From 178afe4a9bc682f85fc40d72609b2cfc547febca Mon Sep 17 00:00:00 2001
From: Dalton Hubble <dghubble@gmail.com>
Date: Sun, 8 Dec 2019 22:05:15 -0800
Subject: [PATCH] Reduce apiserver metrics cardinality and extraneous labels

* Stop mapping node labels to targets discovered via Kubernetes
nodes (e.g. etcd, kubelet, cadvisor). It is rarely useful to
store node labels (e.g. kubernetes.io/os=linux) on these metrics
* kube-apiserver's apiserver_request_duration_seconds_bucket metric
has a high cardinality that includes labels for the API group, verb,
scope, resource, and component for each object type, including for
each CRD. This one metric has ~10k time series in a typical cluster
(btw 10-40% of total)
* Removing the apiserver request duration outright would make latency
alerts a NoOp and break a Grafana apiserver panel. Instead, drop series
that have a "group" label. Effectively, only request durations for
core Kubernetes APIs will be kept (e.g. cardinality won't grow with
each CRD added). This reduces the metric to ~2k unique series
---
 CHANGES.md                    |  1 +
 addons/prometheus/config.yaml | 25 ++++++++++++++-----------
 2 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/CHANGES.md b/CHANGES.md
index 9ce519d6..7e36d0b6 100644
--- a/CHANGES.md
+++ b/CHANGES.md
@@ -28,6 +28,7 @@ Notable changes between versions.
 * Update Grafana from v6.4.4 to [v6.5.1](https://grafana.com/docs/guides/whats-new-in-v6-5/)
 * Add pod networking details in dashboards ([#593](https://github.com/poseidon/typhoon/pull/593))
 * Add node alerts and Grafana dashboard from node-exporter ([#591](https://github.com/poseidon/typhoon/pull/591))
+* Reduce Prometheus time series of high cardinality metrics ([#596](https://github.com/poseidon/typhoon/pull/596))
 
 ## v1.16.3
 
diff --git a/addons/prometheus/config.yaml b/addons/prometheus/config.yaml
index 298c4edc..38b7472f 100644
--- a/addons/prometheus/config.yaml
+++ b/addons/prometheus/config.yaml
@@ -65,6 +65,9 @@ data:
       - source_labels: [__name__]
         action: drop
         regex: apiserver_admission_step_admission_latencies_seconds_.*
+      - source_labels: [__name__, group]
+        regex: apiserver_request_duration_seconds_bucket;.+
+        action: drop
 
     # Scrape config for node (i.e. kubelet) /metrics (e.g. 'kubelet_'). Explore
     # metrics from a node by scraping kubelet (127.0.0.1:10250/metrics).
@@ -81,7 +84,7 @@ data:
 
       relabel_configs:
       - action: labelmap
-        regex: __meta_kubernetes_node_label_(.+)
+        regex: __meta_kubernetes_node_name
 
     # Scrape config for Kubelet cAdvisor. Explore metrics from a node by
     # scraping kubelet (127.0.0.1:10250/metrics/cadvisor).
@@ -99,7 +102,7 @@ data:
 
       relabel_configs:
       - action: labelmap
-        regex: __meta_kubernetes_node_label_(.+)
+        regex: __meta_kubernetes_node_name
       metric_relabel_configs:
       - source_labels: [__name__, image]
         action: drop
@@ -115,15 +118,15 @@ data:
       - role: node
       scheme: http
       relabel_configs:
-        - source_labels: [__meta_kubernetes_node_label_node_kubernetes_io_controller]
-          action: keep
-          regex: 'true'
-        - action: labelmap
-          regex: __meta_kubernetes_node_label_(.+)
-        - source_labels: [__meta_kubernetes_node_address_InternalIP]
-          action: replace
-          target_label: __address__
-          replacement: '${1}:2381'
+      - source_labels: [__meta_kubernetes_node_label_node_kubernetes_io_controller]
+        action: keep
+        regex: 'true'
+      - action: labelmap
+        regex: __meta_kubernetes_node_name
+      - source_labels: [__meta_kubernetes_node_address_InternalIP]
+        action: replace
+        target_label: __address__
+        replacement: '${1}:2381'
     
     # Scrape config for service endpoints.
     #