Bug#407757: marked as done (xen kernel makes dom0 slower)

[owner@bugs.debian.org (Debian Bug Tracking System)]

Your message dated Thu, 2 Aug 2007 17:51:39 +0200
with message-id <20070802155139.GG9582@stro.at>
and subject line Bug#407757: Info received (Bug#407757: xen kernel makes dom0 slower, further information)
has caused the attached Bug report to be marked as done.

This means that you claim that the problem has been dealt with.
If this is not the case it is now your responsibility to reopen the
Bug report if necessary, and/or fix the problem forthwith.

(NB: If you are a system administrator and have no idea what I am
talking about this indicates a serious mail system misconfiguration
somewhere.  Please contact me immediately.)

Debian bug tracking system administrator
(administrator, Debian Bugs database)

--- Begin Message ---

• To: Debian Bug Tracking System <submit@bugs.debian.org>
• Subject: xen kernel makes dom0 slower
• From: Heiko Schulz <heiko@imng13.mathematik.uni-stuttgart.de>
• Date: Sun, 21 Jan 2007 01:32:18 +0100
• Message-id: <20070121003218.31824.51048.reportbug@imng13.mathematik.uni-stuttgart.de>

Package: linux-image-2.6.18-3-xen-amd64
Version: 2.6.18-7
Severity: important

Booting the xen linux image, the cpu performance is much slower 
than with a vanilla kernel (also 2.6.18). A simple shell script
(which compute some numbers, no I/O) needs 60 percent more cpu time
if I am using the xen kernel. No virtual machines are running.

The machine is an IBM X3550 with Dual Core Xeon 5050.
The kernel options are noapic and acpi=off. I hope, somebody have
ideas...

Heiko Schulz
 



-- System Information:
Debian Release: 4.0
Architecture: amd64 (x86_64)
Shell:  /bin/sh linked to /bin/bash
Kernel: Linux 2.6.18.3-k8-smp
Locale: LANG=C, LC_CTYPE=C (charmap=ISO-8859-15) (ignored: LC_ALL set to de_DE@euro)

--- End Message ---

--- Begin Message ---

• To: 407757-done@bugs.debian.org
• Subject: Re: Bug#407757: Info received (Bug#407757: xen kernel makes dom0 slower, further information)
• From: maximilian attems <max@stro.at>
• Date: Thu, 2 Aug 2007 17:51:39 +0200
• Message-id: <20070802155139.GG9582@stro.at>
• In-reply-to: <20070314145229.GA18014@wavehammer.waldi.eu.org>
• References: <20070123141850.GA27060@mathematik.uni-stuttgart.de> <20070121003218.31824.51048.reportbug@imng13.mathematik.uni-stuttgart.de> <handler.407757.B407757.116956193622442.ackinfo@bugs.debian.org> <20070314125921.GA20741@mathematik.uni-stuttgart.de> <20070314145229.GA18014@wavehammer.waldi.eu.org>

On Wed, 14 Mar 2007, Bastian Blank wrote:

> On Wed, Mar 14, 2007 at 01:59:21PM +0100, Heiko Schulz wrote:
> > which information is still needed? The problem also occurs with
> > linux-image-2.6.18-4-xen-amd64.
> 
> It does not appear here:
> athlon 3200+, 2.6.18-3-xen-vsever-amd64:
> bash test.sh 3000000  70,14s user 6,59s system 99% cpu 1:17,27 total
> core duo L2400, 2.6.18-4-vserver-686:
> bash test.sh 3000000  101,83s user 2,10s system 99% cpu 1:44,10 total
> opteron 270, 2.6.20:
> bash test.sh 3000000  80,49s user 2,94s system 99% cpu 1:23,76 total
> 
> Nothings shows the 60% more cpu time you've reported.

closing as bug could not be reproduced.

regards

-- 
maks

--- End Message ---