From c8be07c4038db4d664f34cde3858e0bbb47b7c72 Mon Sep 17 00:00:00 2001
From: Viktor Barzin <viktorbarzin@meta.com>
Date: Mon, 6 Apr 2026 00:25:49 +0300
Subject: [PATCH] resilience improvements: MySQL anti-affinity comment,
 descheduler 5min, prometheus termination 60s

- MySQL InnoDB: keep required anti-affinity but document why (2/3 members OK during node loss)
- Descheduler: increase frequency from hourly to every 5 min for faster rebalancing
- Prometheus: set terminationGracePeriodSeconds=60 to prevent drain timeout [ci skip]
---
 stacks/dbaas/modules/dbaas/main.tf                            | 4 ++++
 stacks/descheduler/values.yaml                                | 2 +-
 .../platform/modules/monitoring/prometheus_chart_values.tpl   | 1 +
 3 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/stacks/dbaas/modules/dbaas/main.tf b/stacks/dbaas/modules/dbaas/main.tf
index 078cf571..79489348 100644
--- a/stacks/dbaas/modules/dbaas/main.tf
+++ b/stacks/dbaas/modules/dbaas/main.tf
@@ -237,6 +237,10 @@ resource "helm_release" "mysql_cluster" {
           }
         }
         podAntiAffinity = {
+          # Required anti-affinity: MySQL pods MUST be on different nodes.
+          # During node loss, one pod will be Pending — this is acceptable because
+          # InnoDB Cluster operates with 2/3 members (OK_NO_TOLERANCE).
+          # The descheduler (every 5 min) handles violations if any occur.
           requiredDuringSchedulingIgnoredDuringExecution = [{
             labelSelector = {
               matchLabels = {
diff --git a/stacks/descheduler/values.yaml b/stacks/descheduler/values.yaml
index 771bf649..dca0d0fc 100644
--- a/stacks/descheduler/values.yaml
+++ b/stacks/descheduler/values.yaml
@@ -52,7 +52,7 @@ namespaceOverride: ""
 commonLabels: {}
 
 cronJobApiVersion: "batch/v1"
-schedule: "0 * * * *"
+schedule: "*/5 * * * *"
 suspend: false
 # startingDeadlineSeconds: 200
 successfulJobsHistoryLimit: 10
diff --git a/stacks/platform/modules/monitoring/prometheus_chart_values.tpl b/stacks/platform/modules/monitoring/prometheus_chart_values.tpl
index d536a1da..4968ff61 100755
--- a/stacks/platform/modules/monitoring/prometheus_chart_values.tpl
+++ b/stacks/platform/modules/monitoring/prometheus_chart_values.tpl
@@ -169,6 +169,7 @@ server:
       memory: 4Gi
   livenessProbeInitialDelay: 300
   readinessProbeInitialDelay: 60
+  terminationGracePeriodSeconds: 60
   strategy:
     type: Recreate
   baseURL: "https://prometheus.viktorbarzin.me"