fix: set restart limits to 0 to prevent being marked as failed

ansible/files/adminapi.service.j2

@@ -3,9 +3,8 @@ Description=AdminAPI
 Requires=network-online.target
 After=network-online.target
 
-# Move this to the Service section if on systemd >=250
-StartLimitIntervalSec=60
-StartLimitBurst=10
+StartLimitIntervalSec=0
+StartLimitBurst=0
 
 [Service]
 Type=simple

ansible/files/gotrue.service.j2

@@ -40,9 +40,19 @@ After=network-online.target systemd-resolved.service
 Wants=postgresql.service
 After=postgresql.service
 
-# Lower start limit ival and burst to prevent the noisy flapping
-StartLimitIntervalSec=10
-StartLimitBurst=5
+# The systemd default is 10s / 5 for these values with a DefaultRestartUSec of
+# 100ms. Most services set a RestartSec limit of 3, under most circumstances it
+# takes 15s to restart 5 times so the limit of 10s is not exceeded. However if
+# other system processes (salt, cloud init) restart it explicitly, or recovering
+# system services within the --before chain trigger a restart the limit can be
+# exceeded causing it to be marked as failed. Since no services mark
+# gotrue.service as required it will remain offline until the next explicit
+# restart is issued.
+#
+# Setting these values to 0 with Restart=always and RestartSec=3 will prevent
+# gotrue from being marked as failed.
+StartLimitIntervalSec=0
+StartLimitBurst=0
 
 [Service]
 Type=exec

ansible/files/nginx.service.j2

@@ -3,6 +3,9 @@ Description=nginx server
 After=postgrest.service gotrue.service adminapi.service
 Wants=postgrest.service gotrue.service adminapi.service
 
+StartLimitIntervalSec=0
+StartLimitBurst=0
+
 [Service]
 Type=forking
 ExecStart=/usr/local/nginx/sbin/nginx -c /etc/nginx/nginx.conf

ansible/files/pg_egress_collect.service.j2

@@ -1,6 +1,9 @@
 [Unit]
 Description=Postgres Egress Collector
 
+StartLimitIntervalSec=0
+StartLimitBurst=0
+
 [Service]
 Type=simple
 ExecStart=/bin/bash -c "tcpdump -s 128 -Q out -nn -tt -vv -p -l 'tcp and (port 5432 or port 6543)' | perl /root/pg_egress_collect.pl"

ansible/files/postgres_exporter.service.j2

@@ -1,6 +1,9 @@
 [Unit]
 Description=Postgres Exporter
 
+StartLimitIntervalSec=0
+StartLimitBurst=0
+
 [Service]
 Type=simple
 ExecStart=/opt/postgres_exporter/postgres_exporter --disable-settings-metrics --extend.query-path="/opt/postgres_exporter/queries.yml" --disable-default-metrics --no-collector.locks --no-collector.replication --no-collector.replication_slot --no-collector.stat_bgwriter --no-collector.stat_database --no-collector.stat_user_tables --no-collector.statio_user_tables --no-collector.wal {% if qemu_mode is defined and qemu_mode %}--no-collector.database {% endif %}

ansible/files/postgrest.service.j2

@@ -3,6 +3,9 @@ Description=PostgREST
 Requires=postgrest-optimizations.service
 After=postgrest-optimizations.service
 
+StartLimitIntervalSec=0
+StartLimitBurst=0
+
 [Service]
 Type=simple
 # We allow the base config (sent from the worker) to override the generated config

ansible/files/vector.service.j2

@@ -4,6 +4,9 @@ Documentation=https://vector.dev
 After=network-online.target
 Requires=network-online.target
 
+StartLimitIntervalSec=0
+StartLimitBurst=0
+
 [Service]
 User=vector
 Group=vector