kata-containers/src/runtime-rs/config/configuration-cloud-hypervisor.toml.in

# Copyright (c) 2022 Intel Corporation
#
# SPDX-License-Identifier: Apache-2.0

# XXX: WARNING: this file is auto-generated.
# XXX:
# XXX: Source file: "@CONFIG_CLH_IN@"
# XXX: Project:
# XXX:   Name: @PROJECT_NAME@
# XXX:   Type: @PROJECT_TYPE@

[hypervisor.cloud-hypervisor]
path = "@CLHPATH@"
kernel = "@KERNELPATH_CLH@"
image = "@IMAGEPATH@"

# rootfs filesystem type:
#   - ext4 (default)
#   - xfs
#   - erofs
rootfs_type=@DEFROOTFSTYPE@
 
# Block storage driver to be used for the VM rootfs is backed
# by a block device.
vm_rootfs_driver = "@VMROOTFSDRIVER_CLH@"

# 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, returning an error if none is
# available, or none is supported by the hypervisor.
#
# Known limitations:
# * Does not work by design:
#   - CPU Hotplug 
#   - Memory Hotplug
#   - NVDIMM devices
#
# Supported TEEs:
# * Intel TDX
#
# Default false
# confidential_guest = true

# Path to the firmware.
# If you want Cloud Hypervisor to use a specific firmware, set its path below.
# This is option is only used when confidential_guest is enabled.
#
# For more information about firmwared that can be used with specific TEEs,
# please, refer to:
# * Intel TDX:
#   - td-shim: https://github.com/confidential-containers/td-shim
#
# firmware = "@FIRMWAREPATH@"

# 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 = @DEFENABLEANNOTATIONS@

# 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: @CLHVALIDHYPERVISORPATHS@
valid_hypervisor_paths = @CLHVALIDHYPERVISORPATHS@

# List of valid annotations values for ctlpath
# The default if not set is empty (all annotations rejected.)
# Your distribution recommends: 
# valid_ctlpaths = 

# 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 = "@KERNELPARAMS@"

# 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 = @DEFVCPUS@

# 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.
default_maxvcpus = @DEFMAXVCPUS@

# Default memory size in MiB for SB/VM.
# If unspecified then it will be set @DEFMEMSZ@ MiB.
default_memory = @DEFMEMSZ@

# Shared file system type:
#   - virtio-fs
#   - virtio-fs-nydus
#   - none
shared_fs = "@DEFSHAREDFS_CLH_VIRTIOFS@"

# Path to vhost-user-fs daemon.
virtio_fs_daemon = "@DEFVIRTIOFSDAEMON@"

# Default size of DAX cache in MiB
virtio_fs_cache_size = @DEFVIRTIOFSCACHESIZE@

# Extra args for virtiofsd daemon
#
# Format example:
#   ["-o", "arg1=xxx,arg2", "-o", "hello world", "--arg3=yyy"]
# Examples:
#   Set virtiofsd log level to debug : ["-o", "log_level=debug"] or ["-d"]
#
# see `virtiofsd -h` for possible options.
virtio_fs_extra_args = @DEFVIRTIOFSEXTRAARGS@

# Cache mode:
#
#  - never
#    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 = "@DEFVIRTIOFSCACHE@"

# 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 the kernel
# Default number of bridges per SB/VM:
# unspecified or 0   --> will be set to @DEFBRIDGES@
# > 1 <= 5           --> will be set to the specified number
# > 5                --> will be set to 5
default_bridges = @DEFBRIDGES@

# Reclaim guest freed memory.
# Enabling this will result in the VM balloon device having f_reporting=on set.
# Then the hypervisor will use it to reclaim guest freed memory.
# This is useful for reducing the amount of memory used by a VM.
# Enabling this feature may sometimes reduce the speed of memory access in
# the VM.
#
# Default false
#reclaim_guest_freed_memory = true

# Block device driver to be used by the hypervisor when a container's storage
# is backed by a block device or a file. This driver facilitates attaching the
# storage directly to the guest VM.
block_device_driver = "virtio-blk-pci"

# 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

# 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 = true

# 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

# This option changes the default hypervisor and kernel parameters
# to enable debug output where available.
#
# Default false
#enable_debug = true

# 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

# 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/kata-containers/tree/main/tools/osbuilder
#
# Hooks must be stored in a subdirectory of guest_hook_path according to their
# hook type, i.e. "guest_hook_path/{prestart,poststart,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 while scanning for hooks,
# but it will not abort container execution.
#guest_hook_path = "/usr/share/oci/hooks"

# Enable swap in the guest. Default false.
# When enable_guest_swap is enabled, insert a raw file to the guest as the swap device.
#enable_guest_swap = true

# If enable_guest_swap is enabled, the swap device will be created in the guest
# at this path. Default "/run/kata-containers/swap".
#guest_swap_path = "/run/kata-containers/swap"

# The percentage of the total memory to be used as swap device.
# Default 100.
#guest_swap_size_percent = 100

# The threshold in seconds to create swap device in the guest.
# Kata will wait guest_swap_create_threshold_secs seconds before creating swap device.
# Default 60.
#guest_swap_create_threshold_secs = 60

[agent.@PROJECT_TYPE@]
container_pipe_size=@PIPESIZE@
# If enabled, make the agent display debug-level messages.
# (default: disabled)
#enable_debug = true

# Enable agent tracing.
#
# If enabled, the agent will generate OpenTelemetry trace spans.
#
# Notes:
#
# - If the runtime also has tracing enabled, the agent spans will be
#   associated with the appropriate runtime parent span.
# - If enabled, the runtime will wait for the container to shutdown,
#   increasing the container shutdown time slightly.
#
# (default: disabled)
#enable_tracing = true

# 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 dial timeout in millisecond.
# (default: 10)
#dial_timeout_ms = 10

# Agent reconnect timeout in millisecond.
# Retry times = reconnect_timeout_ms / dial_timeout_ms (default: 300)
# If you find pod cannot connect to the agent when starting, please
# consider increasing this value to increase the retry times.
# You'd better not change the value of dial_timeout_ms, unless you have an
# idea of what you are doing.
# (default: 3000)
#reconnect_timeout_ms = 3000

[agent.@PROJECT_TYPE@.mem_agent]
# Control the mem-agent function enable or disable.
# Default to false
#mem_agent_enable = true

# Control the mem-agent memcg function disable or enable
# Default to false
#memcg_disable = false

# Control the mem-agent function swap enable or disable.
# Default to false
#memcg_swap = false

# Control the mem-agent function swappiness max number.
# Default to 50
#memcg_swappiness_max = 50

# Control the mem-agent memcg function wait period seconds
# Default to 600
#memcg_period_secs = 600

# Control the mem-agent memcg wait period PSI percent limit.
# If the percentage of memory and IO PSI stall time within
# the memcg waiting period for a cgroup exceeds this value,
# then the aging and eviction for this cgroup will not be
# executed after this waiting period.
# Default to 1
#memcg_period_psi_percent_limit = 1

# Control the mem-agent memcg eviction PSI percent limit.
# If the percentage of memory and IO PSI stall time for a cgroup
# exceeds this value during an eviction cycle, the eviction for
# this cgroup will immediately stop and will not resume until
# the next memcg waiting period.
# Default to 1
#memcg_eviction_psi_percent_limit = 1

# Control the mem-agent memcg eviction run aging count min.
# A cgroup will only perform eviction when the number of aging cycles
# in memcg is greater than or equal to memcg_eviction_run_aging_count_min.
# Default to 3
#memcg_eviction_run_aging_count_min = 3

# Control the mem-agent compact function disable or enable
# Default to false
#compact_disable = false

# Control the mem-agent compaction function wait period seconds
# Default to 600
#compact_period_secs = 600

# Control the mem-agent compaction function wait period PSI percent limit.
# If the percentage of memory and IO PSI stall time within
# the compaction waiting period exceeds this value,
# then the compaction will not be executed after this waiting period.
# Default to 1
#compact_period_psi_percent_limit = 1

# Control the mem-agent compaction function compact PSI percent limit.
# During compaction, the percentage of memory and IO PSI stall time
# is checked every second. If this percentage exceeds
# compact_psi_percent_limit, the compaction process will stop.
# Default to 5
#compact_psi_percent_limit = 5

# Control the maximum number of seconds for each compaction of mem-agent compact function.
# Default to 180
#compact_sec_max = 180

# Control the mem-agent compaction function compact order.
# compact_order is use with compact_threshold.
# Default to 9
#compact_order = 9

