From b3f6d05131fc98b1306ecdc2e6c0cd1172a9cfb2 Mon Sep 17 00:00:00 2001
From: Max Gautier <mg@max.gautier.name>
Date: Wed, 8 Nov 2023 12:35:20 +0100
Subject: [PATCH] Move control plane certs renewal "spread out" into the
systemd timer (#10596)
* Use RandomizedDelaySec to spread out control certificates renewal plane
If the number of control plane node is superior to 6, using (index * 10
minutes) will fail (03:60:00 is not a valid timestamp).
Compared to just fixing the jinja expression (to use a modulo for
example), this should avoid having two control planes certificates
update node being triggered at the same time.
* Make k8s-certs-renew.timer Persistent
If the control plane happens to be offline during the scheduled
certificates renewal (node failure or anything like that), we still want
the renewal to happen.
---
roles/kubernetes/control-plane/defaults/main/main.yml | 3 +--
.../control-plane/templates/k8s-certs-renew.timer.j2 | 3 +++
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/roles/kubernetes/control-plane/defaults/main/main.yml b/roles/kubernetes/control-plane/defaults/main/main.yml
index 4a9800a65..ad9456d5b 100644
--- a/roles/kubernetes/control-plane/defaults/main/main.yml
+++ b/roles/kubernetes/control-plane/defaults/main/main.yml
@@ -222,8 +222,7 @@ event_ttl_duration: "1h0m0s"
## Automatically renew K8S control plane certificates on first Monday of each month
auto_renew_certificates: false
# First Monday of each month
-auto_renew_certificates_systemd_calendar: "{{ 'Mon *-*-1,2,3,4,5,6,7 03:' ~
- groups['kube_control_plane'].index(inventory_hostname) ~ '0:00' }}"
+auto_renew_certificates_systemd_calendar: "Mon *-*-1,2,3,4,5,6,7 03:00:00"
# kubeadm renews all the certificates during control plane upgrade.
# If we have requirement like without renewing certs upgrade the cluster,
# we can opt out from the default behavior by setting kubeadm_upgrade_auto_cert_renewal to false
diff --git a/roles/kubernetes/control-plane/templates/k8s-certs-renew.timer.j2 b/roles/kubernetes/control-plane/templates/k8s-certs-renew.timer.j2
index 904f0073c..cca5aca3e 100644
--- a/roles/kubernetes/control-plane/templates/k8s-certs-renew.timer.j2
+++ b/roles/kubernetes/control-plane/templates/k8s-certs-renew.timer.j2
@@ -3,6 +3,9 @@ Description=Timer to renew K8S control plane certificates
[Timer]
OnCalendar={{ auto_renew_certificates_systemd_calendar }}
+RandomizedDelaySec={{ 10 * (groups['kube_control_plane'] | length) }}min
+FixedRandomDelay=yes
+Persistent=yes
[Install]
WantedBy=multi-user.target
--
GitLab