agent

type Config struct {
	RefreshStateIntervalSeconds uint `json:"refereshStateIntervalSeconds"`

	Scaling   ScalingConfig    `json:"scaling"`
	Metrics   MetricsConfig    `json:"metrics"`
	Scheduler SchedulerConfig  `json:"scheduler"`
	Monitor   MonitorConfig    `json:"monitor"`
	NeonVM    NeonVMConfig     `json:"neonvm"`
	Billing   billing.Config   `json:"billing"`
	DumpState *DumpStateConfig `json:"dumpState"`
}

type Dispatcher struct {
	// contains filtered or unexported fields
}

type DumpStateConfig struct {
	// Port is the port to serve on
	Port uint16 `json:"port"`
	// TimeoutSeconds gives the maximum duration, in seconds, that we allow for a request to dump
	// internal state.
	TimeoutSeconds uint `json:"timeoutSeconds"`
}

type EnvArgs struct {
	// ConfigPath gives the path to read static configuration from. It is taken from the CONFIG_PATH
	// environment variable.
	ConfigPath string

	// K8sNodeName is the Kubernetes node the autoscaler agent is running on. It is taken from the
	// K8S_NODE_NAME environment variable, which is set equal to the pod's Spec.NodeName.
	//
	// The Kubernetes documentation doesn't say this, but the NodeName is always populated with the
	// final node the pod was placed on by the time the environment variables are set.
	K8sNodeName string

	// K8sPodIP is the IP address of the Kubernetes pod that this autoscaler-agent is running in
	K8sPodIP string
}

type GlobalMetrics struct {
	// contains filtered or unexported fields
}

type MainRunner struct {
	EnvArgs    EnvArgs
	Config     *Config
	KubeClient *kubernetes.Clientset
	VMClient   *vmclient.Clientset
}

type MetricsConfig struct {
	// Port is the port that VMs are expected to provide metrics on
	Port uint16 `json:"port"`
	// LoadMetricPrefix is the prefix at the beginning of the load metrics that we use. For
	// node_exporter, this is "node_", and for vector it's "host_"
	LoadMetricPrefix string `json:"loadMetricPrefix"`
	// RequestTimeoutSeconds gives the timeout duration, in seconds, for metrics requests
	RequestTimeoutSeconds uint `json:"requestTimeoutSeconds"`
	// SecondsBetweenRequests sets the number of seconds to wait between metrics requests
	SecondsBetweenRequests uint `json:"secondsBetweenRequests"`
}

type MonitorConfig struct {
	ResponseTimeoutSeconds uint `json:"responseTimeoutSeconds"`
	// ConnectionTimeoutSeconds gives how long we may take to connect to the
	// monitor before cancelling.
	ConnectionTimeoutSeconds uint `json:"connectionTimeoutSeconds"`
	// ConnectionRetryMinWaitSeconds gives the minimum amount of time we must wait between attempts
	// to connect to the vm-monitor, regardless of whether they're successful.
	ConnectionRetryMinWaitSeconds uint `json:"connectionRetryMinWaitSeconds"`
	// ServerPort is the port that the dispatcher serves from
	ServerPort uint16 `json:"serverPort"`
	// UnhealthyAfterSilenceDurationSeconds gives the duration, in seconds, after which failing to
	// receive a successful request from the monitor indicates that it is probably unhealthy.
	UnhealthyAfterSilenceDurationSeconds uint `json:"unhealthyAfterSilenceDurationSeconds"`
	// UnhealthyStartupGracePeriodSeconds gives the duration, in seconds, after which we will no
	// longer excuse total VM monitor failures - i.e. when unhealthyAfterSilenceDurationSeconds
	// kicks in.
	UnhealthyStartupGracePeriodSeconds uint `json:"unhealthyStartupGracePeriodSeconds"`
	// MaxHealthCheckSequentialFailuresSeconds gives the duration, in seconds, after which we
	// should restart the connection to the vm-monitor if health checks aren't succeeding.
	MaxHealthCheckSequentialFailuresSeconds uint `json:"maxHealthCheckSequentialFailuresSeconds"`
	// MaxFailedRequestRate defines the maximum rate of failed monitor requests, above which
	// a VM is considered stuck.
	MaxFailedRequestRate RateThresholdConfig `json:"maxFailedRequestRate"`

