error message. Note, this is on Xen
>> 4.3.1. Now I have new results with a reworked version of the patch,
>> unfortunately it still has this issue. Here is a bnx2 dump, lspci
>> output and some Xen debug output (MSI and interrupt bindings, I have
>> more if needed).
>
> You need debug-keys 'Q' as well to map between the PCI devices and Xen IRQs
>
> ~Andrew
>

I could have it after reboot:

(XEN) [2014-02-06 09:44:34] 0000:02:00.0 - dom 0   - MSIs < 64 65 66 67 
68 69 >

So the relevant MSI informations:

(XEN) [2014-02-05 20:15:20]  MSI-X   64 vec=d7  fixed  edge   assert 
phys    cpu dest=00000022 mask=1/0/0
(XEN) [2014-02-05 20:15:20]  MSI-X   65 vec=ba  fixed  edge   assert 
phys    cpu dest=00000000 mask=1/0/0
(XEN) [2014-02-05 20:15:20]  MSI-X   66 vec=92  fixed  edge   assert 
phys    cpu dest=00000022 mask=1/0/0
(XEN) [2014-02-05 20:15:20]  MSI-X   67 vec=3a  fixed  edge   assert 
phys    cpu dest=00000021 mask=1/0/0
(XEN) [2014-02-05 20:15:20]  MSI-X   68 vec=b8  fixed  edge   assert 
phys    cpu dest=00000022 mask=1/0/0
(XEN) [2014-02-05 20:15:20]  MSI-X   69 vec=2a  fixed  edge   assert 
phys    cpu dest=00000020 mask=1/1/1
...
(XEN) [2014-02-05 20:15:22]    IRQ:  64 affinity:00000004 vec:d7 
type=PCI-MSI/-X      status=00000030 in-flight=0 domain-list=0:304(---),
(XEN) [2014-02-05 20:15:22]    IRQ:  65 affinity:00000100 vec:ba 
type=PCI-MSI/-X      status=00000010 in-flight=0 domain-list=0:303(---),
(XEN) [2014-02-05 20:15:22]    IRQ:  66 affinity:00000004 vec:92 
type=PCI-MSI/-X      status=00000010 in-flight=0 domain-list=0:302(---),
(XEN) [2014-02-05 20:15:22]    IRQ:  67 affinity:00000002 vec:3a 
type=PCI-MSI/-X      status=00000010 in-flight=0 domain-list=0:301(---),
(XEN) [2014-02-05 20:15:22]    IRQ:  68 affinity:00000004 vec:b8 
type=PCI-MSI/-X      status=00000030 in-flight=0 domain-list=0:300(---),
(XEN) [2014-02-05 20:15:22]    IRQ:  69 affinity:00000001 vec:2a 
type=PCI-MSI/-X      status=00000002 mapped, unbound


Zoli

------------------------------------------------------------------------------
Managing the Performance of Cloud-Based Applications
Take advantage of what the Cloud has to offer - Avoid Common Pitfalls.
Read the Whitepaper.
http://pubads.g.doubleclick.net/gampad/clk?id=121051231&iu=/4140/ostg.clktrk
_______________________________________________
E1000-devel mailing list
E1000-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/e1000-devel
To learn more about Intel&#174; Ethernet, visit http://communities.intel.com/community/wired

  reply	other threads:[~2014-02-06  9:58 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-01-30 19:08 igb and bnx2: "NETDEV WATCHDOG: transmit queue timed out" when skb has huge linear buffer Zoltan Kiss
2014-01-30 20:34 ` Michael Chan
2014-01-31 13:29   ` Zoltan Kiss
2014-02-04 19:47     ` Michael Chan
2014-02-05 20:23       ` Zoltan Kiss
2014-02-05 20:27         ` Zoltan Kiss
2014-02-05 20:43         ` Andrew Cooper
2014-02-06  9:58           ` Zoltan Kiss [this message]
2014-01-31 18:56 ` Wei Liu
2014-02-04 21:32   ` Zoltan Kiss
2014-02-12 17:13 ` Zoltan Kiss

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=52F35CC1.60401@citrix.com \
    --to=zoltan.kiss@citrix.com \
    --cc=andrew.cooper3@citrix.com \
    --cc=bruce.w.allan@intel.com \
    --cc=davem@davemloft.net \
    --cc=e1000-devel@lists.sourceforge.net \
    --cc=jesse.brandeburg@intel.com \
    --cc=john.ronciak@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mchan@broadcom.com \
    --cc=netdev@vger.kernel.org \
    --cc=xen-devel@lists.xenproject.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).