@zintrust/core 0.1.42 → 0.1.43

package/packages/workers/src/ResourceMonitor.js

@@ -0,0 +1,632 @@
+/**
+ * Resource Monitor
+ * Real-time resource tracking with cost calculation
+ * Sealed namespace for immutability
+ */
+import { Env, Logger, NodeSingletons } from '../../../src/index.js';
+const getOsModule = () => NodeSingletons?.os ?? null;
+const safeTotalMemory = () => {
+    const os = getOsModule();
+    if (!os?.totalmem)
+        return 0;
+    try {
+        return os.totalmem();
+    }
+    catch {
+        return 0;
+    }
+};
+const safeFreeMemory = () => {
+    const os = getOsModule();
+    if (!os?.freemem)
+        return 0;
+    try {
+        return os.freemem();
+    }
+    catch {
+        return 0;
+    }
+};
+const safeLoadAverage = () => {
+    const os = getOsModule();
+    if (!os?.loadavg)
+        return [0, 0, 0];
+    try {
+        return os.loadavg();
+    }
+    catch {
+        return [0, 0, 0];
+    }
+};
+const safeCpuCount = () => {
+    const os = getOsModule();
+    if (!os?.cpus)
+        return 1;
+    try {
+        return Math.max(1, os.cpus().length);
+    }
+    catch {
+        return 1;
+    }
+};
+const safePlatform = () => {
+    const os = getOsModule();
+    if (!os?.platform)
+        return 'unknown';
+    try {
+        return os.platform();
+    }
+    catch {
+        return 'unknown';
+    }
+};
+const safeArch = () => {
+    const os = getOsModule();
+    if (!os?.arch)
+        return 'unknown';
+    try {
+        return os.arch();
+    }
+    catch {
+        return 'unknown';
+    }
+};
+const safeHostname = () => {
+    const os = getOsModule();
+    if (!os?.hostname)
+        return 'unknown';
+    try {
+        return os.hostname();
+    }
+    catch {
+        return 'unknown';
+    }
+};
+const safeUptime = () => {
+    const os = getOsModule();
+    if (!os?.uptime)
+        return 0;
+    try {
+        return os.uptime();
+    }
+    catch {
+        return 0;
+    }
+};
+const safeProcessCpuUsage = () => {
+    if (!process?.cpuUsage)
+        return { user: 0, system: 0 };
+    try {
+        return process.cpuUsage();
+    }
+    catch {
+        return { user: 0, system: 0 };
+    }
+};
+// Default cost configuration (AWS-like pricing)
+const DEFAULT_COST_CONFIG = {
+    computeCostPerCoreHour: 0.0416, // ~$0.0416 per vCPU hour (t3.medium equivalent)
+    memoryCostPerGBHour: 0.0052, // ~$0.0052 per GB hour
+    networkCostPerGB: 0.09, // $0.09 per GB transferred
+    diskCostPerGB: 0.1, // $0.10 per GB/month
+    spotInstanceDiscount: 70, // 70% discount for spot instances
+};
+// Internal state
+let costConfig = { ...DEFAULT_COST_CONFIG };
+let monitoringInterval = null;
+const resourceHistory = new Map();
+const alertHistory = new Map();
+// Memory management constants
+const MAX_HISTORY_SIZE = 1000; // Keep last 1000 snapshots per worker
+const MAX_ALERT_HISTORY = 100; // Keep last 100 alerts per worker
+// Resource thresholds
+const THRESHOLDS = {
+    cpu: { warning: 70, critical: 90 },
+    memory: { warning: 75, critical: 85 },
+    disk: { warning: 80, critical: 90 },
+    costPerHour: { warning: 10, critical: 50 },
+};
+// Store previous CPU measurements for calculating real-time usage
+let previousCpuTimes = null;
+/**
+ * Helper: Calculate CPU usage percentage (real-time)
+ */
+const calculateCpuUsage = () => {
+    const os = getOsModule();
+    if (!os?.cpus)
+        return 0;
+    try {
+        const cpus = os.cpus();
+        let totalIdle = 0;
+        let totalTick = 0;
+        cpus.forEach((cpu) => {
+            for (const type in cpu.times) {
+                totalTick += cpu.times[type];
+            }
+            totalIdle += cpu.times.idle;
+        });
+        const now = Date.now();
+        // If we have previous measurements, calculate real-time usage
+        if (previousCpuTimes) {
+            const timeDiff = now - previousCpuTimes.timestamp;
+            // Only calculate if enough time has passed (minimum 100ms)
+            if (timeDiff >= 100) {
+                const idleDiff = totalIdle - previousCpuTimes.idle;
+                const totalDiff = totalTick - previousCpuTimes.total;
+                // Calculate CPU usage percentage for this interval
+                const cpuPercentage = totalDiff > 0 ? ((totalDiff - idleDiff) / totalDiff) * 100 : 0;
+                // Update previous measurements
+                previousCpuTimes = { idle: totalIdle, total: totalTick, timestamp: now };
+                return Math.min(100, Math.max(0, cpuPercentage));
+            }
+        }
+        // First measurement or not enough time passed
+        previousCpuTimes = { idle: totalIdle, total: totalTick, timestamp: now };
+        // For first call, return a reasonable estimate or use load average
+        const loadAvg = safeLoadAverage();
+        const cpuCount = safeCpuCount();
+        return Math.min(100, Math.max(0, (loadAvg[0] / cpuCount) * 100));
+    }
+    catch (error) {
+        Logger.error('Failed to calculate system CPU usage', error);
+        return 0;
+    }
+};
+/**
+ * Helper: Get memory usage
+ */
+const getMemoryUsage = () => {
+    const totalMemory = safeTotalMemory();
+    const freeMemory = safeFreeMemory();
+    const usedMemory = totalMemory - freeMemory;
+    const usage = totalMemory > 0 ? (usedMemory / totalMemory) * 100 : 0;
+    return {
+        total: totalMemory,
+        used: usedMemory,
+        free: freeMemory,
+        usage,
+    };
+};
+/**
+ * Helper: Capture resource snapshot
+ */
+const captureSnapshot = () => {
+    const cpuUsage = calculateCpuUsage();
+    const memoryUsage = getMemoryUsage();
+    const loadAverage = safeLoadAverage();
+    const cpuCores = safeCpuCount();
+    return {
+        timestamp: new Date(),
+        cpu: {
+            usage: cpuUsage,
+            loadAverage,
+            cores: cpuCores,
+        },
+        memory: memoryUsage,
+        disk: {
+            read: 0, // Would need platform-specific implementation
+            write: 0,
+        },
+        network: {
+            received: 0, // Would need platform-specific implementation
+            transmitted: 0,
+        },
+        process: {
+            pid: process.pid,
+            uptime: process.uptime(),
+            memoryUsage: process.memoryUsage(),
+            cpuUsage: safeProcessCpuUsage(),
+        },
+    };
+};
+/**
+ * Helper: Calculate cost based on resource usage
+ */
+const calculateCost = (snapshot, useSpotDiscount = false) => {
+    const { cpu, memory } = snapshot;
+    // CPU cost (based on cores and usage)
+    const cpuCostPerHour = cpu.cores * (cpu.usage / 100) * costConfig.computeCostPerCoreHour;
+    // Memory cost (based on GB used)
+    const memoryGB = memory.used / (1024 * 1024 * 1024);
+    const memoryCostPerHour = memoryGB * costConfig.memoryCostPerGBHour;
+    // Total compute cost
+    let totalCostPerHour = cpuCostPerHour + memoryCostPerHour;
+    // Apply spot instance discount if applicable
+    if (useSpotDiscount) {
+        totalCostPerHour *= 1 - costConfig.spotInstanceDiscount / 100;
+    }
+    return {
+        perHour: totalCostPerHour,
+        perDay: totalCostPerHour * 24,
+        perMonth: totalCostPerHour * 24 * 30,
+    };
+};
+/**
+ * Helper: Calculate efficiency score
+ */
+const calculateEfficiency = (snapshot) => {
+    const { cpu, memory } = snapshot;
+    // CPU efficiency: 50-80% usage is ideal
+    let cpuEfficiency;
+    if (cpu.usage < 30) {
+        cpuEfficiency = cpu.usage * 2; // Under-utilized
+    }
+    else if (cpu.usage > 80) {
+        cpuEfficiency = 100 - (cpu.usage - 80) * 2; // Over-utilized
+    }
+    else {
+        cpuEfficiency = 100; // Ideal range
+    }
+    // Memory efficiency: 50-75% usage is ideal
+    let memoryEfficiency;
+    if (memory.usage < 40) {
+        memoryEfficiency = memory.usage * 1.5; // Under-utilized
+    }
+    else if (memory.usage > 75) {
+        memoryEfficiency = 100 - (memory.usage - 75) * 2; // Over-utilized
+    }
+    else {
+        memoryEfficiency = 100; // Ideal range
+    }
+    const overallScore = cpuEfficiency * 0.6 + memoryEfficiency * 0.4;
