From: "Michael S. Tsirkin" <mst@redhat.com>
To: qemu-devel@nongnu.org, kvm@vger.kernel.org, pbonzini@redhat.com,
gleb@redhat.com, mtosatti@redhat.com
Subject: [PATCH 0/4] kvm-unittests: add pci PORT IO and MMIO speed tests
Date: Wed, 3 Apr 2013 11:59:27 +0300 [thread overview]
Message-ID: <cover.1364979441.git.mst@redhat.com> (raw)
These patches add a test device, useful to measure speed of MMIO versus PIO, in
different configurations. As I didn't want to reserve a hardcoded range
of memory, I added pci device for this instead. Used together with the
kvm unittest patches I posted on kvm mailing list.
To use, simply add the device on the pci bus.
Example test output:
mmio-no-eventfd:pci-mem 8796
mmio-wildcard-eventfd:pci-mem 3609
mmio-datamatch-eventfd:pci-mem 3685
portio-no-eventfd:pci-io 5287
portio-wildcard-eventfd:pci-io 1762
portio-datamatch-eventfd:pci-io 1777
First interesting conclusion is that the overhead of MMIO
exit to QEMU as compared to PIO is double that of
MMIO ioeventfd as compared to PIO eventfd. Is this a known fact?
I also had to extend kvm in a minor way, making all ioeventfd
options accessible through the API. This actually needs less code
than checking that users DTRT.
What's the best way to merge this patchset?
I'm guessing the kvm tree ...
Michael S. Tsirkin (4):
kvm: remove unused APIs
kvm: support any size for pio eventfd
kvm: support non datamatch ioeventfd
pci: add pci test device
hw/i386/Makefile.objs | 2 +-
hw/pci-testdev.c | 306 ++++++++++++++++++++++++++++++++++++++++++++++++++
hw/pci/pci.h | 1 +
include/sysemu/kvm.h | 4 -
kvm-all.c | 133 +++++++++++-----------
kvm-stub.c | 10 --
6 files changed, 376 insertions(+), 80 deletions(-)
create mode 100644 hw/pci-testdev.c
--
MST
next reply other threads:[~2013-04-03 8:58 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-03 8:59 Michael S. Tsirkin [this message]
2013-04-03 8:59 ` [PATCH 1/4] kvm: remove unused APIs Michael S. Tsirkin
2013-04-03 8:59 ` [PATCH 2/4] kvm: support any size for pio eventfd Michael S. Tsirkin
2013-04-03 8:59 ` [PATCH 3/4] kvm: support non datamatch ioeventfd Michael S. Tsirkin
2013-04-03 8:59 ` [PATCH 4/4] pci: add pci test device Michael S. Tsirkin
2013-04-03 9:28 ` Paolo Bonzini
2013-04-03 9:45 ` Michael S. Tsirkin
2013-04-03 9:53 ` Paolo Bonzini
2013-04-03 10:22 ` Michael S. Tsirkin
2013-04-03 10:25 ` Paolo Bonzini
2013-04-03 10:33 ` Michael S. Tsirkin
2013-04-03 10:34 ` Paolo Bonzini
2013-04-03 10:38 ` Michael S. Tsirkin
2013-04-03 11:48 ` Paolo Bonzini
2013-04-03 12:00 ` Michael S. Tsirkin
2013-04-03 12:05 ` Paolo Bonzini
2013-04-03 14:06 ` Michael S. Tsirkin
2013-04-03 14:08 ` Paolo Bonzini
2013-04-03 14:28 ` Michael S. Tsirkin
2013-04-03 15:46 ` Paolo Bonzini
2013-04-03 17:04 ` Michael S. Tsirkin
2013-04-03 17:10 ` Paolo Bonzini
2013-04-03 14:33 ` Michael S. Tsirkin
2013-04-03 15:09 ` Michael S. Tsirkin
2013-04-03 15:43 ` Paolo Bonzini
2013-04-03 18:39 ` Michael S. Tsirkin
2013-04-03 19:59 ` Paolo Bonzini
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=cover.1364979441.git.mst@redhat.com \
--to=mst@redhat.com \
--cc=gleb@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
/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