Skip site navigation (1)Skip section navigation (2)
Date:      Sun, 28 Dec 2008 14:45:15 -0800
From:      "Li, Qing" <qing.li@bluecoat.com>
To:        "Christian Gusenbauer" <c47g@gmx.at>, "Kip Macy" <kmacy@freebsd.org>
Cc:        qingli@freebsd.org, "Li, Qing" <qing.li@bluecoat.com>, freebsd-current@freebsd.org
Subject:   RE: Network slowdown on lo0 introduced with svn186119/186121
Message-ID:  <031f01c9693d$f7f5a514$7202020a@internal.cacheflow.com>

next in thread | raw e-mail | index | archive | help
I'll investigate and get back to you ...

-- Qing


-----Original Message-----
From: Christian Gusenbauer <c47g@gmx.at>
Sent: Sunday, December 28, 2008 2:04 PM
To: Kip Macy <kmacy@freebsd.org>
Cc: Li, Qing <qing.li@bluecoat.com>; freebsd-current@freebsd.org =
<freebsd-current@freebsd.org>; qingli@freebsd.org <qingli@freebsd.org>
Subject: Re: Network slowdown on lo0 introduced with svn186119/186121

Hi Kip!

Hmmm, I thought amanda is using a localhost connection? But you're =
right. If I=20
test connections using the 'discard' or 'echo' service with the IP =
address of=20
my lan interface, I get this terrible throughput, too. Using the =
localhost=20
address the throughput is *much* better!

Thanks,
Christian.

On Sunday 28 December 2008, Kip Macy wrote:
> This problem can reproduced with netperf. 127.0.0.1 will give good
> throughput, but using the IP address of one of the interfaces gives
> terrible throughput.
>
> -Kip
>
> On Sun, Dec 28, 2008 at 12:50 PM, Li, Qing <qing.li@bluecoat.com> =
wrote:
> > Hi Christian,
> >
> > Is the loopback address or an address that is assigned to
> > an interface used by amanda? Would it be possible for you
> > to give me some information on the tests you performed and
> > on your method of measurement?
> >
> > Thanks,
> >
> > -- Qing
> >
> > ________________________________
> >
> > From: owner-freebsd-current@freebsd.org on behalf of Christian =
Gusenbauer
> > Sent: Sun 12/28/2008 9:56 AM
> > To: freebsd-current@freebsd.org
> > Subject: Network slowdown on lo0 introduced with svn186119/186121
> >
> >
> >
> > Hi!
> >
> > Today I built a new kernel on current and experienced a massive =
network
> > slowdown on lo0 when doing a backup using amanda. I made some tests =
and
> > it seems that the commits 186119 and 186121 to the svn repository =
are
> > causing it. A kernel based on revision 186107 runs fine and all =
kernels
> > starting with revison 186119 do not.
> >
> > This slowdown seems to appear only on the loopback interface, not on =
my
> > lan interface.
> >
> > Is this a known issue?
> >
> > Regards,
> > Christian.
> > _______________________________________________
> > 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"
> >
> >
> > _______________________________________________
> > 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"





Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?031f01c9693d$f7f5a514$7202020a>