From 61b1a645bb776315a3a603e315675e50b3af2a65 Mon Sep 17 00:00:00 2001
From: admin <alec@bryanmail.net>
Date: Sun, 26 Jul 2026 17:34:35 -0700
Subject: [PATCH] uptime-kuma: set restart_policy.delay to 30s

Increases the delay before Swarm restarts a failed uptime-kuma task
from the default 5s to 30s. Applied live via `docker service update
--restart-delay 30s` on 2026-07-26; this persists it so it survives
the next stack deploy.

Note: this does not pin the task to a specific node or prevent
cross-node reschedule races against the CephFS-backed SQLite data
dir - it only slows the restart-after-failure loop. See prior
incident notes for the DB corruption root cause discussion.
---
 maintenance/maintenance.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/maintenance/maintenance.yaml b/maintenance/maintenance.yaml
index 05955d4..4699573 100644
--- a/maintenance/maintenance.yaml
+++ b/maintenance/maintenance.yaml
@@ -66,6 +66,8 @@ services:
         max-size: "10m"
         max-file: "3"
     deploy:
+      restart_policy:
+        delay: 30s
       labels:
         - traefik.enable=true
         - traefik.http.routers.uptime.rule=Host(`uptime.${DOMAIN}`)