[skip ci]Add a metric to display the number of files opened by Milvus (#4509)

* [skip ci]Add a metric to display the number of files opened by Milvus

Signed-off-by: fishpenguin <kun.yu@zilliz.com>

* [skip ci]Add dashboard.yml

Signed-off-by: fishpenguin <kun.yu@zilliz.com>

CHANGELOG.md

@@ -8,6 +8,7 @@ Please mark all change in change log and use the issue from GitHub
 -   \#4484 Milvus only search default partition if search parameter 'partition_tags' contains '_default'
 
 ## Feature
+-   \#4504 Add a metric to display the number of files opened by Milvus
 
 ## Improvement
 -   \#4454 Optimize the process of indexing and querying

docker/docker-compose-monitor.yml

@@ -4,13 +4,19 @@ networks:
     monitor:
         driver: bridge
 
+volumes:
+    prometheus_data: {}
+    grafana_data: {}
+
 services:
     prometheus:
-        image: prom/prometheus:v2.11.1
+        image: prom/prometheus:v2.17.1
         container_name: prometheus
         hostname: prometheus
         restart: always
         volumes:
+            - ./prometheus:/etc/prometheus
+            - prometheus_data:/prometheus
             - ./prometheus.yml:/etc/prometheus/prometheus.yml
             - ./server_down.yml:/etc/prometheus/node_down.yml
         ports:
@@ -30,29 +36,54 @@ services:
         networks:
             - monitor
 
+    pushgateway:
+        image: prom/pushgateway
+        container_name: pushgateway
+        restart: unless-stopped
+        expose:
+        - 9091
+        ports:
+        - "9091:9091"
+        networks:
+        - monitor
+        labels:
+            org.label-schema.group: "monitoring"
+
+    nodeexporter:
+        image: prom/node-exporter:v0.18.1
+        container_name: nodeexporter
+        volumes:
+            - /proc:/host/proc:ro
+            - /sys:/host/sys:ro
+            - /:/rootfs:ro
+        command:
+            - '--path.procfs=/host/proc'
+            - '--path.rootfs=/rootfs'
+            - '--path.sysfs=/host/sys'
+            - '--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|host|etc)($$|/)'
+        restart: unless-stopped
+        expose:
+            - 9100
+        networks:
+            - monitor
+        labels:
+            org.label-schema.group: "monitoring"
+
     grafana:
-        image: grafana/grafana
+        image: grafana/grafana:6.7.2
         container_name: grafana
+        volumes:
+            - grafana_data:/var/lib/grafana
+            - ./grafana/provisioning:/etc/grafana/provisioning
+        environment:
+            - GF_SECURITY_ADMIN_USER=${ADMIN_USER}
+            - GF_SECURITY_ADMIN_PASSWORD=${ADMIN_PASSWORD}
+            - GF_USERS_ALLOW_SIGN_UP=false
+        restart: unless-stopped
+        expose:
+            - 3000
         hostname: grafana
-        restart: always
         ports:
             - "3000:3000"
         networks:
             - monitor
-
-    milvus_server:
-        runtime: nvidia
-        image: milvusdb/milvus:latest
-        restart: always
-        links:
-            - prometheus
-        environment:
-            WEB_APP: host.docker.internal
-        volumes:
-            - ../core/conf/server_config.yaml:/var/lib/milvus/conf/server_config.yaml
-            - ../core/conf/log_config.conf:/var/lib/milvus/conf/log_config.conf
-        ports:
-            - "8080:8080"
-            - "19530:19530"
-        networks:
-            - monitor

docker/grafana/provisioning/dashboards/dashboard.yml

@@ -0,0 +1,12 @@
+apiVersion: 1
+
+providers:
+  - name: 'Prometheus'
+    orgId: 1
+    folder: ''
+    type: file
+    disableDeletion: false
+    editable: true
+    allowUiUpdates: true
+    options:
+      path: /etc/grafana/provisioning/dashboards

docker/grafana/provisioning/datasources/datasource.yml

@@ -0,0 +1,11 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    access: proxy
+    orgId: 1
+    url: http://prometheus:9090
+    basicAuth: false
+    isDefault: true
+    editable: true

docker/prometheus.yml

@@ -1,7 +1,7 @@
 # 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_interval:     2s # Set the scrape interval to every 1 seconds. Default is every 1 minute.
+  evaluation_interval: 2s # Evaluate rules every 15 seconds. The default is every 1 minute.
   # scrape_timeout is set to the global default (10s).
 
 # Alertmanager configuration
@@ -19,10 +19,8 @@ rule_files:
 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: ['prometheus:9090']
 
@@ -32,6 +30,11 @@ scrape_configs:
     static_configs:
     - targets: ['milvus_server:8080']
 
+  - job_name: 'nodeexporter'
+    scrape_interval: 5s
+    static_configs:
+      - targets: ['nodeexporter:9100']
+
    # under development
   - job_name: 'pushgateway'
     static_configs: