Add log level control for docker agent

Related to #742

cmd/pulse-docker-agent/main.go

@@ -50,7 +50,9 @@ func main() {
 
 	cfg := loadConfig()
 
-	logger := zerolog.New(os.Stdout).With().Timestamp().Logger()
+	zerolog.SetGlobalLevel(cfg.LogLevel)
+
+	logger := zerolog.New(os.Stdout).Level(cfg.LogLevel).With().Timestamp().Logger()
 	cfg.Logger = &logger
 
 	agent, err := dockeragent.New(cfg)
@@ -87,6 +89,7 @@ func loadConfig() dockeragent.Config {
 	envSwarmTasks := utils.GetenvTrim("PULSE_SWARM_TASKS")
 	envIncludeContainers := utils.GetenvTrim("PULSE_INCLUDE_CONTAINERS")
 	envCollectDisk := utils.GetenvTrim("PULSE_COLLECT_DISK")
+	envLogLevel := utils.GetenvTrim("LOG_LEVEL")
 
 	defaultInterval := 30 * time.Second
 	if envInterval != "" {
@@ -120,6 +123,11 @@ func loadConfig() dockeragent.Config {
 		collectDiskDefault = utils.ParseBool(envCollectDisk)
 	}
 
+	logLevelDefault := "info"
+	if envLogLevel != "" {
+		logLevelDefault = envLogLevel
+	}
+
 	urlFlag := flag.String("url", envURL, "Pulse server URL (e.g. http://pulse:7655)")
 	tokenFlag := flag.String("token", envToken, "Pulse API token (required)")
 	intervalFlag := flag.Duration("interval", defaultInterval, "Reporting interval (e.g. 30s)")
@@ -128,6 +136,7 @@ func loadConfig() dockeragent.Config {
 	insecureFlag := flag.Bool("insecure", utils.ParseBool(envInsecure), "Skip TLS certificate verification")
 	noAutoUpdateFlag := flag.Bool("no-auto-update", utils.ParseBool(envNoAutoUpdate), "Disable automatic agent updates")
 	runtimeFlag := flag.String("runtime", envRuntime, "Container runtime to expect (auto, docker, podman)")
+	logLevelFlag := flag.String("log-level", logLevelDefault, "Log level: debug, info, warn, error")
 	var targetFlags stringFlagList
 	flag.Var(&targetFlags, "target", "Pulse target in url|token[|insecure] format. Repeat to send to multiple Pulse instances")
 	var containerStateFlags stringFlagList
@@ -211,6 +220,12 @@ func loadConfig() dockeragent.Config {
 		interval = 30 * time.Second
 	}
 
+	logLevel, err := parseLogLevel(*logLevelFlag)
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "error: %v\n", err)
+		os.Exit(1)
+	}
+
 	containerStates := make([]string, 0)
 	if len(containerStateFlags) > 0 {
 		containerStates = append(containerStates, containerStateFlags.Values()...)
@@ -235,9 +250,24 @@ func loadConfig() dockeragent.Config {
 		IncludeTasks:       *includeTasksFlag,
 		IncludeContainers:  *includeContainersFlag,
 		CollectDiskMetrics: *collectDiskFlag,
+		LogLevel:           logLevel,
 	}
 }
 
+func parseLogLevel(value string) (zerolog.Level, error) {
+	normalized := strings.ToLower(strings.TrimSpace(value))
+	if normalized == "" {
+		return zerolog.InfoLevel, nil
+	}
+
+	level, err := zerolog.ParseLevel(normalized)
+	if err != nil {
+		return zerolog.InfoLevel, fmt.Errorf("invalid log level %q: must be debug, info, warn, or error", value)
+	}
+
+	return level, nil
+}
+
 func parseTargetSpecs(specs []string) ([]dockeragent.TargetConfig, error) {
 	targets := make([]dockeragent.TargetConfig, 0, len(specs))
 	for _, spec := range specs {