+    return {
+        cpuEfficiency: Math.round(cpuEfficiency),
+        memoryEfficiency: Math.round(memoryEfficiency),
+        overallScore: Math.round(overallScore),
+    };
+};
+/**
+ * Helper: Check thresholds and create alerts
+ */
+const checkThresholds = (workerName, snapshot, cost) => {
+    const alerts = [];
+    // CPU alerts
+    if (snapshot.cpu.usage >= THRESHOLDS.cpu.critical) {
+        alerts.push({
+            timestamp: new Date(),
+            workerName,
+            alertType: 'cpu-high',
+            severity: 'critical',
+            message: `Critical CPU usage: ${snapshot.cpu.usage.toFixed(1)}%`,
+            currentValue: snapshot.cpu.usage,
+            threshold: THRESHOLDS.cpu.critical,
+            recommendation: 'Consider scaling up or optimizing worker code',
+        });
+    }
+    else if (snapshot.cpu.usage >= THRESHOLDS.cpu.warning) {
+        alerts.push({
+            timestamp: new Date(),
+            workerName,
+            alertType: 'cpu-high',
+            severity: 'warning',
+            message: `High CPU usage: ${snapshot.cpu.usage.toFixed(1)}%`,
+            currentValue: snapshot.cpu.usage,
+            threshold: THRESHOLDS.cpu.warning,
+            recommendation: 'Monitor closely and consider scaling',
+        });
+    }
+    // Memory alerts
+    if (snapshot.memory.usage >= THRESHOLDS.memory.critical) {
+        alerts.push({
+            timestamp: new Date(),
+            workerName,
+            alertType: 'memory-high',
+            severity: 'critical',
+            message: `Critical memory usage: ${snapshot.memory.usage.toFixed(1)}%`,
+            currentValue: snapshot.memory.usage,
+            threshold: THRESHOLDS.memory.critical,
+            recommendation: 'Increase memory allocation or optimize memory usage',
+        });
+    }
+    else if (snapshot.memory.usage >= THRESHOLDS.memory.warning) {
+        alerts.push({
+            timestamp: new Date(),
+            workerName,
+            alertType: 'memory-high',
+            severity: 'warning',
+            message: `High memory usage: ${snapshot.memory.usage.toFixed(1)}%`,
+            currentValue: snapshot.memory.usage,
+            threshold: THRESHOLDS.memory.warning,
+            recommendation: 'Monitor memory consumption',
+        });
+    }
+    // Cost alerts
+    if (cost.perHour >= THRESHOLDS.costPerHour.critical) {
+        alerts.push({
+            timestamp: new Date(),
+            workerName,
+            alertType: 'cost-high',
+            severity: 'critical',
+            message: `Critical hourly cost: $${cost.perHour.toFixed(2)}/hr`,
+            currentValue: cost.perHour,
+            threshold: THRESHOLDS.costPerHour.critical,
+            recommendation: 'Review resource allocation and consider cost optimization',
+        });
+    }
+    else if (cost.perHour >= THRESHOLDS.costPerHour.warning) {
+        alerts.push({
+            timestamp: new Date(),
+            workerName,
+            alertType: 'cost-high',
+            severity: 'warning',
+            message: `High hourly cost: $${cost.perHour.toFixed(2)}/hr`,
+            currentValue: cost.perHour,
+            threshold: THRESHOLDS.costPerHour.warning,
+            recommendation: 'Consider using spot instances or reducing concurrency',
+        });
+    }
+    return alerts;
+};
+/**
+ * Helper: Store alert
+ */
+const storeAlert = (alert) => {
+    let history = alertHistory.get(alert.workerName);
+    if (!history) {
+        history = [];
+        alertHistory.set(alert.workerName, history);
+    }
+    history.push(alert);
+    // Trim alert history to prevent memory leaks
+    if (history.length > MAX_ALERT_HISTORY) {
+        alertHistory.set(alert.workerName, history.slice(-MAX_ALERT_HISTORY));
+    }
+};
+/**
+ * Helper: Calculate trend
+ */
+const calculateTrend = (workerName, metric, period) => {
+    const history = resourceHistory.get(workerName);
+    if (!history || history.length < 2)
+        return null;
