perf: reduce runner-to-server connection load with adaptive reporting and polling

- Replace fixed 1s RunDaemon timer with event-driven select loop using
  separate log (3s) and state (5s) tickers for periodic flush
- Add batch-size threshold (default 100 rows) to flush logs immediately
  during bursty output like npm install
- Add max-latency timer (default 5s) to guarantee single log lines are
  delivered within a bounded time
- Trigger immediate flush on step transitions (start/stop) and job
  result for responsive frontend UX
- Skip ReportLog when no pending rows and ReportState when state is
  unchanged to eliminate no-op HTTP requests
- Replace fixed-rate polling with exponential backoff and jitter to
  prevent thundering herd on idle runners
- Tune HTTP client with MaxIdleConnsPerHost=10 and share a single
  http.Client between Ping and Runner service clients
- Add configurable options: log_report_interval, log_report_max_latency,
  log_report_batch_size, state_report_interval, fetch_interval_max

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

internal/pkg/config/config.example.yaml

@@ -32,6 +32,22 @@ runner:
   fetch_timeout: 5s
   # The interval for fetching the job from the Gitea instance.
   fetch_interval: 2s
+  # The maximum interval for fetching the job from the Gitea instance.
+  # The runner uses exponential backoff when idle, increasing the interval up to this maximum.
+  # Set to 0 or same as fetch_interval to disable backoff.
+  fetch_interval_max: 60s
+  # The base interval for periodic log flush to the Gitea instance.
+  # Logs may be sent earlier if the buffer reaches log_report_batch_size.
+  log_report_interval: 3s
+  # The maximum time a log row can wait before being sent.
+  # This ensures even a single log line appears on the frontend within this duration.
+  log_report_max_latency: 5s
+  # Flush logs immediately when the buffer reaches this many rows.
+  # This ensures bursty output (e.g., npm install) is delivered promptly.
+  log_report_batch_size: 100
+  # The interval for reporting task state (step status, timing) to the Gitea instance.
+  # State is also reported immediately on step transitions (start/stop).
+  state_report_interval: 5s
   # The github_mirror of a runner is used to specify the mirror address of the github that pulls the action repository.
   # It works when something like `uses: actions/checkout@v4` is used and DEFAULT_ACTIONS_URL is set to github,
   # and github_mirror is not empty. In this case,

internal/pkg/config/config.go

@@ -22,17 +22,23 @@ type Log struct {
 
 // Runner represents the configuration for the runner.
 type Runner struct {
-	File            string            `yaml:"file"`             // File specifies the file path for the runner.
-	Capacity        int               `yaml:"capacity"`         // Capacity specifies the capacity of the runner.
-	Envs            map[string]string `yaml:"envs"`             // Envs stores environment variables for the runner.
-	EnvFile         string            `yaml:"env_file"`         // EnvFile specifies the path to the file containing environment variables for the runner.
-	Timeout         time.Duration     `yaml:"timeout"`          // Timeout specifies the duration for runner timeout.
-	ShutdownTimeout time.Duration     `yaml:"shutdown_timeout"` // ShutdownTimeout specifies the duration to wait for running jobs to complete during a shutdown of the runner.
-	Insecure        bool              `yaml:"insecure"`         // Insecure indicates whether the runner operates in an insecure mode.
-	FetchTimeout    time.Duration     `yaml:"fetch_timeout"`    // FetchTimeout specifies the timeout duration for fetching resources.
-	FetchInterval   time.Duration     `yaml:"fetch_interval"`   // FetchInterval specifies the interval duration for fetching resources.
-	Labels          []string          `yaml:"labels"`           // Labels specify the labels of the runner. Labels are declared on each startup
-	GithubMirror    string            `yaml:"github_mirror"`    // GithubMirror defines what mirrors should be used when using github
+	File                string            `yaml:"file"`                   // File specifies the file path for the runner.
+	Capacity            int               `yaml:"capacity"`               // Capacity specifies the capacity of the runner.
+	Envs                map[string]string `yaml:"envs"`                   // Envs stores environment variables for the runner.
+	EnvFile             string            `yaml:"env_file"`               // EnvFile specifies the path to the file containing environment variables for the runner.
+	Timeout             time.Duration     `yaml:"timeout"`                // Timeout specifies the duration for runner timeout.
+	ShutdownTimeout     time.Duration     `yaml:"shutdown_timeout"`       // ShutdownTimeout specifies the duration to wait for running jobs to complete during a shutdown of the runner.
+	Insecure            bool              `yaml:"insecure"`               // Insecure indicates whether the runner operates in an insecure mode.
+	FetchTimeout        time.Duration     `yaml:"fetch_timeout"`          // FetchTimeout specifies the timeout duration for fetching resources.
+	FetchInterval       time.Duration     `yaml:"fetch_interval"`         // FetchInterval specifies the interval duration for fetching resources.
+	FetchIntervalMax    time.Duration     `yaml:"fetch_interval_max"`     // FetchIntervalMax specifies the maximum backoff interval when idle.
+	ReportInterval      time.Duration     `yaml:"report_interval"`        // Deprecated: use LogReportInterval and StateReportInterval instead.
+	LogReportInterval   time.Duration     `yaml:"log_report_interval"`    // LogReportInterval specifies the base interval for periodic log flush.
+	LogReportMaxLatency time.Duration     `yaml:"log_report_max_latency"` // LogReportMaxLatency specifies the max time a log row can wait before being sent.
+	LogReportBatchSize  int               `yaml:"log_report_batch_size"`  // LogReportBatchSize triggers immediate log flush when buffer reaches this size.
+	StateReportInterval time.Duration     `yaml:"state_report_interval"`  // StateReportInterval specifies the interval for state reporting.
+	Labels              []string          `yaml:"labels"`                 // Labels specify the labels of the runner. Labels are declared on each startup
+	GithubMirror        string            `yaml:"github_mirror"`          // GithubMirror defines what mirrors should be used when using github
 }
 
 // Cache represents the configuration for caching.
@@ -137,6 +143,21 @@ func LoadDefault(file string) (*Config, error) {
 	if cfg.Runner.FetchInterval <= 0 {
 		cfg.Runner.FetchInterval = 2 * time.Second
 	}
+	if cfg.Runner.FetchIntervalMax <= 0 {
+		cfg.Runner.FetchIntervalMax = 60 * time.Second
+	}
+	if cfg.Runner.LogReportInterval <= 0 {
+		cfg.Runner.LogReportInterval = 3 * time.Second
+	}
+	if cfg.Runner.LogReportMaxLatency <= 0 {
+		cfg.Runner.LogReportMaxLatency = 5 * time.Second
+	}
+	if cfg.Runner.LogReportBatchSize <= 0 {
+		cfg.Runner.LogReportBatchSize = 100
+	}
+	if cfg.Runner.StateReportInterval <= 0 {
+		cfg.Runner.StateReportInterval = 5 * time.Second
+	}
 
 	// although `container.network_mode` will be deprecated, but we have to be compatible with it for now.
 	if cfg.Container.NetworkMode != "" && cfg.Container.Network == "" {