kubespray/roles/container-engine/kata-containers/templates/configuration-qemu.toml.j2

# Copyright (c) 2017-2019 Intel Corporation
#
# SPDX-License-Identifier: Apache-2.0
#

# XXX: WARNING: this file is auto-generated.
# XXX:
# XXX: Source file: "cli/config/configuration-qemu.toml.in"
# XXX: Project:
# XXX:   Name: Kata Containers
# XXX:   Type: kata

[hypervisor.qemu]
path = "/opt/kata/bin/qemu-system-x86_64"
{% if kata_containers_version is version('2.2.0', '>=') %}
kernel = "/opt/kata/share/kata-containers/vmlinux.container"
{% else %}
kernel = "/opt/kata/share/kata-containers/vmlinuz.container"
{% endif %}
image = "/opt/kata/share/kata-containers/kata-containers.img"
machine_type = "q35"

# Enable confidential guest support.
# Toggling that setting may trigger different hardware features, ranging
# from memory encryption to both memory and CPU-state encryption and integrity.
# The Kata Containers runtime dynamically detects the available feature set and
# aims at enabling the largest possible one.
# Default false
# confidential_guest = true

# List of valid annotation names for the hypervisor
# Each member of the list is a regular expression, which is the base name
# of the annotation, e.g. "path" for io.katacontainers.config.hypervisor.path"
enable_annotations = []

# List of valid annotations values for the hypervisor
# Each member of the list is a path pattern as described by glob(3).
# The default if not set is empty (all annotations rejected.)
# Your distribution recommends: ["/opt/kata/bin/qemu-system-x86_64"]
valid_hypervisor_paths = ["/opt/kata/bin/qemu-system-x86_64"]

# Optional space-separated list of options to pass to the guest kernel.
# For example, use `kernel_params = "vsyscall=emulate"` if you are having
# trouble running pre-2.15 glibc.
#
# WARNING: - any parameter specified here will take priority over the default
# parameter value of the same name used to start the virtual machine.
# Do not set values here unless you understand the impact of doing so as you
# may stop the virtual machine from booting.
# To see the list of default parameters, enable hypervisor debug, create a
# container and look for 'default-kernel-parameters' log entries.
kernel_params = ""

# Path to the firmware.
# If you want that qemu uses the default firmware leave this option empty
firmware = ""

# Machine accelerators
# comma-separated list of machine accelerators to pass to the hypervisor.
# For example, `machine_accelerators = "nosmm,nosmbus,nosata,nopit,static-prt,nofw"`
machine_accelerators=""

# CPU features
# comma-separated list of cpu features to pass to the cpu
# For example, `cpu_features = "pmu=off,vmx=off"
cpu_features="pmu=off"

# Default number of vCPUs per SB/VM:
# unspecified or 0                --> will be set to 1
# < 0                             --> will be set to the actual number of physical cores
# > 0 <= number of physical cores --> will be set to the specified number
# > number of physical cores      --> will be set to the actual number of physical cores
default_vcpus = 1

# Default maximum number of vCPUs per SB/VM:
# unspecified or == 0             --> will be set to the actual number of physical cores or to the maximum number
#                                     of vCPUs supported by KVM if that number is exceeded
# > 0 <= number of physical cores --> will be set to the specified number
# > number of physical cores      --> will be set to the actual number of physical cores or to the maximum number
#                                     of vCPUs supported by KVM if that number is exceeded
# WARNING: Depending of the architecture, the maximum number of vCPUs supported by KVM is used when
# the actual number of physical cores is greater than it.
# WARNING: Be aware that this value impacts the virtual machine's memory footprint and CPU
# the hotplug functionality. For example, `default_maxvcpus = 240` specifies that until 240 vCPUs
# can be added to a SB/VM, but the memory footprint will be big. Another example, with
# `default_maxvcpus = 8` the memory footprint will be small, but 8 will be the maximum number of
# vCPUs supported by the SB/VM. In general, we recommend that you do not edit this variable,
# unless you know what are you doing.
# NOTICE: on arm platform with gicv2 interrupt controller, set it to 8.
default_maxvcpus = 0

