<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html; charset=windows-1252"
http-equiv="Content-Type">
</head>
<body bgcolor="#ffffff" text="#000000">
Walt,<br>
<br>
The performance regression you're seeing is possibly fixed in the
trunk now (not synced yet).<br>
Look for the following commit:<br>
<span class="Apple-style-span" style="border-collapse: separate;
color: rgb(0, 0, 0); font-family: 'Times New Roman'; font-style:
normal; font-variant: normal; font-weight: normal; letter-spacing:
normal; line-height: normal; orphans: 2; text-indent: 0px;
text-transform: none; white-space: normal; widows: 2;
word-spacing: 0px; font-size: medium;"><span
class="Apple-style-span" style="font-family:
Verdana,Arial,'Bitstream Vera Sans',Helvetica,sans-serif;
font-size: 13px; line-height: 16px;"><a class="missing wiki"
href="http://linserv.germany.sun.com/vbox/wiki/SyncPageWorkerTrackDeref"
rel="nofollow" style="text-decoration: none; color: rgb(153,
153, 136); border-bottom: 1px dotted rgb(187, 187, 187);">
SyncPageWorkerTrackDeref</a>: Use the hint we retrieved from
the cached dirty guest PT.<br>
Do not reset the modifications counter in<span
class="Apple-converted-space"> </span><a class="missing wiki"
href="http://linserv.germany.sun.com/vbox/wiki/InvalidatePage"
rel="nofollow" style="text-decoration: none; color: rgb(153,
153, 136); border-bottom: 1px dotted rgb(187, 187, 187);">InvalidatePage</a>.<br>
<br>
Sander<br>
<br>
<br>
</span></span>On 9/14/2010 12:00 AM, walt wrote:
<blockquote cite="mid:i6m6td$ess$1@dough.gmane.org" type="cite">On
09/13/2010 12:31 PM, Frank Mehnert wrote:
<br>
<blockquote type="cite">On Monday 13 September 2010, walt wrote:
<br>
<blockquote type="cite">On 09/13/2010 05:49 AM, Frank Mehnert
wrote:
<br>
<blockquote type="cite">On Sunday 12 September 2010, walt
wrote:
<br>
<blockquote type="cite">I'm using the latest OSE.svn, and
I'm seeing Windows 7 guests running at
<br>
one-third the usual speed (linux host).
<br>
</blockquote>
<br>
We also had a check of the time which is used for a Windows
7
<br>
installation and were not able to observe any differences
between 3.2.8
<br>
and current trunk. We tested this on an Intel Xeon E5345 (2
x 4 cores) on
<br>
Windows Server 2008.
<br>
</blockquote>
<br>
I found the guilty commit:
<br>
<br>
------------------------------------------------------------------------
<br>
r32410 | vboxsync | 2010-09-10 07:19:33 -0700 (Fri, 10 Sep
2010) | 2 lines
<br>
<br>
Got rid of unnecessary dirty page flush in InvalidatePage.
(NOTE: high risk
<br>
change)
<br>
------------------------------------------------------------------------
<br>
</blockquote>
</blockquote>
<br>
<blockquote type="cite">Thanks for this information! Does your
host have an Intel CPU or an AMD CPU?
<br>
</blockquote>
<br>
AMD Athlon(tm) 64 X2 Dual Core Processor 4200+
<br>
<br>
I've found an obvious bug in git-svn during this whole process,
and I'd like
<br>
to file a helpful bug report. If you can spare a minute or two to
give me
<br>
your educated guess about it, I'd be very grateful.
<br>
<br>
The clone I made of your svn repo using git-svn won't compile, and
to me the
<br>
error message doesn't make any sense:
<br>
<br>
kBuild: Compiling RuntimeR3 -
/U/wa1ter/src/vbox.git/src/VBox/Runtime/common/misc/buildconfig.cpp
<br>
/U/wa1ter/src/vbox.git/src/VBox/Runtime/common/misc/buildconfig.cpp:
In function ‘uint32_t RTBldCfgRevision()’:
<br>
/U/wa1ter/src/vbox.git/src/VBox/Runtime/common/misc/buildconfig.cpp:39:
error: ‘ev’ was not declared in this scope
<br>
<br>
The source file is identical between your svn repo and my git-svn
repo, so it
<br>
seems git-svn has messed up some other file(s) somewhere.
<br>
<br>
Any wild guesses about where I should look in my git-svn repo to
find the real
<br>
source of the breakage?
<br>
<br>
Many thanks for your help!
<br>
<br>
<br>
<br>
_______________________________________________
<br>
vbox-dev mailing list
<br>
<a class="moz-txt-link-abbreviated" href="mailto:vbox-dev@virtualbox.org">vbox-dev@virtualbox.org</a>
<br>
<a class="moz-txt-link-freetext" href="http://vbox.innotek.de/mailman/listinfo/vbox-dev">http://vbox.innotek.de/mailman/listinfo/vbox-dev</a>
<br>
</blockquote>
<br>
<br>
<div class="moz-signature">-- <br>
Kind regards / Mit freundlichen Gruessen / Met vriendelijke groet<br>
<br>
--<br>
Sander van Leeuwen | Senior Staff Engineer, VirtualBox<br>
Oracle Virtualization<br>
<br>
ORACLE Deutschland B.V. & Co. KG | Werkstrasse 24 | 71384
Weinstadt<br>
<br>
ORACLE Deutschland B.V. & Co. KG<br>
Hauptverwaltung: Riesstr. 25, D-80992 München<br>
Registergericht: Amtsgericht München, HRA 95603<br>
<br>
Komplementärin: ORACLE Deutschland Verwaltung B.V.<br>
Rijnzathe 6, 3454PV De Meern, Niederlande<br>
Handelsregister der Handelskammer Midden-Niederlande, Nr. 30143697<br>
Geschäftsführer: Jürgen Kunz, Marcel van de Molen, Alexander van
der Ven<br>
</div>
</body>
</html>