	// RetryFailedRequestSeconds gives the duration, in seconds, that we must wait before retrying a
	// request that previously failed.
	RetryFailedRequestSeconds uint `json:"retryFailedRequestSeconds"`
	// RetryDeniedDownscaleSeconds gives the duration, in seconds, that we must wait before retrying
	// a downscale request that was previously denied
	RetryDeniedDownscaleSeconds uint `json:"retryDeniedDownscaleSeconds"`
	// RequestedUpscaleValidSeconds gives the duration, in seconds, that requested upscaling should
	// be respected for, before allowing re-downscaling.
	RequestedUpscaleValidSeconds uint `json:"requestedUpscaleValidSeconds"`
}

type MonitorResult struct {
	Result       *api.DownscaleResult
	Confirmation *api.UpscaleConfirmation
	HealthCheck  *api.HealthCheck
}

type MonitorState struct {
	WaitersSize int `json:"waitersSize"`
}

type NeonVMConfig struct {
	// RequestTimeoutSeconds gives the timeout duration, in seconds, for VM patch requests
	RequestTimeoutSeconds uint `json:"requestTimeoutSeconds"`
	// RetryFailedRequestSeconds gives the duration, in seconds, that we must wait after a previous
	// failed request before making another one.
	RetryFailedRequestSeconds uint `json:"retryFailedRequestSeconds"`

	// MaxFailedRequestRate defines the maximum rate of failed NeonVM requests, above which
	// a VM is considered stuck.
	MaxFailedRequestRate RateThresholdConfig `json:"maxFailedRequestRate"`
}

type PerVMMetrics struct {
	// contains filtered or unexported fields
}

type RateThresholdConfig struct {
	IntervalSeconds uint `json:"intervalSeconds"`
	Threshold       uint `json:"threshold"`
}

type Runner struct {
	// contains filtered or unexported fields
}

type RunnerState struct {
	PodIP                 string             `json:"podIP"`
	ExecutorState         executor.StateDump `json:"executorState"`
	Monitor               *MonitorState      `json:"monitor"`
	BackgroundWorkerCount int64              `json:"backgroundWorkerCount"`
}

type ScalingConfig struct {
	// ComputeUnit is the desired ratio between CPU and memory that the autoscaler-agent should
	// uphold when making changes to a VM
	ComputeUnit api.Resources `json:"computeUnit"`
	// DefaultConfig gives the default scaling config, to be used if there is no configuration
	// supplied with the "autoscaling.neon.tech/config" annotation.
	DefaultConfig api.ScalingConfig `json:"defaultConfig"`
}

type SchedulerConfig struct {
	// SchedulerName is the name of the scheduler we're expecting to communicate with.
	//
	// Any VMs that don't have a matching Spec.SchedulerName will not be autoscaled.
	SchedulerName string `json:"schedulerName"`
	// RequestTimeoutSeconds gives the timeout duration, in seconds, for requests to the scheduler
	//
	// If zero, requests will have no timeout.
	RequestTimeoutSeconds uint `json:"requestTimeoutSeconds"`
	// RequestAtLeastEverySeconds gives the maximum duration we should go without attempting a
	// request to the scheduler, even if nothing's changed.
	RequestAtLeastEverySeconds uint `json:"requestAtLeastEverySeconds"`
	// RetryFailedRequestSeconds gives the duration, in seconds, that we must wait after a previous
	// failed request before making another one.
	RetryFailedRequestSeconds uint `json:"retryFailedRequestSeconds"`
	// RetryDeniedUpscaleSeconds gives the duration, in seconds, that we must wait before resending
	// a request for resources that were not approved
	RetryDeniedUpscaleSeconds uint `json:"retryDeniedUpscaleSeconds"`
	// RequestPort defines the port to access the scheduler's ✨special✨ API with
	RequestPort uint16 `json:"requestPort"`
	// MaxFailedRequestRate defines the maximum rate of failed scheduler requests, above which
	// a VM is considered stuck.
	MaxFailedRequestRate RateThresholdConfig `json:"maxFailedRequestRate"`
}

type SchedulerState struct {
	Info schedwatch.SchedulerInfo `json:"info"`
}

type StateDump struct {
	Stopped   bool           `json:"stopped"`
	BuildInfo util.BuildInfo `json:"buildInfo"`
	Pods      []podStateDump `json:"pods"`
}