Merge branch 'branch-0.5.0' into Refactor_Knowhere

Former-commit-id: a57472c60518d5fe322469561bd71304192df9f9

cpp/CHANGELOG.md

@@ -140,6 +140,7 @@ Please mark all change in change log and use the ticket from JIRA.
 - MS-523 - Config file validation
 - MS-539 - Remove old task code
 - MS-546 - Add simple mode resource_config
+- MS-570 - Add prometheus docker-compose file
 
 ## New Feature
 - MS-343 - Implement ResourceMgr

cpp/src/metrics/SystemInfo.cpp

@@ -245,6 +245,7 @@ SystemInfo::CPUTemperature(){
         float temp;
         fscanf(file, "%f", &temp);
         result.push_back(temp / 1000);
+        fclose(file);
     }
 
 }

docker/alertmanager.yml

@@ -0,0 +1,19 @@
+global:
+  resolve_timeout: 5m
+
+route:
+  group_by: ['alertname']
+  group_wait: 10s
+  group_interval: 10s
+  repeat_interval: 1h
+  receiver: 'web.hook'
+receivers:
+- name: 'web.hook'
+  webhook_configs:
+  - url: 'http://127.0.0.1:5001/'
+inhibit_rules:
+  - source_match:
+      severity: 'critical'
+    target_match:
+      severity: 'warning'
+    equal: ['alertname', 'dev', 'instance']

docker/docker-compose-monitor.yml

@@ -0,0 +1,56 @@
+version: '2.3'
+
+networks:
+    monitor:
+        driver: bridge
+
+services:
+    prometheus:
+        image: prom/prometheus:v2.11.1
+        container_name: prometheus
+        hostname: prometheus
+        restart: always
+        volumes:
+            - ./prometheus.yml:/etc/prometheus/prometheus.yml
+            - ./server_down.yml:/etc/prometheus/node_down.yml
+        ports:
+            - "9090:9090"
+        networks:
+            - monitor
+
+    alertmanager:
+        image: prom/alertmanager
+        container_name: alertmanager
+        hostname: alertmanager
+        restart: always
+        volumes:
+            - ./alertmanager.yml:/etc/alertmanager/alertmanager.yml
+        ports:
+            - "9093:9093"
+        networks:
+            - monitor
+
+    grafana:
+        image: grafana/grafana
+        container_name: grafana
+        hostname: grafana
+        restart: always
+        ports:
+            - "3000:3000"
+        networks:
+            - monitor
+
+    milvus:
+        runtime: nvidia
+        image: registry.zilliz.com/milvus/engine:branch-0.4.0-release
+        container_name: milvus
+        hostname: milvus
+        restart: always
+        volumes:
+            - ../cpp/conf/server_config.yaml:/opt/milvus/cpp/conf/server_config.yaml
+            - ../cpp/conf/log_config.conf:/opt/milvus/cpp/conf/log_config.conf
+        ports:
+            - "8080:8080"
+            - "19530:19530"
+        networks:
+            - monitor

docker/prometheus.yml

@@ -0,0 +1,46 @@
+# my global config
+global:
+  scrape_interval:     15s # Set the scrape interval to every 1 seconds. Default is every 1 minute.
+  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
+  # scrape_timeout is set to the global default (10s).
+
+# Alertmanager configuration
+alerting:
+  alertmanagers:
+  - static_configs:
+    - targets: ['localhost:9093']
+
+# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
+rule_files:
+   - "serverdown.yml" # add alerting rules
+
+# 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: 'prometheus'
+
+    # metrics_path defaults to '/metrics'
+    # scheme defaults to 'http'.
+
+    static_configs:
+    - targets: ['localhost:9090']
+
+   # scrape metrics of server
+  - job_name: 'milvus_server'
+    scrape_interval: 1s
+    static_configs:
+    - targets: ['localhost:8080']
+
+   # scrape metrics of server
+  - job_name: 'milvus_server_1'
+    scrape_interval: 1s
+    static_configs:
+    - targets: ['localhost:8080']
+
+
+
+   # under development
+  - job_name: 'pushgateway'
+    static_configs:
+    - targets: ['localhost:9091']

docker/server_down.yml

@@ -0,0 +1,8 @@
+groups:
+- name: milvus
+  rules:
+    - alert: MilvusServerDown
+      expr: up{job="milvus_server"}
+      for: 1s
+      labels:
+        serverity: page