engine

Documentation

Overview

Package engine defines the check contract and the runner. A Check produces Findings; the runner executes every registered check with a shared timeout and aggregates results. Output rendering lives in internal/output, so checks stay pure and testable.

Index

• func Summarize(findings []Finding) map[Status]int
• type CertsConfig
• type Check
• type ChecksConfig
• type Config
  • func LoadConfig(path string) (*Config, error)
• type Finding
• type HAProxyConfig
• type HTTPConfig
• type HTTPTarget
• type NATSConfig
• type Result
  • func Run(ctx context.Context, checks []Check, timeout time.Duration) Result
• type Status
  • func Worst(findings []Finding) Status
• type StreamConfig
• type StreamTarget

Functions

func Summarize

func Summarize(findings []Finding) map[Status]int

Summarize counts findings per status.

Types

type CertsConfig

type CertsConfig struct {
	WarnDays int `yaml:"warn_days"`
	CritDays int `yaml:"crit_days"`
	// Default port for targets and inventory hosts without an explicit one.
	Port int `yaml:"port"`
	// Explicit host[:port] targets.
	Targets []string `yaml:"targets"`
	// Optional Ansible INI inventory: every host becomes a target on Port.
	AnsibleInventory string `yaml:"ansible_inventory"`
}

CertsConfig configures the TLS certificate expiry check.

type Check

type Check interface {
	Name() string
	Run(ctx context.Context) []Finding
}

Check is implemented by every module (certs, http, ...).

type ChecksConfig

type ChecksConfig struct {
	Certs   *CertsConfig   `yaml:"certs"`
	HTTP    *HTTPConfig    `yaml:"http"`
	NATS    *NATSConfig    `yaml:"nats"`
	HAProxy *HAProxyConfig `yaml:"haproxy"`
	Stream  *StreamConfig  `yaml:"stream"`
}

type Config

type Config struct {
	TimeoutSeconds int          `yaml:"timeout_seconds"`
	Checks         ChecksConfig `yaml:"checks"`
}

Config is the root of checkfleet.yml.

func LoadConfig

func LoadConfig(path string) (*Config, error)

LoadConfig reads and validates checkfleet.yml, applying defaults.

type Finding

type Finding struct {
	Check   string `json:"check"`
	Target  string `json:"target"`
	Status  Status `json:"status"`
	Message string `json:"message"`
}

Finding is one observation about one target.

type HAProxyConfig

type HAProxyConfig struct {
	// Stats endpoints as host[:port]; Port applies when a target has none.
	Targets []string `yaml:"targets"`
	Port    int      `yaml:"port"`
	// Scheme (http/https) and path of the CSV stats export.
	Scheme string `yaml:"scheme"`
	Path   string `yaml:"path"`
	// Optional Ansible INI inventory: every host becomes a stats target.
	AnsibleInventory string `yaml:"ansible_inventory"`
	// Optional WARN when a server/backend session usage reaches this percent
	// of its limit (scur/slim). 0 disables the check.
	SessionWarnPct int `yaml:"session_warn_pct"`
	// Optional HTTP basic auth. The password is read from the named env var —
	// never store it in the config file.
	AuthUser    string `yaml:"auth_user"`
	AuthPassEnv string `yaml:"auth_pass_env"`
}

HAProxyConfig configures the HAProxy backend/server health check.

type HTTPConfig

type HTTPConfig struct {
	Targets []HTTPTarget `yaml:"targets"`
}

HTTPConfig configures the HTTP probe check.

type HTTPTarget

type HTTPTarget struct {
	URL          string `yaml:"url"`
	ExpectStatus int    `yaml:"expect_status"`
	MaxLatencyMS int    `yaml:"max_latency_ms"`
	ExpectBody   string `yaml:"expect_body"`
}

type NATSConfig

type NATSConfig struct {
	// Monitoring endpoints as host[:port]; Port applies when a target has none.
	Targets []string `yaml:"targets"`
	Port    int      `yaml:"port"`
	// Optional Ansible INI inventory: every host becomes a monitoring target.
	AnsibleInventory string `yaml:"ansible_inventory"`
	// Scheme for the monitoring endpoint (http or https). Default http.
	Scheme string `yaml:"scheme"`
	// Optional expected meta-leader (server_name); a mismatch is WARN.
	ExpectMetaLeader string `yaml:"expect_meta_leader"`
	// Optional expected peer set (server_name); unexpected peers are ghosts
	// (WARN), missing expected peers are BAD.
	ExpectPeers []string `yaml:"expect_peers"`
	// Raft peer lag thresholds (entries). WARN/BAD when a peer is at or above.
	LagWarn int `yaml:"lag_warn"`
	LagCrit int `yaml:"lag_crit"`
}

NATSConfig configures the NATS JetStream cluster health check.

type Result

type Result struct {
	Findings []Finding     `json:"findings"`
	Started  time.Time     `json:"started"`
	Duration time.Duration `json:"duration_ns"`
}

Result aggregates the findings of a run.

func Run

func Run(ctx context.Context, checks []Check, timeout time.Duration) Result

Run executes the checks sequentially, each bounded by timeout. Findings are sorted by severity (worst first), then check, then target.

type Status

type Status string

Status of a single finding. Severity order: OK < WARN < BAD < ERROR.

const (
	OK    Status = "OK"
	WARN  Status = "WARN"
	BAD   Status = "BAD"
	ERROR Status = "ERROR" // the check itself could not run against the target
)

func Worst

func Worst(findings []Finding) Status

Worst returns the most severe status present (OK for an empty list).

type StreamConfig

type StreamConfig struct {
	Targets []StreamTarget `yaml:"targets"`
}

StreamConfig configures the HLS/DASH stream health check.

type StreamTarget

type StreamTarget struct {
	// Manifest URL: an HLS .m3u8 (master or media) or a DASH .mpd.
	URL string `yaml:"url"`
	// Optional display label; defaults to the URL.
	Name string `yaml:"name"`
	// Expected minimum ladder size (variants/representations). 0 disables.
	MinVariants int `yaml:"min_variants"`
	// Expect a live stream: check live-edge freshness and warn if it's VOD.
	Live bool `yaml:"live"`
	// Live-edge age thresholds in seconds (WARN/BAD). Applied when Live is set.
	MaxAgeWarnSeconds int `yaml:"max_age_warn_seconds"`
	MaxAgeCritSeconds int `yaml:"max_age_crit_seconds"`
}