No description
Find a file
David Hildenbrand 177f9b1ee4 virtio-mem: Expose device memory dynamically via multiple memslots if enabled
Having large virtio-mem devices that only expose little memory to a VM
is currently a problem: we map the whole sparse memory region into the
guest using a single memslot, resulting in one gigantic memslot in KVM.
KVM allocates metadata for the whole memslot, which can result in quite
some memory waste.

Assuming we have a 1 TiB virtio-mem device and only expose little (e.g.,
1 GiB) memory, we would create a single 1 TiB memslot and KVM has to
allocate metadata for that 1 TiB memslot: on x86, this implies allocating
a significant amount of memory for metadata:

(1) RMAP: 8 bytes per 4 KiB, 8 bytes per 2 MiB, 8 bytes per 1 GiB
    -> For 1 TiB: 2147483648 + 4194304 + 8192 = ~ 2 GiB (0.2 %)

    With the TDP MMU (cat /sys/module/kvm/parameters/tdp_mmu) this gets
    allocated lazily when required for nested VMs
(2) gfn_track: 2 bytes per 4 KiB
    -> For 1 TiB: 536870912 = ~512 MiB (0.05 %)
(3) lpage_info: 4 bytes per 2 MiB, 4 bytes per 1 GiB
    -> For 1 TiB: 2097152 + 4096 = ~2 MiB (0.0002 %)
(4) 2x dirty bitmaps for tracking: 2x 1 bit per 4 KiB page
    -> For 1 TiB: 536870912 = 64 MiB (0.006 %)

So we primarily care about (1) and (2). The bad thing is, that the
memory consumption *doubles* once SMM is enabled, because we create the
memslot once for !SMM and once for SMM.

Having a 1 TiB memslot without the TDP MMU consumes around:
* With SMM: 5 GiB
* Without SMM: 2.5 GiB
Having a 1 TiB memslot with the TDP MMU consumes around:
* With SMM: 1 GiB
* Without SMM: 512 MiB

... and that's really something we want to optimize, to be able to just
start a VM with small boot memory (e.g., 4 GiB) and a virtio-mem device
that can grow very large (e.g., 1 TiB).

Consequently, using multiple memslots and only mapping the memslots we
really need can significantly reduce memory waste and speed up
memslot-related operations. Let's expose the sparse RAM memory region using
multiple memslots, mapping only the memslots we currently need into our
device memory region container.

The feature can be enabled using "dynamic-memslots=on" and requires
"unplugged-inaccessible=on", which is nowadays the default.

Once enabled, we'll auto-detect the number of memslots to use based on the
memslot limit provided by the core. We'll use at most 1 memslot per
gigabyte. Note that our global limit of memslots accross all memory devices
is currently set to 256: even with multiple large virtio-mem devices,
we'd still have a sane limit on the number of memslots used.

The default is to not dynamically map memslot for now
("dynamic-memslots=off"). The optimization must be enabled manually,
because some vhost setups (e.g., hotplug of vhost-user devices) might be
problematic until we support more memslots especially in vhost-user backends.

Note that "dynamic-memslots=on" is just a hint that multiple memslots
*may* be used for internal optimizations, not that multiple memslots
*must* be used. The actual number of memslots that are used is an
internal detail: for example, once memslot metadata is no longer an
issue, we could simply stop optimizing for that. Migration source and
destination can differ on the setting of "dynamic-memslots".

Message-ID: <20230926185738.277351-17-david@redhat.com>
Reviewed-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
2023-10-12 14:15:22 +02:00
.github/workflows
.gitlab/issue_templates
.gitlab-ci.d
accel kvm: Add stub for kvm_get_max_memslots() 2023-10-12 14:15:22 +02:00
audio
authz
backends
block
bsd-user
chardev
common-user
configs
contrib
crypto
disas
docs
dump
ebpf
fpu
fsdev
gdb-xml
gdbstub
host/include
hw virtio-mem: Expose device memory dynamically via multiple memslots if enabled 2023-10-12 14:15:22 +02:00
include virtio-mem: Expose device memory dynamically via multiple memslots if enabled 2023-10-12 14:15:22 +02:00
io
libdecnumber
linux-headers
linux-user
migration
monitor
nbd
net
pc-bios
plugins
po
python
qapi
qga
qobject
qom
replay
roms
scripts
scsi
semihosting
stats
storage-daemon
stubs memory-device,vhost: Support automatic decision on the number of memslots 2023-10-12 14:15:22 +02:00
subprojects
system memory: Clarify mapping requirements for RamDiscardManager 2023-10-12 14:15:22 +02:00
target
tcg
tests testing, gdbstub and plugin updates 2023-10-11 09:43:10 -04:00
tools
trace
ui
util
.dir-locals.el
.editorconfig
.exrc
.gdbinit
.git-blame-ignore-revs
.gitattributes
.gitignore
.gitlab-ci.yml
.gitmodules
.gitpublish
.mailmap
.patchew.yml
.readthedocs.yml
.travis.yml
block.c
blockdev-nbd.c
blockdev.c
blockjob.c
configure
COPYING
COPYING.LIB
cpu-common.c
cpu-target.c
event-loop-base.c
gitdm.config
hmp-commands-info.hx
hmp-commands.hx
iothread.c
job-qmp.c
job.c
Kconfig
Kconfig.host
LICENSE
MAINTAINERS stubs: Rename qmp_memory_device.c to memory_device.c 2023-10-12 14:15:22 +02:00
Makefile
memory_ldst.c.inc
meson.build
meson_options.txt
module-common.c
os-posix.c
os-win32.c
page-vary-common.c
page-vary-target.c
pythondeps.toml
qemu-bridge-helper.c
qemu-edid.c
qemu-img-cmds.hx
qemu-img.c
qemu-io-cmds.c
qemu-io.c
qemu-keymap.c
qemu-nbd.c
qemu-options.hx
qemu.nsi
qemu.sasl
README.rst
replication.c
trace-events
VERSION
version.rc

===========
QEMU README
===========

QEMU is a generic and open source machine & userspace emulator and
virtualizer.