# Bridges can be used to hot plug devices.
# Limitations:
# * Currently only pci bridges are supported
# * Until 30 devices per bridge can be hot plugged.
# * Until 5 PCI bridges can be cold plugged per VM.
#   This limitation could be a bug in qemu or in the kernel
# Default number of bridges per SB/VM:
# unspecified or 0   --> will be set to 1
# > 1 <= 5           --> will be set to the specified number
# > 5                --> will be set to 5
default_bridges = 1

# Default memory size in MiB for SB/VM.
# If unspecified then it will be set 2048 MiB.
default_memory = {{ kata_containers_qemu_default_memory }}
#
# Default memory slots per SB/VM.
# If unspecified then it will be set 10.
# This is will determine the times that memory will be hotadded to sandbox/VM.
#memory_slots = 10

# The size in MiB will be plused to max memory of hypervisor.
# It is the memory address space for the NVDIMM devie.
# If set block storage driver (block_device_driver) to "nvdimm",
# should set memory_offset to the size of block device.
# Default 0
#memory_offset = 0

# Specifies virtio-mem will be enabled or not.
# Please note that this option should be used with the command
# "echo 1 > /proc/sys/vm/overcommit_memory".
# Default false
#enable_virtio_mem = true

# Disable block device from being used for a container's rootfs.
# In case of a storage driver like devicemapper where a container's
# root file system is backed by a block device, the block device is passed
# directly to the hypervisor for performance reasons.
# This flag prevents the block device from being passed to the hypervisor,
# 9pfs is used instead to pass the rootfs.
disable_block_device_use = false

# Shared file system type:
#   - virtio-fs (default)
#   - virtio-9p
{% if kata_containers_version is version('2.2.0', '>=') %}
shared_fs = "virtio-fs"
{% else %}
shared_fs = "virtio-9p"
{% endif %}

# Path to vhost-user-fs daemon.
virtio_fs_daemon = "/opt/kata/libexec/kata-qemu/virtiofsd"

# List of valid annotations values for the virtiofs daemon
# The default if not set is empty (all annotations rejected.)
# Your distribution recommends: ["/opt/kata/libexec/kata-qemu/virtiofsd"]
valid_virtio_fs_daemon_paths = ["/opt/kata/libexec/kata-qemu/virtiofsd"]

# Default size of DAX cache in MiB
virtio_fs_cache_size = 0

# Extra args for virtiofsd daemon
#
# Format example:
#   ["-o", "arg1=xxx,arg2", "-o", "hello world", "--arg3=yyy"]
#
# see `virtiofsd -h` for possible options.
virtio_fs_extra_args = ["--thread-pool-size=1"]

# Cache mode:
#
#  - none
#    Metadata, data, and pathname lookup are not cached in guest. They are
#    always fetched from host and any changes are immediately pushed to host.
#
#  - auto
#    Metadata and pathname lookup cache expires after a configured amount of
#    time (default is 1 second). Data is cached while the file is open (close
#    to open consistency).
#
#  - always
#    Metadata, data, and pathname lookup are cached in guest and never expire.
virtio_fs_cache = "always"

# Block storage driver to be used for the hypervisor in case the container
# rootfs is backed by a block device. This is virtio-scsi, virtio-blk
# or nvdimm.
block_device_driver = "virtio-scsi"

# Specifies cache-related options will be set to block devices or not.
# Default false
#block_device_cache_set = true

# Specifies cache-related options for block devices.
# Denotes whether use of O_DIRECT (bypass the host page cache) is enabled.
# Default false
#block_device_cache_direct = true

# Specifies cache-related options for block devices.
# Denotes whether flush requests for the device are ignored.
# Default false
#block_device_cache_noflush = true

# Enable iothreads (data-plane) to be used. This causes IO to be
# handled in a separate IO thread. This is currently only implemented
# for SCSI.
#
enable_iothreads = false

