From cafd0f1705aace6678d25c09277bfb012017d46c Mon Sep 17 00:00:00 2001
From: Bin Yi <byi@sumologic.com>
Date: Tue, 30 Apr 2019 09:53:19 -0700
Subject: [PATCH 1/2] remove go_* metrics

---
 deploy/helm/overrides.yaml | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/deploy/helm/overrides.yaml b/deploy/helm/overrides.yaml
index 89f0331cef..f4c24c9c18 100644
--- a/deploy/helm/overrides.yaml
+++ b/deploy/helm/overrides.yaml
@@ -131,9 +131,3 @@ prometheus:
       - action: keep
         regex: node-exporter;node_filesystem_(?:avail|free|size)_bytes
         sourceLabels: [job, __name__]
-    # golang related metrics
-    - url: http://fluentd:9888/prometheus.metrics.go
-      writeRelabelConfigs:
-      - action: keep
-        regex: go_gc_duration_seconds|go_threads|go_goroutines
-        sourceLabels: [__name__]

From d183dffdb75d062b65618cad0fb0fb8809ae7ad2 Mon Sep 17 00:00:00 2001
From: Bin Yi <byi@sumologic.com>
Date: Wed, 1 May 2019 15:48:24 -0700
Subject: [PATCH 2/2] add rule metrics and up

---
 deploy/helm/overrides.yaml               | 62 ++++++++++++++++++++++++
 deploy/kubernetes/fluentd-sumologic.yaml | 11 +++--
 2 files changed, 69 insertions(+), 4 deletions(-)

diff --git a/deploy/helm/overrides.yaml b/deploy/helm/overrides.yaml
index f4c24c9c18..de7818d14c 100644
--- a/deploy/helm/overrides.yaml
+++ b/deploy/helm/overrides.yaml
@@ -131,3 +131,65 @@ prometheus:
       - action: keep
         regex: node-exporter;node_filesystem_(?:avail|free|size)_bytes
         sourceLabels: [job, __name__]
+    # prometheus operator rules
+    - url: http://fluentd:9888/prometheus.metrics.operator.rule
+      writeRelabelConfigs:
+      - action: keep
+        regex: apiserver;cluster_quantile:apiserver_request_latencies:histogram_quantile
+        sourceLabels: [job, __name__]
+    - url: http://fluentd:9888/prometheus.metrics.operator.rule
+      writeRelabelConfigs:
+      - action: keep
+        regex: instance:node_(?:cpu|filesystem_usage|network_receive_bytes|node_network_transmit_bytes):rate:sum
+        sourceLabels: [__name__]
+    - url: http://fluentd:9888/prometheus.metrics.operator.rule
+      writeRelabelConfigs:
+      - action: keep
+        regex: instance:node_cpu:ratio|cluster:node_cpu:sum_rate5m|cluster:node_cpu:ratio
+        sourceLabels: [__name__]
+    - url: http://fluentd:9888/prometheus.metrics.operator.rule
+      writeRelabelConfigs:
+      - action: keep
+        regex: cluster_quantile:scheduler_(?:e2e_scheduling|scheduling_algorithm|binding)_latency:histogram_quantile
+        sourceLabels: [__name__]
+    - url: http://fluentd:9888/prometheus.metrics.operator.rule
+      writeRelabelConfigs:
+      - action: keep
+        regex: 'node_namespace_pod:kube_pod_info:|:kube_pod_info_node_count:'
+        sourceLabels: [__name__]
+    - url: http://fluentd:9888/prometheus.metrics.operator.rule
+      writeRelabelConfigs:
+      - action: keep
+        regex: 'node:node_num_cpu:sum|:node_cpu_utilisation:avg1m|node:node_cpu_utilisation:avg1m|node:cluster_cpu_utilisation:ratio|:node_cpu_saturation_load1:|node:node_cpu_saturation_load1:'
+        sourceLabels: [__name__]
+    - url: http://fluentd:9888/prometheus.metrics.operator.rule
+      writeRelabelConfigs:
+      - action: keep
+        regex: ':node_memory_utilisation:|:node_memory_MemFreeCachedBuffers_bytes:sum|:node_memory_MemTotal_bytes:sum|node:node_memory_bytes_available:sum|node:node_memory_bytes_total:sum|node:node_memory_utilisation:ratio|node:cluster_memory_utilisation:ratio|:node_memory_swap_io_bytes:sum_rate|node:node_memory_utilisation:|node:node_memory_utilisation_2:|node:node_memory_swap_io_bytes:sum_rate'
+        sourceLabels: [__name__]
+    - url: http://fluentd:9888/prometheus.metrics.operator.rule
+      writeRelabelConfigs:
+      - action: keep
+        regex: ':node_disk_utilisation:avg_irate|node:node_disk_utilisation:avg_irate|:node_disk_saturation:avg_irate|node:node_disk_saturation:avg_irate'
+        sourceLabels: [__name__]
+    - url: http://fluentd:9888/prometheus.metrics.operator.rule
+      writeRelabelConfigs:
+      - action: keep
+        regex: 'node:node_filesystem_usage:|node:node_filesystem_avail:'
+        sourceLabels: [__name__]
+    - url: http://fluentd:9888/prometheus.metrics.operator.rule
+      writeRelabelConfigs:
+      - action: keep
+        regex: ':node_net_utilisation:sum_irate|node:node_net_utilisation:sum_irate|:node_net_saturation:sum_irate|node:node_net_saturation:sum_irate'
+        sourceLabels: [__name__]
+    - url: http://fluentd:9888/prometheus.metrics.operator.rule
+      writeRelabelConfigs:
+      - action: keep
+        regex: 'node:node_inodes_total:|node:node_inodes_free:'
+        sourceLabels: [__name__]
+    # up metrics
+    - url: http://fluentd:9888/prometheus.metrics
+      writeRelabelConfigs:
+      - action: keep
+        regex: up
+        sourceLabels: [__name__]
diff --git a/deploy/kubernetes/fluentd-sumologic.yaml b/deploy/kubernetes/fluentd-sumologic.yaml
index a3d88f0305..6857a67556 100644
--- a/deploy/kubernetes/fluentd-sumologic.yaml
+++ b/deploy/kubernetes/fluentd-sumologic.yaml
@@ -79,7 +79,11 @@ data:
         @type protobuf
       </parse>
     </source>
-    <match prometheus.metrics.**>
+    <match prometheus.metrics.operator.rule>
+      @type datapoint
+      tag prometheus.datapoint.operator.rule
+    </match>
+    <match prometheus.metrics**>
       @type datapoint
       tag prometheus.datapoint
     </match>
@@ -91,10 +95,9 @@ data:
         tag ${tag}.$1
       </rule>
     </match>
-    <filter prometheus.datapoint.**>
+    <filter prometheus.datapoint**>
       @type carbon_v2
     </filter>
-
     <match prometheus.datapoint.apiserver**>
       @type sumologic
       endpoint "#{ENV['SUMO_ENDPOINT_METRICS_APISERVER']}"
@@ -137,7 +140,7 @@ data:
       data_type metrics
       metric_data_format carbon2
     </match>
-    <match prometheus.datapoint.**>
+    <match prometheus.datapoint**>
       @type sumologic
       endpoint "#{ENV['SUMO_ENDPOINT_METRICS']}"
       data_type metrics