feat(infra): prometheus metrics improvements

core/bot.ts

@@ -333,10 +333,6 @@ Commands:
         withPayments: String(includePay),
       })
 
-      this.metricsService.replyCounter.inc({
-        chatId: 'all_chats',
-      })
-
       ctx.reply(msg, {
         reply_to_message_id: messageId,
       })

core/cache.ts

@@ -45,7 +45,6 @@ export class CacheService {
     if (arr.length < this.MAX_CACHE_SIZE) return
 
     this.metricsService.cacheCounter.reset()
-    this.metricsService.teamsCacheCounter.reset()
 
     const date = new Date()
     this.metricsService.cacheClearingCounter.inc({
@@ -67,13 +66,8 @@ export class CacheService {
       chatId: chatId.toString(),
     })
 
-    this.metricsService.cacheCounter.inc({
-      chatId: 'all_chats',
-    })
-
     if (!this.cachedChats.has(chatId)) {
       this.cachedChats.set(chatId, new Set())
-      this.metricsService.teamsCacheCounter.inc()
     }
 
     this.cachedChats.get(chatId)?.add(username)

core/metrics.ts

@@ -12,8 +12,6 @@ export class MetricsService {
 
   public readonly cacheCounter: Counter
 
-  public readonly teamsCacheCounter: Counter
-
   public readonly cacheClearingCounter: Counter
 
   public readonly groupsCounter: Counter
@@ -56,12 +54,6 @@ export class MetricsService {
     })
     this.registry.registerMetric(this.cacheCounter)
 
-    this.teamsCacheCounter = new Counter({
-      name: 'allbot_teams_cache',
-      help: 'The number of total teams in cache right now',
-    })
-    this.registry.registerMetric(this.teamsCacheCounter)
-
     this.groupsCounter = new Counter({
       name: 'allbot_groups',
       help: 'The number of new added/deleted groups',

dist/core/bot.js

@@ -232,9 +232,6 @@ Commands:
                 chatId: chatId.toString(),
                 withPayments: String(includePay),
             });
-            this.metricsService.replyCounter.inc({
-                chatId: 'all_chats',
-            });
             ctx.reply(msg, {
                 reply_to_message_id: messageId,
             });

dist/core/cache.js

@@ -34,7 +34,6 @@ export class CacheService {
         if (arr.length < this.MAX_CACHE_SIZE)
             return;
         this.metricsService.cacheCounter.reset();
-        this.metricsService.teamsCacheCounter.reset();
         const date = new Date();
         this.metricsService.cacheClearingCounter.inc({
             time: date.toLocaleString('ru-RU', { timeZone: 'Asia/Yekaterinburg' }),
@@ -48,12 +47,8 @@ export class CacheService {
         this.metricsService.cacheCounter.inc({
             chatId: chatId.toString(),
         });
-        this.metricsService.cacheCounter.inc({
-            chatId: 'all_chats',
-        });
         if (!this.cachedChats.has(chatId)) {
             this.cachedChats.set(chatId, new Set());
-            this.metricsService.teamsCacheCounter.inc();
         }
         this.cachedChats.get(chatId)?.add(username);
         const size = this.cachedChats.get(chatId)?.size ?? 0;

dist/core/metrics.js

@@ -7,7 +7,6 @@ export class MetricsService {
     registry;
     replyCounter;
     cacheCounter;
-    teamsCacheCounter;
     cacheClearingCounter;
     groupsCounter;
     commandsCounter;
@@ -37,11 +36,6 @@ export class MetricsService {
             labelNames: ['chatId'],
         });
         this.registry.registerMetric(this.cacheCounter);
-        this.teamsCacheCounter = new Counter({
-            name: 'allbot_teams_cache',
-            help: 'The number of total teams in cache right now',
-        });
-        this.registry.registerMetric(this.teamsCacheCounter);
         this.groupsCounter = new Counter({
             name: 'allbot_groups',
             help: 'The number of new added/deleted groups',

docker-compose.yml

@@ -0,0 +1,41 @@
+version: '3.8'
+
+networks:
+  monitoring:
+    driver: bridge
+
+volumes:
+  prometheus_data: {}
+
+services:
+  prometheus:
+    image: prom/prometheus:latest
+    container_name: prometheus
+    restart: unless-stopped
+    volumes:
+      - ./infra/prometheus.yml:/etc/prometheus/prometheus.yml
+      - prometheus_data:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--web.console.libraries=/etc/prometheus/console_libraries'
+      - '--web.console.templates=/etc/prometheus/consoles'
+      - '--web.enable-lifecycle'
+    ports:
+      - 9090:9090
+    networks:
+      - monitoring
+
+  grafana:
+    image: grafana/grafana
+    container_name: grafana
+    ports:
+      - 3000:3000
+    restart: unless-stopped
+    environment:
+      - GF_SECURITY_ADMIN_USER=admin
+      - GF_SECURITY_ADMIN_PASSWORD=admin
+    volumes:
+      - ./grafana:/etc/grafana/provisioning/datasources
+    networks:
+      - monitoring

infra/prometheus.yml

@@ -0,0 +1,17 @@
+global:
+  scrape_interval: 1m # By default, scrape targets every 15 seconds.
+
+# A scrape configuration containing exactly one endpoint to scrape:
+# Here it's Prometheus itself.
+scrape_configs:
+  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
+  - job_name: 'allbot'
+
+    # Override the global default and scrape targets from this job every 5 seconds.
+    scrape_interval: 1m
+
+    metrics_path: "/metrics"
+    scheme: "http"
+
+    static_configs:
+      - targets: ['allbot-vartose.eu-4.evennode.com']