# Enable pre allocation of VM RAM, default false
# Enabling this will result in lower container density
# as all of the memory will be allocated and locked
# This is useful when you want to reserve all the memory
# upfront or in the cases where you want memory latencies
# to be very predictable
# Default false
enable_mem_prealloc = {{ kata_containers_qemu_enable_mem_prealloc }}

# Enable huge pages for VM RAM, default false
# Enabling this will result in the VM memory
# being allocated using huge pages.
# This is useful when you want to use vhost-user network
# stacks within the container. This will automatically
# result in memory pre allocation
#enable_hugepages = true

# Enable vhost-user storage device, default false
# Enabling this will result in some Linux reserved block type
# major range 240-254 being chosen to represent vhost-user devices.
enable_vhost_user_store = false

# The base directory specifically used for vhost-user devices.
# Its sub-path "block" is used for block devices; "block/sockets" is
# where we expect vhost-user sockets to live; "block/devices" is where
# simulated block device nodes for vhost-user devices to live.
vhost_user_store_path = "/var/run/kata-containers/vhost-user"

# Enable vIOMMU, default false
# Enabling this will result in the VM having a vIOMMU device
# This will also add the following options to the kernel's
# command line: intel_iommu=on,iommu=pt
#enable_iommu = true

# Enable IOMMU_PLATFORM, default false
# Enabling this will result in the VM device having iommu_platform=on set
#enable_iommu_platform = true

# List of valid annotations values for the vhost user store path
# The default if not set is empty (all annotations rejected.)
# Your distribution recommends: ["/var/run/kata-containers/vhost-user"]
valid_vhost_user_store_paths = ["/var/run/kata-containers/vhost-user"]

# Enable file based guest memory support. The default is an empty string which
# will disable this feature. In the case of virtio-fs, this is enabled
# automatically and '/dev/shm' is used as the backing folder.
# This option will be ignored if VM templating is enabled.
#file_mem_backend = ""

# List of valid annotations values for the file_mem_backend annotation
# The default if not set is empty (all annotations rejected.)
# Your distribution recommends: [""]
valid_file_mem_backends = [""]

# Enable swap of vm memory. Default false.
# The behaviour is undefined if mem_prealloc is also set to true
#enable_swap = true

# -pflash can add image file to VM. The arguments of it should be in format
# of ["/path/to/flash0.img", "/path/to/flash1.img"]
pflashes = []

# This option changes the default hypervisor and kernel parameters
# to enable debug output where available. This extra output is added
# to the proxy logs, but only when proxy debug is also enabled.
#
# Default false
enable_debug = {{ kata_containers_qemu_debug }}

# Disable the customizations done in the runtime when it detects
# that it is running on top a VMM. This will result in the runtime
# behaving as it would when running on bare metal.
#
#disable_nesting_checks = true

# This is the msize used for 9p shares. It is the number of bytes
# used for 9p packet payload.
#msize_9p = 8192

# If true and vsocks are supported, use vsocks to communicate directly
# with the agent and no proxy is started, otherwise use unix
# sockets and start a proxy to communicate with the agent.
# Default false
#use_vsock = true

# If false and nvdimm is supported, use nvdimm device to plug guest image.
# Otherwise virtio-block device is used.
# Default is false
#disable_image_nvdimm = true

# VFIO devices are hotplugged on a bridge by default.
# Enable hotplugging on root bus. This may be required for devices with
# a large PCI bar, as this is a current limitation with hotplugging on
# a bridge. This value is valid for "pc" machine type.
# Default false
#hotplug_vfio_on_root_bus = true

# Before hot plugging a PCIe device, you need to add a pcie_root_port device.
# Use this parameter when using some large PCI bar devices, such as Nvidia GPU
# The value means the number of pcie_root_port
# This value is valid when hotplug_vfio_on_root_bus is true and machine_type is "q35"
# Default 0
#pcie_root_port = 2

# If vhost-net backend for virtio-net is not desired, set to true. Default is false, which trades off
# security (vhost-net runs ring0) for network I/O performance.
#disable_vhost_net = true