docs/DOCKER_MONITORING.md

@@ -220,6 +220,8 @@ docker run -d \
   ghcr.io/rcourtman/pulse-docker-agent:latest
 ```
 
+Add `-e LOG_LEVEL=warn` when your container logs feed into journald or another centralized collector and you want quieter steady-state logging.
+
 > **Note**: Official images for `linux/amd64` and `linux/arm64` are published to `ghcr.io/rcourtman/pulse-docker-agent`. To test local changes, run `docker build --target agent_runtime -t pulse-docker-agent:test .` from the repository root.
 
 `--pid=host`, `--uts=host`, and the `/etc/machine-id` bind keep host metadata stable so Pulse doesn’t think the container itself is the Docker host. Auto-update is disabled in the image by default; rebuild or override `PULSE_NO_AUTO_UPDATE=false` only if you manage upgrades outside of your orchestrator. Expect to grant the container the same level of Docker socket access as the systemd service—running inside Docker doesn’t sandbox the agent from the host.
@@ -232,6 +234,7 @@ docker run -d \
 | `--token`, `PULSE_TOKEN`| Pulse API token with `docker:report` scope (required).    | —               |
 | `--target`, `PULSE_TARGETS` | One or more `url|token[|insecure]` entries to fan-out reports to multiple Pulse servers. Separate entries with `;` or repeat the flag. | — |
 | `--interval`, `PULSE_INTERVAL` | Reporting cadence (supports `30s`, `1m`, etc.).     | `30s`           |
+| `--log-level`, `LOG_LEVEL` | Log verbosity (`debug`, `info`, `warn`, `error`). Use `debug` only while actively troubleshooting to avoid noisy journals. | `info` |
 | `--runtime`, `PULSE_RUNTIME` | Container runtime to target (`docker`, `podman`, `auto`). | `docker` |
 | `--container-socket`, `PULSE_CONTAINER_SOCKET` / `CONTAINER_HOST` | Explicit runtime socket path or `unix://` URI. | Runtime default |
 | `--rootless`, `PULSE_RUNTIME_ROOTLESS` | Install/manage the agent as a user service (Podman). | Auto (rootful) |
@@ -260,6 +263,7 @@ Need the alerts but at a different tone? The same Containers tab exposes global
 ## Testing and troubleshooting
 
 - Run with `--interval 15s --insecure` in a terminal to see log output while testing.
+- Adjust verbosity with `--log-level` or `LOG_LEVEL` (`info` by default). Drop to `warn` for quiet steady-state logs; use `debug` only when actively debugging.
 - Ensure the Pulse API token has not expired or been regenerated.
 - If `pulse-docker-agent` reports `Cannot connect to the Docker daemon`, verify the socket path and permissions.
 - Check Pulse (`/containers` tab) for the latest heartbeat time. Hosts are marked offline if they stop reporting for >4× the configured interval.

internal/dockeragent/agent.go

@@ -57,6 +57,7 @@ type Config struct {
 	IncludeTasks       bool
 	IncludeContainers  bool
 	CollectDiskMetrics bool
+	LogLevel           zerolog.Level
 	Logger             *zerolog.Logger
 }
 
@@ -81,20 +82,20 @@ const (
 
 // Agent collects Docker metrics and posts them to Pulse.
 type Agent struct {
-	cfg              Config
+	cfg                 Config
-	docker           *client.Client
+	docker              *client.Client
-	daemonHost       string
+	daemonHost          string
-	runtime          RuntimeKind
+	runtime             RuntimeKind
-	runtimeVer       string
+	runtimeVer          string
-	supportsSwarm    bool
+	supportsSwarm       bool
-	httpClients      map[bool]*http.Client
+	httpClients         map[bool]*http.Client
-	logger           zerolog.Logger
+	logger              zerolog.Logger
-	machineID        string
+	machineID           string
-	hostName         string
+	hostName            string
-	cpuCount         int
+	cpuCount            int
-	targets          []TargetConfig
+	targets             []TargetConfig
-	allowedStates    map[string]struct{}
+	allowedStates       map[string]struct{}
-	stateFilters     []string
+	stateFilters        []string
 	hostID              string
 	prevContainerCPU    map[string]cpuSample
 	preCPUStatsFailures int
@@ -158,8 +159,12 @@ func New(cfg Config) (*Agent, error) {
 	}
 
 	logger := cfg.Logger
+	if zerolog.GlobalLevel() == zerolog.DebugLevel && cfg.LogLevel != zerolog.DebugLevel {
+		zerolog.SetGlobalLevel(cfg.LogLevel)
+	}
+
 	if logger == nil {
-		defaultLogger := zerolog.New(os.Stdout).With().Timestamp().Str("component", "pulse-docker-agent").Logger()
+		defaultLogger := zerolog.New(os.Stdout).Level(cfg.LogLevel).With().Timestamp().Str("component", "pulse-docker-agent").Logger()
 		logger = &defaultLogger
 	} else {
 		scoped := logger.With().Str("component", "pulse-docker-agent").Logger()