+    const now = Date.now();
+    let periodMs;
+    switch (period) {
+        case 'hour':
+            periodMs = 60 * 60 * 1000;
+            break;
+        case 'day':
+            periodMs = 24 * 60 * 60 * 1000;
+            break;
+        case 'week':
+            periodMs = 7 * 24 * 60 * 60 * 1000;
+            break;
+    }
+    // Filter snapshots within period
+    const periodSnapshots = history.filter((s) => now - s.timestamp.getTime() <= periodMs);
+    if (periodSnapshots.length < 2)
+        return null;
+    // Get metric values
+    const values = periodSnapshots.map((s) => {
+        switch (metric) {
+            case 'cpu':
+                return s.cpu.usage;
+            case 'memory':
+                return s.memory.usage;
+            case 'disk':
+                return s.disk.read + s.disk.write;
+            case 'network':
+                return s.network.received + s.network.transmitted;
+            case 'cost':
+                return calculateCost(s).perHour;
+        }
+    });
+    // Simple linear regression for trend
+    const firstValue = values[0];
+    const lastValue = values[values.length - 1] ?? values[0];
+    const changePercentage = ((lastValue - firstValue) / firstValue) * 100;
+    let trend;
+    if (Math.abs(changePercentage) < 5) {
+        trend = 'stable';
+    }
+    else if (changePercentage > 0) {
+        trend = 'increasing';
+    }
+    else {
+        trend = 'decreasing';
+    }
+    // Simple predictions (linear extrapolation)
+    const avgChange = (lastValue - firstValue) / periodSnapshots.length;
+    const predictions = {
+        nextHour: lastValue + avgChange * 12, // Assuming 5-min intervals
+        nextDay: lastValue + avgChange * 288,
+        nextWeek: lastValue + avgChange * 2016,
+    };
+    return {
+        workerName,
+        metric,
+        period,
+        trend,
+        changePercentage,
+        predictions,
+    };
+};
+/**
+ * Resource Monitor - Sealed namespace
+ */
+export const ResourceMonitor = Object.freeze({
+    /**
+     * Initialize resource monitor
+     */
+    initialize(config) {
+        if (config) {
+            costConfig = { ...DEFAULT_COST_CONFIG, ...config };
+        }
+        Logger.info('ResourceMonitor initialized', { costConfig });
+    },
+    /**
+     * Check whether monitoring is running
+     */
+    isRunning() {
+        return monitoringInterval !== null;
+    },
+    /**
+     * Start monitoring
+     */
+    start(intervalSeconds = 30) {
+        const globalResourceMonitoring = Env.getBool('WORKER_RESOURCE_MONITORING', false);
+        if (!globalResourceMonitoring) {
+            Logger.warn('ResourceMonitor disabled (WORKER_RESOURCE_MONITORING=false)');
+            return;
+        }
+        if (monitoringInterval) {
+            Logger.warn('ResourceMonitor already running');
+            return;
+        }
+        monitoringInterval = setInterval(() => {
+            const snapshot = captureSnapshot();
+            // Store snapshot for later analysis
+            // This would typically be saved to a time-series database
+            Logger.debug('Resource snapshot captured', {
+                cpu: snapshot.cpu.usage.toFixed(1) + '%',
+                memory: snapshot.memory.usage.toFixed(1) + '%',
+            });
+        }, intervalSeconds * 1000);
+        Logger.info('ResourceMonitor started', { intervalSeconds });
+    },
+    /**
+     * Stop monitoring
+     */
+    stop() {
+        if (monitoringInterval) {
+            clearInterval(monitoringInterval);
+            monitoringInterval = null;
+            Logger.info('ResourceMonitor stopped');
+        }
+    },
+    /**
+     * Get current resource usage
+     */
+    getCurrentUsage(workerName, useSpotDiscount = false) {
+        const snapshot = captureSnapshot();
+        const cost = calculateCost(snapshot, useSpotDiscount);
+        const efficiency = calculateEfficiency(snapshot);
+        // Store in history
+        let history = resourceHistory.get(workerName);
+        if (!history) {