#
# Default entropy source.
# The path to a host source of entropy (including a real hardware RNG)
# /dev/urandom and /dev/random are two main options.
# Be aware that /dev/random is a blocking source of entropy.  If the host
# runs out of entropy, the VMs boot time will increase leading to get startup
# timeouts.
# The source of entropy /dev/urandom is non-blocking and provides a
# generally acceptable source of entropy. It should work well for pretty much
# all practical purposes.
#entropy_source= "/dev/urandom"

# List of valid annotations values for entropy_source
# The default if not set is empty (all annotations rejected.)
# Your distribution recommends: ["/dev/urandom","/dev/random",""]
valid_entropy_sources = ["/dev/urandom","/dev/random",""]

# Path to OCI hook binaries in the *guest rootfs*.
# This does not affect host-side hooks which must instead be added to
# the OCI spec passed to the runtime.
#
# You can create a rootfs with hooks by customizing the osbuilder scripts:
# https://github.com/kata-containers/osbuilder
#
# Hooks must be stored in a subdirectory of guest_hook_path according to their
# hook type, i.e. "guest_hook_path/{prestart,postart,poststop}".
# The agent will scan these directories for executable files and add them, in
# lexicographical order, to the lifecycle of the guest container.
# Hooks are executed in the runtime namespace of the guest. See the official documentation:
# https://github.com/opencontainers/runtime-spec/blob/v1.0.1/config.md#posix-platform-hooks
# Warnings will be logged if any error is encountered will scanning for hooks,
# but it will not abort container execution.
#guest_hook_path = "/usr/share/oci/hooks"
#
# Use rx Rate Limiter to control network I/O inbound bandwidth(size in bits/sec for SB/VM).
# In Qemu, we use classful qdiscs HTB(Hierarchy Token Bucket) to discipline traffic.
# Default 0-sized value means unlimited rate.
#rx_rate_limiter_max_rate = 0
# Use tx Rate Limiter to control network I/O outbound bandwidth(size in bits/sec for SB/VM).
# In Qemu, we use classful qdiscs HTB(Hierarchy Token Bucket) and ifb(Intermediate Functional Block)
# to discipline traffic.
# Default 0-sized value means unlimited rate.
#tx_rate_limiter_max_rate = 0

# Set where to save the guest memory dump file.
# If set, when GUEST_PANICKED event occurred,
# guest memeory will be dumped to host filesystem under guest_memory_dump_path,
# This directory will be created automatically if it does not exist.
#
# The dumped file(also called vmcore) can be processed with crash or gdb.
#
# WARNING:
#   Dump guest’s memory can take very long depending on the amount of guest memory
#   and use much disk space.
#guest_memory_dump_path="/var/crash/kata"

# If enable paging.
# Basically, if you want to use "gdb" rather than "crash",
# or need the guest-virtual addresses in the ELF vmcore,
# then you should enable paging.
#
# See: https://www.qemu.org/docs/master/qemu-qmp-ref.html#Dump-guest-memory for details
#guest_memory_dump_paging=false

# Enable swap in the guest. Default false.
# When enable_guest_swap is enabled, insert a raw file to the guest as the swap device
# if the swappiness of a container (set by annotation "io.katacontainers.container.resource.swappiness")
# is bigger than 0.
# The size of the swap device should be 
# swap_in_bytes (set by annotation "io.katacontainers.container.resource.swap_in_bytes") - memory_limit_in_bytes.
# If swap_in_bytes is not set, the size should be memory_limit_in_bytes.
# If swap_in_bytes and memory_limit_in_bytes is not set, the size should
# be default_memory.
#enable_guest_swap = true

[factory]
# VM templating support. Once enabled, new VMs are created from template
# using vm cloning. They will share the same initial kernel, initramfs and
# agent memory by mapping it readonly. It helps speeding up new container
# creation and saves a lot of memory if there are many kata containers running
# on the same host.
#
# When disabled, new VMs are created from scratch.
#
# Note: Requires "initrd=" to be set ("image=" is not supported).
#
# Default false
#enable_template = true

