netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Alex Samad <alex@samad.com.au>
To: David Miller <davem@davemloft.net>
Cc: linux-net@vger.kernel.org, netdev@vger.kernel.org,
	herbert@gondor.apana.org.au
Subject: Re: kernel oops when system under network stress
Date: Thu, 16 Oct 2008 16:08:10 +1100	[thread overview]
Message-ID: <20081016050810.GA8240@samad.com.au> (raw)
In-Reply-To: <20081015.215536.242281148.davem@davemloft.net>

[-- Attachment #1: Type: text/plain, Size: 3248 bytes --]

On Wed, Oct 15, 2008 at 09:55:36PM -0700, David Miller wrote:
> From: Alex Samad <alex@samad.com.au>
> Date: Thu, 16 Oct 2008 14:04:16 +1100
> 
> [ Kernel network developers don't read linux-net, which is for
>   user discussion.  They read netdev@vger.kernel.org instead
>   which I've added to the CC:, please maintain this in all
>   follow ups and replys. ]
> 
> > I seems to be getting lots of crashes when my system is under network
> > load, I was moving 1/4T of data over a 1G link and I got lots and lots
> > of these
> 
> What kernel version?

Sorry I put this at the bottom of the email.  its a stock debian 2.6.26
(-8) kernel, nothing special on my side

> 
> How is your system configured?

 lspci -s 0a.0 -vv
00:0a.0 Ethernet controller: nVidia Corporation Device 0760 (rev a2)
	Subsystem: Giga-byte Technology Device e000
	Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop-
ParErr- Stepping- SERR- FastB2B- DisINTx+
	Status: Cap+ 66MHz+ UDF- FastB2B+ ParErr- DEVSEL=fast >TAbort-
<TAbort- <MAbort- >SERR- <PERR- INTx-
	Latency: 0 (250ns min, 5000ns max)
	Interrupt: pin A routed to IRQ 1277
	Region 0: Memory at f8007000 (32-bit, non-prefetchable)
[size=4K]
	Region 1: I/O ports at d800 [size=8]
	Region 2: Memory at f8008000 (32-bit, non-prefetchable)
[size=256]
	Region 3: Memory at f8009000 (32-bit, non-prefetchable)
[size=16]
	Capabilities: <access denied>
	Kernel driver in use: forcedeth
	Kernel modules: forcedeth

I have eth0 bridged to brhme1.

I have seen this problem when doing rsync/ssh of large files and whilst
doing transfer of files with nfs (udp & tcp thought more issues arise
with udp), also tried different mtu's as well and that was worst of all.

The thing to note was (for example), when I was doing a nfs transfer, it
would not be nfs that would crash, it would be other network based
application that would cause the problem, for ex sshd, apache etc


> 
> Otherwise it is harder for us to analyze this report.
> 
> Thanks.
> 

[snip]

> > somebody if it would help.
> > 
> > Is this a bug or ?
> > 
> > I am running debian 2.6.26-8 
> > Linux max 2.6.26-1-amd64 #1 SMP Thu Oct 9 14:16:53 UTC 2008 x86_64
> > GNU/Linux
> > 
> > 
> > I have eth0 bridges to brhme1 (so that I can attach virtual box machines
> > there - none attached currently)
> > 
> > and I have some firewall rules as well.  That really about it to the
> > changes I have made
> > 
> > 
> > 
> > Thanks
> > Alex 
> > 
> > PS can you cc me on the replay, in the process of registering
> > 
> > 
> > -- 
> > "Columbia carried in its payroll classroom experiments from some of our students in America."
> > 
> > 	- George W. Bush
> > 02/03/2003
> > Bethesda, MD
> --
> To unsubscribe from this list: send the line "unsubscribe linux-net" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 

-- 
"If there's a leak out of my administration, I want to know who it is. If the person has violated law, that person will be taken care of."

	- George W. Bush
09/30/2003
Washington, DC
Commenting on the CIA leak that he and Cheney later admitted they approved

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 197 bytes --]

  reply	other threads:[~2008-10-16  5:08 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20081016030416.GA5551@samad.com.au>
2008-10-16  4:55 ` kernel oops when system under network stress David Miller
2008-10-16  5:08   ` Alex Samad [this message]
2008-10-16  6:41     ` Herbert Xu
2008-10-16  7:09       ` Alex Samad
2008-10-16  7:15         ` Alex Samad
2008-10-16  9:10         ` Herbert Xu
2008-10-24  2:09           ` Alex Samad
2008-10-16  5:41   ` Herbert Xu
2008-10-16  5:48     ` Alex Samad
2008-10-16  7:07       ` Herbert Xu

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=20081016050810.GA8240@samad.com.au \
    --to=alex@samad.com.au \
    --cc=davem@davemloft.net \
    --cc=herbert@gondor.apana.org.au \
    --cc=linux-net@vger.kernel.org \
    --cc=netdev@vger.kernel.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).