QEMU is capable of emulating a complete machine in software without any
need for hardware virtualization support. By using dynamic translation,
it achieves very good performance. QEMU can also integrate with the Xen
and KVM hypervisors to provide emulated hardware while allowing the
hypervisor to manage the CPU. With hypervisor support, QEMU can achieve
near native performance for CPUs. When QEMU emulates CPUs directly it is
capable of running operating systems made for one machine (e.g. an ARMv7
board) on a different machine (e.g. an x86_64 PC board).

QEMU is also capable of providing userspace API virtualization for Linux
and BSD kernel interfaces. This allows binaries compiled against one
architecture ABI (e.g. the Linux PPC64 ABI) to be run on a host using a
different architecture ABI (e.g. the Linux x86_64 ABI). This does not
involve any hardware emulation, simply CPU and syscall emulation.

QEMU aims to fit into a variety of use cases. It can be invoked directly
by users wishing to have full control over its behaviour and settings.
It also aims to facilitate integration into higher level management
layers, by providing a stable command line interface and monitor API.
It is commonly invoked indirectly via the libvirt library when using
open source applications such as oVirt, OpenStack and virt-manager.

QEMU as a whole is released under the GNU General Public License,
version 2. For full licensing details, consult the LICENSE file.


Documentation
=============

Documentation can be found hosted online at
`<https://www.qemu.org/documentation/>`_. The documentation for the
current development version that is available at
`<https://www.qemu.org/docs/master/>`_ is generated from the ``docs/``
folder in the source tree, and is built by `Sphinx
<https://www.sphinx-doc.org/en/master/>`_.


Building
========

QEMU is multi-platform software intended to be buildable on all modern
Linux platforms, OS-X, Win32 (via the Mingw64 toolchain) and a variety
of other UNIX targets. The simple steps to build QEMU are:


.. code-block:: shell

  mkdir build
  cd build
  ../configure
  make

Additional information can also be found online via the QEMU website:

* `<https://wiki.qemu.org/Hosts/Linux>`_
* `<https://wiki.qemu.org/Hosts/Mac>`_
* `<https://wiki.qemu.org/Hosts/W32>`_


Submitting patches
==================

The QEMU source code is maintained under the GIT version control system.

.. code-block:: shell

   git clone https://gitlab.com/qemu-project/qemu.git

When submitting patches, one common approach is to use 'git
format-patch' and/or 'git send-email' to format & send the mail to the
qemu-devel@nongnu.org mailing list. All patches submitted must contain
a 'Signed-off-by' line from the author. Patches should follow the
guidelines set out in the `style section
<https://www.qemu.org/docs/master/devel/style.html>`_ of
the Developers Guide.

Additional information on submitting patches can be found online via
the QEMU website

* `<https://wiki.qemu.org/Contribute/SubmitAPatch>`_
* `<https://wiki.qemu.org/Contribute/TrivialPatches>`_

The QEMU website is also maintained under source control.

.. code-block:: shell

  git clone https://gitlab.com/qemu-project/qemu-web.git

* `<https://www.qemu.org/2017/02/04/the-new-qemu-website-is-up/>`_

A 'git-publish' utility was created to make above process less
cumbersome, and is highly recommended for making regular contributions,
or even just for sending consecutive patch series revisions. It also
requires a working 'git send-email' setup, and by default doesn't
automate everything, so you may want to go through the above steps
manually for once.

For installation instructions, please go to

*  `<https://github.com/stefanha/git-publish>`_

The workflow with 'git-publish' is:

.. code-block:: shell

  $ git checkout master -b my-feature
  $ # work on new commits, add your 'Signed-off-by' lines to each
  $ git publish

Your patch series will be sent and tagged as my-feature-v1 if you need to refer
back to it in the future.

Sending v2:

.. code-block:: shell

  $ git checkout my-feature # same topic branch
  $ # making changes to the commits (using 'git rebase', for example)
  $ git publish

Your patch series will be sent with 'v2' tag in the subject and the git tip
will be tagged as my-feature-v2.

Bug reporting
=============

The QEMU project uses GitLab issues to track bugs. Bugs
found when running code built from QEMU git or upstream released sources
should be reported via:

* `<https://gitlab.com/qemu-project/qemu/-/issues>`_

If using QEMU via an operating system vendor pre-built binary package, it
is preferable to report bugs to the vendor's own bug tracker first. If
the bug is also known to affect latest upstream code, it can also be
reported via GitLab.

For additional information on bug reporting consult:

* `<https://wiki.qemu.org/Contribute/ReportABug>`_


ChangeLog
=========

For version history and release notes, please visit
`<https://wiki.qemu.org/ChangeLog/>`_ or look at the git history for
more detailed information.


Contact
=======

The QEMU community can be contacted in a number of ways, with the two
main methods being email and IRC

* `<mailto:qemu-devel@nongnu.org>`_
* `<https://lists.nongnu.org/mailman/listinfo/qemu-devel>`_
* #qemu on irc.oftc.net

Information on additional methods of contacting the community can be
found online via the QEMU website:

* `<https://wiki.qemu.org/Contribute/StartHere>`_