# Specifies the path of template.
#
# Default "/run/vc/vm/template"
#template_path = "/run/vc/vm/template"

# The number of caches of VMCache:
# unspecified or == 0   --> VMCache is disabled
# > 0                   --> will be set to the specified number
#
# VMCache is a function that creates VMs as caches before using it.
# It helps speed up new container creation.
# The function consists of a server and some clients communicating
# through Unix socket.  The protocol is gRPC in protocols/cache/cache.proto.
# The VMCache server will create some VMs and cache them by factory cache.
# It will convert the VM to gRPC format and transport it when gets
# requestion from clients.
# Factory grpccache is the VMCache client.  It will request gRPC format
# VM and convert it back to a VM.  If VMCache function is enabled,
# kata-runtime will request VM from factory grpccache when it creates
# a new sandbox.
#
# Default 0
#vm_cache_number = 0

# Specify the address of the Unix socket that is used by VMCache.
#
# Default /var/run/kata-containers/cache.sock
#vm_cache_endpoint = "/var/run/kata-containers/cache.sock"

[proxy.kata]
path = "/opt/kata/libexec/kata-containers/kata-proxy"

# If enabled, proxy messages will be sent to the system log
# (default: disabled)
enable_debug = {{ kata_containers_qemu_debug }}

[shim.kata]
path = "/opt/kata/libexec/kata-containers/kata-shim"

# If enabled, shim messages will be sent to the system log
# (default: disabled)
enable_debug = {{ kata_containers_qemu_debug }}

# If enabled, the shim will create opentracing.io traces and spans.
# (See https://www.jaegertracing.io/docs/getting-started).
#
# Note: By default, the shim runs in a separate network namespace. Therefore,
# to allow it to send trace details to the Jaeger agent running on the host,
# it is necessary to set 'disable_new_netns=true' so that it runs in the host
# network namespace.
#
# (default: disabled)
#enable_tracing = true

[agent.kata]
# If enabled, make the agent display debug-level messages.
# (default: disabled)
enable_debug = {{ kata_containers_qemu_debug }}

# Enable agent tracing.
#
# If enabled, the default trace mode is "dynamic" and the
# default trace type is "isolated". The trace mode and type are set
# explicity with the `trace_type=` and `trace_mode=` options.
#
# Notes:
#
# - Tracing is ONLY enabled when `enable_tracing` is set: explicitly
#   setting `trace_mode=` and/or `trace_type=` without setting `enable_tracing`
#   will NOT activate agent tracing.
#
# - See https://github.com/kata-containers/agent/blob/master/TRACING.md for
#   full details.
#
# (default: disabled)
#enable_tracing = true
#
#trace_mode = "dynamic"
#trace_type = "isolated"

# Comma separated list of kernel modules and their parameters.
# These modules will be loaded in the guest kernel using modprobe(8).
# The following example can be used to load two kernel modules with parameters
#  - kernel_modules=["e1000e InterruptThrottleRate=3000,3000,3000 EEE=1", "i915 enable_ppgtt=0"]
# The first word is considered as the module name and the rest as its parameters.
# Container will not be started when:
#  * A kernel module is specified and the modprobe command is not installed in the guest
#    or it fails loading the module.
#  * The module is not available in the guest or it doesn't met the guest kernel
#    requirements, like architecture and version.
#
kernel_modules=[]

# Enable debug console.

# If enabled, user can connect guest OS running inside hypervisor
# through "kata-runtime exec <sandbox-id>" command

#debug_console_enabled = true

# Agent connection dialing timeout value in seconds
# (default: 30)
#dial_timeout = 30

[netmon]
# If enabled, the network monitoring process gets started when the
# sandbox is created. This allows for the detection of some additional
# network being added to the existing network namespace, after the
# sandbox has been created.
# (default: disabled)
#enable_netmon = true

# Specify the path to the netmon binary.
path = "/opt/kata/libexec/kata-containers/kata-netmon"

# If enabled, netmon messages will be sent to the system log
# (default: disabled)
enable_debug = {{ kata_containers_qemu_debug }}

