feat(sherlock): Implemented prometheus scraper

Author: isala404

gazer/deployment.yaml

@@ -150,17 +150,27 @@ spec:
         app: prometheus
     spec:
       serviceAccountName: gazer
+      securityContext:
+        runAsUser: 65534
+        runAsNonRoot: true
+        runAsGroup: 65534
+        fsGroup: 65534
       containers:
         - name: prometheus
           image: prom/prometheus:v2.33.1
+          args:
+            [
+              "--storage.tsdb.path=/data",
+              "--config.file=/etc/prometheus/prometheus.yml",
+            ]
           ports:
             - containerPort: 9090
               name: default
           volumeMounts:
             - name: config-volume
               mountPath: /etc/prometheus
             - name: prom-pvc
-              mountPath: /etc/prometheus/data
+              mountPath: /data
       volumes:
         - name: config-volume
           configMap:
@@ -177,7 +187,6 @@ metadata:
 spec:
   accessModes:
     - ReadWriteOnce
-  volumeMode: Filesystem
   resources:
     requests:
       storage: 8Gi

sherlock/.gitignore

@@ -0,0 +1 @@
+data/*.json

sherlock/data/.gitkeep

@@ -0,0 +1,3 @@
+prometheus-api-client~=0.5.0
+tqdm~=4.62.3
+matplotlib~=3.5.1

sherlock/requirements.txt

@@ -0,0 +1,37 @@
+from prometheus_api_client import PrometheusConnect, MetricRangeDataFrame
+from prometheus_api_client.utils import parse_datetime
+from tqdm import tqdm
+
+prom = PrometheusConnect(url="http://127.0.0.1:9090", disable_ssl=True)
+
+queries = [
+    {'name': 'requests_sent_per_minute', "query": 'rate(requests_sent_total[1m])'},
+    {'name': 'requests_received_per_minute', "query": 'sum by (serviceName) (rate(requests_received_total[1m]))'},
+    {'name': 'requests_duration_per_minute', "query": 'rate(request_duration_seconds_sum[1m])'},
+    {'name': 'cpu_usage', "query": 'avg_over_time(cpu_seconds[1m])'},
+    {'name': 'memory_usage', "query": 'avg_over_time(memory_usage_bytes[1m])'},
+    {'name': 'acknowledged_bytes_per_minute', "query": 'rate(acknowledged_bytes_sum[1m])'},
+    {'name': 'acknowledged_bytes_per_minute', "query": 'rate(transmitted_bytes_sum[1m])'},
+    {'name': 'syn_backlog_per_minute', "query": 'avg_over_time(backlog{level="1"}[1m])'},
+    {'name': 'high_syn_backlog_per_minute', "query": 'sum by (serviceName) (avg_over_time(backlog{level!="1"}[1m]))'},
+]
+
+
+for query in tqdm(queries):
+
+    start_time = parse_datetime("1d")
+    end_time = parse_datetime("now")
+
+    metric_data = prom.custom_query_range(
+        query['query'],  # this is the metric name and label config
+        start_time=start_time,
+        end_time=end_time,
+        step="14",
+    )
+
+    metric_df = MetricRangeDataFrame(metric_data, columns=['timestamp', 'serviceName', 'value'])
+
+    metric_df['value'] = metric_df['value'].apply(float)
+    metric_df.reset_index(inplace=True)
+
+    metric_df.to_json(f"data/{query['name']}.json", orient="records", indent=4)