config

type Config struct {
	APIVersion string `json:"api_version"`

	// Address for the server to listen on.
	Address string `json:"address"`

	// DataDir is the root directory for GPUd state and package artifacts.
	DataDir string `json:"data_dir"`

	// State file that persists the latest status.
	// If empty, the states are not persisted to file.
	State string `json:"state"`

	// Amount of time to retain states/metrics for.
	// Once elapsed, old states/metrics are purged/compacted.
	MetricsRetentionPeriod metav1.Duration `json:"metrics_retention_period"`

	// Amount of time to retain component events for.
	// Once elapsed, old events are purged from the event store.
	EventsRetentionPeriod metav1.Duration `json:"events_retention_period"`

	// Interval at which to compact the state database.
	CompactPeriod metav1.Duration `json:"compact_period"`

	// Set true to enable profiler.
	Pprof bool `json:"pprof"`

	// Set false to disable auto update
	EnableAutoUpdate bool `json:"enable_auto_update"`

	// Exit code to exit with when auto updating.
	// Only valid when the auto update is enabled.
	// Set -1 to disable the auto update by exit code.
	AutoUpdateExitCode int `json:"auto_update_exit_code"`

	// RebootCommands is a bash script to run when the control plane sends a reboot session request.
	// Empty preserves the built-in "sudo reboot" path.
	RebootCommands string `json:"reboot_commands,omitempty"`

	// FindmntCommands overrides how the disk component invokes "findmnt".
	// Empty preserves the legacy behavior of locating "findmnt" on PATH and
	// running it in the current namespace. When set (e.g.
	// "nsenter --target 1 --mount -- findmnt"), it runs in the host mount
	// namespace so the disk component reports the host's mounts.
	FindmntCommands string `json:"findmnt_commands,omitempty"`

	// LsblkCommands overrides how the disk component invokes "lsblk".
	// Empty preserves the legacy behavior. When set (e.g.
	// "nsenter --target 1 --mount -- lsblk"), it runs in the host mount namespace.
	LsblkCommands string `json:"lsblk_commands,omitempty"`

	// BlockdevUsageCommands overrides how the disk component collects partition
	// usage. Empty preserves the legacy behavior of enumerating mounts via
	// gopsutil and measuring usage via the statfs syscall. When set (e.g.
	// "nsenter --target 1 --mount -- df"), partitions and usage are read from
	// that command's output in the host mount namespace.
	BlockdevUsageCommands string `json:"blockdev_usage_commands,omitempty"`

	// NFSHostRoot prefixes NFS volume paths for file operations. Empty preserves
	// the existing direct-path behavior used by systemd installations. A
	// containerized deployment can use /proc/1/root to access the node filesystem
	// without mounting every node-group-specific NFS path into the container.
	NFSHostRoot string `json:"nfs_host_root,omitempty"`

	// ContainerdServiceActiveCommands overrides how the containerd component checks
	// whether the containerd service is active. Empty preserves the legacy
	// behavior of calling systemd directly (systemd.IsActive), which only sees the
	// container's own service manager. When set (e.g.
	// "nsenter --target 1 --mount -- systemctl is-active containerd"), the command
	// runs against the host's service manager; exit code 0 means active.
	ContainerdServiceActiveCommands string `json:"containerd_service_active_commands,omitempty"`

	// ContainerdDanglingPodGracePeriod delays counting API-absent READY sandboxes. Zero counts immediately.
	ContainerdDanglingPodGracePeriod metav1.Duration `json:"containerd_dangling_pod_grace_period,omitempty"`

	Containerd pkgconfigcommon.ContainerdConfig `json:"containerd,omitempty"`

	// VersionFile is the file that contains the target version.
	// If empty, the version file is not used.
	VersionFile string `json:"version_file"`

	// A list of nvidia tool command paths to overwrite the default paths.
	NvidiaToolOverwrites pkgconfigcommon.ToolOverwrites `json:"nvidia_tool_overwrites"`

	// PluginSpecsFile is the file that contains the plugin specs.
	PluginSpecsFile string `json:"plugin_specs_file"`

	// NVSentinel configures the optional NVSentinel integration.
	// When enabled, GPUd serves the NVSentinel PlatformConnector gRPC API on
	// a local unix socket. The node's NVSentinel platform-connector forwards
	// health events to that socket. Components prefer the NVSentinel data
	// point when one exists and fall back to their own detection otherwise.
	NVSentinel *NVSentinelConfig `json:"nvsentinel,omitempty"`