# Control the mem-agent compaction function compact threshold.
# compact_threshold is the pages number.
# When examining the /proc/pagetypeinfo, if there's an increase in the
# number of movable pages of orders smaller than the compact_order
# compared to the amount following the previous compaction,
# and this increase surpasses a certain threshold—specifically,
# more than 'compact_threshold' number of pages.
# Or the number of free pages has decreased by 'compact_threshold'
# since the previous compaction.
# then the system should initiate another round of memory compaction.
# Default to 1024
#compact_threshold = 1024

# Control the mem-agent compaction function force compact times.
# After one compaction, if there has not been a compaction within
# the next compact_force_times times, a compaction will be forced
# regardless of the system's memory situation.
# If compact_force_times is set to 0, will do force compaction each time.
# If compact_force_times is set to 18446744073709551615, will never do force compaction.
# Default to 18446744073709551615
#compact_force_times = 18446744073709551615

# Create Container Request Timeout
# This timeout value is used to set the maximum duration for the agent to process a CreateContainerRequest.
# It's also used to ensure that workloads, especially those involving large image pulls within the guest,
# have sufficient time to complete.
#
# Effective Timeout Determination:
# The effective timeout for a CreateContainerRequest is determined by taking the minimum of the following two values:
# - create_container_timeout: The timeout value configured for creating containers (default: 30,000 milliseconds).
# - runtime-request-timeout: The timeout value specified in the Kubelet configuration described as the link below:
# (https://kubernetes.io/docs/reference/command-line-tools-reference/kubelet/#:~:text=runtime%2Drequest%2Dtimeout)
# Defaults to @DEFCREATECONTAINERTIMEOUT@ second(s)
# create_container_timeout = @DEFCREATECONTAINERTIMEOUT@

[runtime]
# If enabled, the runtime will log additional debug messages to the
# system log
# (default: disabled)
#enable_debug = true

# If enabled, enabled, it means that 1) if the runtime exits abnormally,
# the cleanup process will be skipped, and 2) the runtime will not exit
# even if the health check fails.
# This option is typically used to retain abnormal information for debugging.
# (default: false)
#keep_abnormal = true

# Internetworking model
# Determines how the VM should be connected to the
# the container network interface
# Options:
#
#   - bridged (Deprecated)
#     Uses a linux bridge to interconnect the container interface to
#     the VM. Works for most cases except macvlan and ipvlan.
#     ***NOTE: This feature has been deprecated with plans to remove this
#     feature in the future. Please use other network models listed below.
#
#
#   - 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="@DEFNETWORKMODEL_CLH@"

name="@RUNTIMENAME@"
hypervisor_name="@HYPERVISOR_CLH@"
agent_name="@PROJECT_TYPE@"

# 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=@DEFDISABLEGUESTSECCOMP@

# 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 `internetworking_model=bridged` 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.
# (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://pkg.go.dev/github.com/kata-containers/kata-containers/src/runtime/virtcontainers#ContainerType
sandbox_cgroup_only=@DEFSANDBOXCGROUPONLY_CLH@

# 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=@DEFAULTEXPFEATURES@

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

# If enabled, the runtime will attempt to determine appropriate sandbox size (memory, CPU) before booting the virtual machine. In
# this case, the runtime will not dynamically update the amount of memory and CPU in the virtual machine. This is generally helpful
# when a hardware architecture or hypervisor solutions is utilized which does not support CPU and/or memory hotplug.
# Compatibility for determining appropriate sandbox (VM) size:
# - When running with pods, sandbox sizing information will only be available if using Kubernetes >= 1.23 and containerd >= 1.6. CRI-O
#   does not yet support sandbox sizing annotations.
# - When running single containers using a tool like ctr, container sizing information will be available.
static_sandbox_resource_mgmt=@DEFSTATICRESOURCEMGMT_CLH@

# If specified, sandbox_bind_mounts identifieds host paths to be mounted(ro, rw) 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.
# Now it supports three kinds of bind mount format:
# - "/path/to", default readonly mode.
# - "/path/to:ro", readonly mode.
# - "/path/to:rw", readwrite mode.
sandbox_bind_mounts=@DEFBINDMOUNTS@

# Base directory of directly attachable network config.
# Network devices for VM-based containers are allowed to be placed in the
# host netns to eliminate as many hops as possible, which is what we
# called a "Directly Attachable Network". The config, set by special CNI
# plugins, is used to tell the Kata containers what devices are attached
# to the hypervisor.
# (default: /run/kata-containers/dans)
dan_conf = "@DEFDANCONF@"