From: Juergen Gross <juergen.gross@ts.fujitsu.com>
To: "xen-devel@lists.xensource.com" <xen-devel@lists.xensource.com>
Subject: Performance difference between Xen versions
Date: Fri, 29 Apr 2011 14:32:49 +0200 [thread overview]
Message-ID: <4DBAAFF1.8080001@ts.fujitsu.com> (raw)
Hi,
comparing performance of different Xen versions with BS2000 as HVM guest
showed some weird data I'd like to understand.
All measurements were done on an Intel Xeon E7220 box. We used a disk-
benchmark and found the cpu utilization was much higher with Xen 4.0 compared
to Xen 3.3. I did some more investigation and narrowed things down to calls of
the hypervisor (implicit or explicit).
Following is a table with timing data for different low-level functions, all
timing values are tsc ticks obtained via rdtsc:
Xen 3.3 Xen 4.0 Function
88 165 just the measurement overhead
176 330 rdtsc-instruction + cli/sti
5896 11044 lapic timer query
7381 13519 setting lapic timer
4653 8987 reload of cr3
3124 5709 invlpg instruction
792253 792264 wbinvd instruction
748 1375 int + iret
5203 9317 hypervisor yield call
12598102 12597882 memory access loop
All operations involving the hypervisor take nearly twice the time on 4.0.
Operations not involving the hypervisor (wbinvd and memory access loop) are
the same on both systems (this rules out the possibility of different rdtsc
behavior).
Is there any easy explanation for this? Both Xen versions are from SLES
(SLES11 or SLES11 SP1).
Juergen
--
Juergen Gross Principal Developer Operating Systems
TSP ES&S SWE OS6 Telephone: +49 (0) 89 3222 2967
Fujitsu Technology Solutions e-mail: juergen.gross@ts.fujitsu.com
Domagkstr. 28 Internet: ts.fujitsu.com
D-80807 Muenchen Company details: ts.fujitsu.com/imprint.html
next reply other threads:[~2011-04-29 12:32 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-04-29 12:32 Juergen Gross [this message]
2011-04-29 13:28 ` Performance difference between Xen versions Keir Fraser
2011-04-29 13:35 ` Juergen Gross
2011-04-29 14:58 ` Keir Fraser
2011-04-29 16:10 ` Jan Beulich
2011-05-02 5:31 ` Juergen Gross
2011-05-02 6:41 ` Keir Fraser
2011-05-02 7:23 ` Jan Beulich
2011-05-02 8:00 ` Juergen Gross
2011-05-02 8:15 ` Jan Beulich
2011-05-02 8:23 ` Juergen Gross
2011-05-02 8:49 ` Keir Fraser
2011-05-03 3:06 ` Tian, Kevin
2011-05-06 13:49 ` Juergen Gross
2011-05-06 14:27 ` Jan Beulich
2011-05-11 6:08 ` Tian, Kevin
2011-05-11 6:23 ` Juergen Gross
2011-05-02 17:52 ` John Weekes
2011-05-02 18:12 ` Konrad Rzeszutek Wilk
2011-05-02 18:43 ` John Weekes
2011-05-02 19:16 ` John Weekes
2011-05-02 19:36 ` Konrad Rzeszutek Wilk
2011-05-02 19:54 ` John Weekes
2011-05-03 2:16 ` Tian, Kevin
2011-05-03 3:04 ` Tian, Kevin
2011-05-03 3:39 ` John Weekes
2011-05-03 7:23 ` Tian, Kevin
[not found] ` <4DBF13BB.3000309@nuclearfallout.net>
2011-05-03 7:23 ` Jan Beulich
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=4DBAAFF1.8080001@ts.fujitsu.com \
--to=juergen.gross@ts.fujitsu.com \
--cc=xen-devel@lists.xensource.com \
/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).