From 094aa1eb7e1e082bdf8a2a23fe4d583d52691e4d Mon Sep 17 00:00:00 2001
From: Daniel Berteaud <dbd@ehtrace.com>
Date: Tue, 26 Mar 2024 17:05:51 +0100
Subject: [PATCH] Update vector and double thres for Context Switch alert

---
 example/agent.nomad.hcl             | 2 +-
 example/images/vector/Dockerfile    | 2 +-
 example/services.nomad.hcl          | 6 +++---
 templates/prometheus/rules/node.yml | 4 ++--
 variables.yml                       | 2 +-
 5 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/example/agent.nomad.hcl b/example/agent.nomad.hcl
index 0406a0e..b875423 100644
--- a/example/agent.nomad.hcl
+++ b/example/agent.nomad.hcl
@@ -296,7 +296,7 @@ _EOT
       leader = true
 
       config {
-        image           = "danielberteaud/vector:0.36.1-1"
+        image           = "danielberteaud/vector:0.37.0-1"
         userns_mode     = "host"
         readonly_rootfs = true
         pids_limit      = 200
diff --git a/example/images/vector/Dockerfile b/example/images/vector/Dockerfile
index 4b231a4..338ad0e 100644
--- a/example/images/vector/Dockerfile
+++ b/example/images/vector/Dockerfile
@@ -1 +1 @@
-FROM timberio/vector:0.36.1-alpine
+FROM timberio/vector:0.37.0-alpine
diff --git a/example/services.nomad.hcl b/example/services.nomad.hcl
index cf8c94e..7af9208 100644
--- a/example/services.nomad.hcl
+++ b/example/services.nomad.hcl
@@ -1116,13 +1116,13 @@ groups:
         description: "Time spent in IO is too high on {{ $labels.instance }}. Check storage for issues.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostContextSwitching
-      expr: '((rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 10000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+      expr: '((rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 20000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
       for: 0m
       labels:
         severity: warning
       annotations:
         summary: Host context switching (instance {{ $labels.instance }})
-        description: "Context switching is growing on the node (> 10000 / CPU / s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+        description: "Context switching is growing on the node (> 20000 / CPU / s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
 #    - alert: HostSwapIsFillingUp
 #      expr: '((1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
@@ -2096,7 +2096,7 @@ _EOT
       leader = true
 
       config {
-        image           = "danielberteaud/vector:0.36.1-1"
+        image           = "danielberteaud/vector:0.37.0-1"
         readonly_rootfs = true
         pids_limit      = 200
         args            = ["--config=/local/vector.yml"]
diff --git a/templates/prometheus/rules/node.yml b/templates/prometheus/rules/node.yml
index df796c9..c701caa 100644
--- a/templates/prometheus/rules/node.yml
+++ b/templates/prometheus/rules/node.yml
@@ -176,13 +176,13 @@ groups:
         description: "Time spent in IO is too high on {{ $labels.instance }}. Check storage for issues.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostContextSwitching
-      expr: '((rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 10000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+      expr: '((rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 20000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
       for: 0m
       labels:
         severity: warning
       annotations:
         summary: Host context switching (instance {{ $labels.instance }})
-        description: "Context switching is growing on the node (> 10000 / CPU / s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+        description: "Context switching is growing on the node (> 20000 / CPU / s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
 #    - alert: HostSwapIsFillingUp
 #      expr: '((1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
diff --git a/variables.yml b/variables.yml
index 0a817c0..da1c39e 100644
--- a/variables.yml
+++ b/variables.yml
@@ -262,7 +262,7 @@ monitoring:
   # Common vector settings
   vector:
     # Version of vector
-    version: 0.36.1
+    version: 0.37.0
     # Docker image to use
     image: '[[ .docker.repo ]]vector:[[ .monitoring.vector.version ]]-1'