	// Components specifies the components to enable.
	// Leave empty, "*", or "all" to enable all components.
	// Or prefix component names with "-" to disable them.
	Components []string `json:"components"`

	// FailureInjector is the failure injector.
	FailureInjector *components.FailureInjector `json:"failure_injector,omitempty"`

	// SkipSessionUpdateConfig skips processing of updateConfig session commands. Intended for testing.
	SkipSessionUpdateConfig bool `json:"skip_session_update_config"`

	// SessionProtocol selects the control-plane session transport: v1, v2, or auto.
	SessionProtocol string `json:"session_protocol"`

	// DBInMemory enables in-memory SQLite database mode.
	// When true, the database is opened as a shared in-memory database (file::memory:?cache=shared)
	// instead of using the State file path. Data will not persist across restarts.
	// ref. https://github.com/mattn/go-sqlite3?tab=readme-ov-file#faq
	DBInMemory bool `json:"db_in_memory"`

	// SessionToken is the session token for control plane authentication.
	// Used when DBInMemory is true and session credentials are passed via CLI flags.
	// This allows gpud up to pass the session token from login to gpud run.
	SessionToken string `json:"-"`

	// SessionMachineID is the machine ID assigned by the control plane.
	// Used when DBInMemory is true and session credentials are passed via CLI flags.
	// This allows gpud up to pass the assigned machine ID from login to gpud run.
	SessionMachineID string `json:"-"`

	// SessionMachineProof is the per-machine proof returned by login.
	SessionMachineProof string `json:"-"`

	// SessionEndpoint is the control plane endpoint.
	// Used when DBInMemory is true and session credentials are passed via CLI flags.
	// This allows gpud up to pass the endpoint from login to gpud run.
	// The server reads the endpoint from metadata DB, so it must be seeded for in-memory mode.
	SessionEndpoint string `json:"-"`
	// contains filtered or unexported fields
}

type NVSentinelConfig struct {
	// Enabled turns the NVSentinel receiver on. Default false.
	Enabled bool `json:"enabled"`

	// SocketPath is the unix socket GPUd serves for NVSentinel health event
	// forwarding. The NVSentinel platform-connector container must reach this
	// path. The default works with the stock NVSentinel DaemonSet, which
	// mounts the host /var/run/nvsentinel directory at container /var/run.
	// Empty means nvsentinel.DefaultSocketPath.
	SocketPath string `json:"socket_path,omitempty"`

	// EventDedupWindow is how long a received NVSentinel event suppresses
	// GPUd's own duplicate detection of the same data point. It needs only
	// to cover the delivery skew between the two detectors that watch the
	// same incident. Zero means nvsentinel.DefaultEventDedupWindow.
	EventDedupWindow metav1.Duration `json:"event_dedup_window,omitempty"`
}

type Op struct {
	pkgconfigcommon.ToolOverwrites

	FailureInjector *components.FailureInjector

	DataDir    string
	DBInMemory bool

	// RebootCommands is an optional bash script used for control-plane reboot requests.
	// Empty keeps the default host reboot implementation.
	RebootCommands string

	// FindmntCommands optionally overrides how the disk component invokes "findmnt".
	// Empty keeps the legacy in-namespace behavior.
	FindmntCommands string

	// LsblkCommands optionally overrides how the disk component invokes "lsblk".
	// Empty keeps the legacy in-namespace behavior.
	LsblkCommands string

	// BlockdevUsageCommands optionally overrides how the disk component collects
	// partition usage. Empty keeps the legacy gopsutil + statfs behavior.
	BlockdevUsageCommands string

	// ContainerdServiceActiveCommands optionally overrides how the containerd
	// component checks whether the containerd service is active. Empty keeps the
	// legacy in-namespace systemd.IsActive behavior.
	ContainerdServiceActiveCommands string
	Containerd                      pkgconfigcommon.ContainerdConfig

	// SessionToken is the session token for db-in-memory mode.
	// When DBInMemory is true and this is set, the server will seed
	// this token into the in-memory database.
	SessionToken string

	// SessionMachineID is the machine ID for db-in-memory mode.
	// When DBInMemory is true and this is set, the server will seed
	// this machine ID into the in-memory database.
	SessionMachineID string

	// SessionMachineProof is the per-machine proof for db-in-memory mode.
	SessionMachineProof string

	// SessionEndpoint is the control plane endpoint for db-in-memory mode.
	// When DBInMemory is true and this is set, the server will seed
	// this endpoint into the in-memory database.
	// The server reads the endpoint from metadata DB, so it must be seeded for in-memory mode.
	SessionEndpoint string
}

type OpOption func(*Op)