+            history = [];
+            resourceHistory.set(workerName, history);
+        }
+        history.push(snapshot);
+        // Trim resource history to prevent memory leaks
+        if (history.length > MAX_HISTORY_SIZE) {
+            resourceHistory.set(workerName, history.slice(-MAX_HISTORY_SIZE));
+        }
+        // Check thresholds
+        const alerts = checkThresholds(workerName, snapshot, cost);
+        alerts.forEach((element) => {
+            storeAlert(element);
+        });
+        return {
+            workerName,
+            cpu: snapshot.cpu.usage,
+            memory: {
+                number: snapshot.memory.total,
+                percent: snapshot.memory.usage,
+                used: snapshot.memory.used,
+                free: snapshot.memory.free,
+            },
+            cost: {
+                hourly: cost.perHour,
+                daily: cost.perDay,
+            },
+            resourceSnapshot: snapshot,
+            estimatedCost: cost,
+            efficiency,
+        };
+    },
+    /**
+     * Get resource history
+     */
+    getHistory(workerName, limit = 100) {
+        const history = resourceHistory.get(workerName) ?? [];
+        return history.slice(-limit).map((s) => ({ ...s }));
+    },
+    /**
+     * Get alerts
+     */
+    getAlerts(workerName, limit = 100) {
+        const history = alertHistory.get(workerName) ?? [];
+        return history.slice(-limit).map((a) => ({ ...a }));
+    },
+    /**
+     * Get trend analysis
+     */
+    getTrend(workerName, metric, period) {
+        return calculateTrend(workerName, metric, period);
+    },
+    /**
+     * Get all trends
+     */
+    getAllTrends(workerName, period) {
+        return {
+            cpu: calculateTrend(workerName, 'cpu', period),
+            memory: calculateTrend(workerName, 'memory', period),
+            disk: calculateTrend(workerName, 'disk', period),
+            network: calculateTrend(workerName, 'network', period),
+            cost: calculateTrend(workerName, 'cost', period),
+        };
+    },
+    /**
+     * Update cost configuration
+     */
+    updateCostConfig(config) {
+        costConfig = { ...costConfig, ...config };
+        Logger.info('Resource monitor cost config updated', { costConfig });
+    },
+    /**
+     * Get cost configuration
+     */
+    getCostConfig() {
+        return { ...costConfig };
+    },
+    /**
+     * Calculate projected cost
+     */
+    calculateProjectedCost(cpuUsagePercent, memoryGB, hoursPerDay, useSpotDiscount = false) {
+        const cpuCores = safeCpuCount();
+        const cpuCostPerHour = cpuCores * (cpuUsagePercent / 100) * costConfig.computeCostPerCoreHour;
+        const memoryCostPerHour = memoryGB * costConfig.memoryCostPerGBHour;
+        let totalCostPerHour = cpuCostPerHour + memoryCostPerHour;
+        if (useSpotDiscount) {
+            totalCostPerHour *= 1 - costConfig.spotInstanceDiscount / 100;
+        }
+        return {
+            daily: totalCostPerHour * hoursPerDay,
+            monthly: totalCostPerHour * hoursPerDay * 30,
+            yearly: totalCostPerHour * hoursPerDay * 365,
+        };
+    },
+    /**
+     * Get system information
+     */
+    getSystemInfo() {
+        return {
+            platform: safePlatform(),
+            arch: safeArch(),
+            hostname: safeHostname(),
+            cpus: safeCpuCount(),
+            totalMemory: safeTotalMemory(),
+            freeMemory: safeFreeMemory(),
+            uptime: safeUptime(),
+        };
+    },
+    /**
+     * Clear history for a worker
+     */
+    clearHistory(workerName) {
+        resourceHistory.delete(workerName);
+        alertHistory.delete(workerName);
+        Logger.info(`Cleared resource history for ${workerName}`);
+    },
+    /**
+     * Shutdown
+     */
+    shutdown() {
+        ResourceMonitor.stop();
+        resourceHistory.clear();
+        alertHistory.clear();
+        Logger.info('ResourceMonitor shutdown complete');
+    },
+});
+// Graceful shutdown handled by WorkerShutdown