From 722c58ab8b4a3d74e04b0d433e4c4fbfff05a409 Mon Sep 17 00:00:00 2001
From: Gabriel mermelstein <gabrielmermelstein@gmail.com>
Date: Wed, 24 Apr 2024 17:52:22 +0300
Subject: [PATCH] Having first alert working

---
 monitoring/alert-rules.yml       | 40 +-------------------------------
 monitoring/prometheus-config.yml |  3 +++
 2 files changed, 4 insertions(+), 39 deletions(-)

diff --git a/monitoring/alert-rules.yml b/monitoring/alert-rules.yml
index 9478457..24d3dbc 100644
--- a/monitoring/alert-rules.yml
+++ b/monitoring/alert-rules.yml
@@ -1,49 +1,11 @@
----
 groups:
   - name: waku
     rules:
-      - alert: HighNimWakuNodeTraffic
-        expr: >
-          abs(
-            netdata_net_net_kilobits_persec_average{
-              family!~"^(wg|veth|br|docker).*",
-              fleet=~"(shards|waku|status|wakuv2)\\..*"
-          }) > 40000
-        for: 5m
-        annotations:
-          summary: "Too high traffic for {{ $labels.instance }}"
-          description: "Host {{ $labels.instance }} running nim-waku has {{ $labels.dimension }} traffic higher 40Mbps"
-
       - alert: HighNimWakuMemUsage
         expr: >
-          nim_gc_mem_bytes{
-            fleet=~"(shards|waku|status|wakuv2)\\..*"
-          } > 1073741824
+          nim_gc_mem_bytes{} > 1073741824
         for: 5m
         annotations:
           summary: "Too high memory usage for {{ $labels.instance }}"
           description: "Host {{ $labels.instance }} running nim-waku has GC memory usage higher 1GB"
-          current_value: "{{ $value }}"
-
-      - alert: HighNimWakuNodeOpenSockets
-        expr: >
-          netdata_ipv4_sockstat_tcp_sockets_sockets_average{
-            fleet=~"(shards|waku|status|wakuv2)\\..*"
-          } > 300
-        for: 5m
-        annotations:
-          summary: "Too high open sockets for {{ $labels.instance }}"
-          description: "Host {{ $labels.instance }} running nim-waku has more than 300 open sockets"
-          current_value: "{{ $value }}"
-
-      - record: job:waku_libp2p_peers
-        expr: libp2p_peers{fleet=~"(shards|waku|status|wakuv2)\\..*"}
-
-      - alert: NimWakuPeersDecrease
-        expr: >
-          (job:waku_libp2p_peers / avg_over_time(job:waku_libp2p_peers[12h])) < 0.50
-        for: 15m
-        annotations:
-          summary: "Drop of libp2p_peers on {{ $labels.instance }}"
-          description: "Host {{ $labels.instance }} running nim-waku has more than 50% drop of peers compared to 12h average"
           current_value: "{{ $value }}"
\ No newline at end of file
diff --git a/monitoring/prometheus-config.yml b/monitoring/prometheus-config.yml
index 5368395..322f305 100644
--- a/monitoring/prometheus-config.yml
+++ b/monitoring/prometheus-config.yml
@@ -10,6 +10,9 @@ alerting:
       static_configs:
         - targets: [ 'alertmanager:9093' ]
 
+rule_files:
+    - "./alert-rules.yml"
+
 scrape_configs:
   - job_name: cadvisor
     scrape_interval: 5s