On Tue, Jul 12, 2011 at 02:26:34PM -0500, Paul Keusemann wrote:
> On 07/07/11 14:39, Chuck Swiger wrote:
> >On Jul 7, 2011, at 4:45 AM, Paul Keusemann wrote:
> >>My setup is something like this:
> >>- My local network is a mix of AIX, HP-UX, Linux, FreeBSD and Solaris
> >>machines running various
Jack,
I think the SCP scenario would be easiest for anyone else to
reproduce. If you need a different type of scenario, let me know.
I can't put this box into heavy use until I figure this out, so you
might as well use me as a guinea pig.
Thanks,
==ml
On Wed, Jul 20, 2011 at 10:18:32AM -0700, J
Synopsis: [ipfw] [em] ipfw nat and em interface rxcsum problem
State-Changed-From-To: open->feedback
State-Changed-By: ae
State-Changed-When: Wed Jul 20 19:17:03 UTC 2011
State-Changed-Why:
Can you still reproduce this on a supported release?
http://www.freebsd.org/cgi/query-pr.cgi?pr=143939
___
Hi,
I'm not seeing a complete stall, just very slow performance.
I have two hosts on a shared gigabit Ethernet. One is OpenSolaris, the
other FreeBSD. My SCP from the Opensolaris box to the FreeBSD one
goes at:
653 MB00:29
The FreeBSD machine is an Intel SS4200-E.
I have a second environm
It stalls on just a basic file scp. Our current test is to scp the freebsd
iso to the machine. It won't always do it but it does "seem" like once its had
one stall its very much more prone to repeat stalls.
Here are some examples of what we see:-
FreeBSD-8.2-RELEASE-amd64-disc1.iso41% 2
Can you formulate a scenario that anyone else can setup and reproduce this?
Jack
On Wed, Jul 20, 2011 at 10:13 AM, Steven Hartland
wrote:
> **
> Yep, it stalls 8.2 partners as well :(
>
> - Original Message -
> *From:* Jack Vogel
> *To:* Steven Hartland
> *Cc:* Michael W. Lucas ;
> f
Yep, it stalls 8.2 partners as well :(
- Original Message -
From: Jack Vogel
To: Steven Hartland
Cc: Michael W. Lucas ; freebsd-net@freebsd.org
Sent: Wednesday, July 20, 2011 6:03 PM
Subject: Re: kern/152828: [em] poor performance on 8.1, 8.2-PRE
Did you eliminate that 7
Did you eliminate that 7.0 box as part of the issue? Meaning switch to say a
Linux
or 8.2 partner to see if the problem persists or stops?
Cheers,
Jack
On Wed, Jul 20, 2011 at 10:02 AM, Steven Hartland
wrote:
> **
> Apologies, thought it might be worth a shot, but clearly not thanks for
> clar
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
loa
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 wha
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=0
Might be worth trying that.
Regards
Steve
- Original Message -
From: "Michael W
The following reply was made to PR kern/152828; it has been noted by GNATS.
From: "Michael W. Lucas"
To: bug-follo...@freebsd.org
Cc: r...@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
Thanks Patrick and Dmitry,
indeed `ifstated' and the ``running external tests''-part, sound like it will
be helpful.
/Kim
On 2011-07-20 16:19, Patrick Lamaiziere wrote:
> Le Mon, 18 Jul 2011 19:18:53 +0400,
> Dmitry Banschikov a écrit :
>
> Hi,
>
>>> is it possible to let a CARP-interface fa
Le Mon, 18 Jul 2011 19:18:53 +0400,
Dmitry Banschikov a écrit :
Hi,
> > is it possible to let a CARP-interface fail(-over) in the situation
> > when a certain program fails or stops working? I hope it's clear
> > enough what I have in mind. Could you give me any pointers on how
> > this can be a
> Tue, Jul 19, 2011 at 10:40:11AM +0300, Daniel Braniss wrote:
> > > And that non-broadcast ethernet address is the MAC of your
> > > default router?
> > yes.
with dest_addr = INADDR_BROADCAST on the non diskless:
09:44:29.850576 00:0d:b9:00:72:a8 (oui Unknown) > 00:04:38:a0:c6:07 (oui
Unknown),
15 matches
Mail list logo