[runtime]
# If enabled, the runtime will log additional debug messages to the
# system log
# (default: disabled)
enable_debug = {{ kata_containers_qemu_debug }}
#
# Internetworking model
# Determines how the VM should be connected to the
# the container network interface
# Options:
#
#   - macvtap
#     Used when the Container network interface can be bridged using
#     macvtap.
#
#   - none
#     Used when customize network. Only creates a tap device. No veth pair.
#
#   - tcfilter
#     Uses tc filter rules to redirect traffic from the network interface
#     provided by plugin to a tap interface connected to the VM.
#
internetworking_model="tcfilter"

# disable guest seccomp
# Determines whether container seccomp profiles are passed to the virtual
# machine and applied by the kata agent. If set to true, seccomp is not applied
# within the guest
# (default: true)
disable_guest_seccomp=true

# If enabled, the runtime will create opentracing.io traces and spans.
# (See https://www.jaegertracing.io/docs/getting-started).
# (default: disabled)
#enable_tracing = true

# Set the full url to the Jaeger HTTP Thrift collector.
# The default if not set will be "http://localhost:14268/api/traces"
#jaeger_endpoint = ""

# Sets the username to be used if basic auth is required for Jaeger.
#jaeger_user = ""

# Sets the password to be used if basic auth is required for Jaeger.
#jaeger_password = ""

# If enabled, the runtime will not create a network namespace for shim and hypervisor processes.
# This option may have some potential impacts to your host. It should only be used when you know what you're doing.
# `disable_new_netns` conflicts with `enable_netmon`
# `disable_new_netns` conflicts with `internetworking_model=tcfilter` and `internetworking_model=macvtap`. It works only
# with `internetworking_model=none`. The tap device will be in the host network namespace and can connect to a bridge
# (like OVS) directly.
# If you are using docker, `disable_new_netns` only works with `docker run --net=none`
# (default: false)
#disable_new_netns = true

# if enabled, the runtime will add all the kata processes inside one dedicated cgroup.
# The container cgroups in the host are not created, just one single cgroup per sandbox.
# The runtime caller is free to restrict or collect cgroup stats of the overall Kata sandbox.
# The sandbox cgroup path is the parent cgroup of a container with the PodSandbox annotation.
# The sandbox cgroup is constrained if there is no container type annotation.
# See: https://godoc.org/github.com/kata-containers/runtime/virtcontainers#ContainerType
sandbox_cgroup_only={{ kata_containers_qemu_sandbox_cgroup_only }}

# If specified, sandbox_bind_mounts identifieds host paths to be mounted (ro) into the sandboxes shared path.
# This is only valid if filesystem sharing is utilized. The provided path(s) will be bindmounted into the shared fs directory.
# If defaults are utilized, these mounts should be available in the guest at `/run/kata-containers/shared/containers/sandbox-mounts`
# These will not be exposed to the container workloads, and are only provided for potential guest services.
sandbox_bind_mounts=[]

# Enabled experimental feature list, format: ["a", "b"].
# Experimental features are features not stable enough for production,
# they may break compatibility, and are prepared for a big version bump.
# Supported experimental features:
# (default: [])
experimental=[]

# If enabled, user can run pprof tools with shim v2 process through kata-monitor.
# (default: false)
# enable_pprof = true

# WARNING: All the options in the following section have not been implemented yet.
# This section was added as a placeholder. DO NOT USE IT!
[image]
# Container image service.
#
# Offload the CRI image management service to the Kata agent.
# (default: false)
#service_offload = true

# Container image decryption keys provisioning.
# Applies only if service_offload is true.
# Keys can be provisioned locally (e.g. through a special command or
# a local file) or remotely (usually after the guest is remotely attested).
# The provision setting is a complete URL that lets the Kata agent decide
# which method to use in order to fetch the keys.
#
# Keys can be stored in a local file, in a measured and attested initrd:
#provision=data:///local/key/file
#
# Keys could be fetched through a special command or binary from the
# initrd (guest) image, e.g. a firmware call:
#provision=file:///path/to/bin/fetcher/in/guest
#
# Keys can be remotely provisioned. The Kata agent fetches them from e.g.
# a HTTPS URL:
#provision=https://my-key-broker.foo/tenant/<tenant-id>