From d69234146ebab0a8c8f9a28fddd74161e5552a37 Mon Sep 17 00:00:00 2001
From: Mike Reeves <reevesmk@gmail.com>
Date: Mon, 10 Aug 2026 15:44:45 -0400
Subject: [PATCH] Let partman premake forward across the gap a stall leaves

Retention drops every child once they all age out, partman refuses to
drop the last one, and with infinite_time_partitions off it will not
premake forward from a child that far in the past. The set is left with
one stale partition and no current one, so metrics land right back in
the default.

Set infinite_time_partitions on telegraf parents, in both the repair
script and the retention subcommand, and stop blaming the launcher when
pg_cron is not loaded at all.
---
 salt/postgres/tools/sbin/so-telegraf-postgres |  5 +++-
 salt/postgres/tools/sbin/so-telegraf-repair   | 26 ++++++++++++-------
 2 files changed, 20 insertions(+), 11 deletions(-)

diff --git a/salt/postgres/tools/sbin/so-telegraf-postgres b/salt/postgres/tools/sbin/so-telegraf-postgres
index 8a85f9443..df7d16e65 100644
--- a/salt/postgres/tools/sbin/so-telegraf-postgres
+++ b/salt/postgres/tools/sbin/so-telegraf-postgres
@@ -234,10 +234,13 @@ EOSQL
 SELECT CASE WHEN EXISTS (SELECT 1 FROM pg_catalog.pg_extension WHERE extname = 'pg_partman')
             THEN 'true' ELSE 'false' END AS has_partman \gset
 \if :has_partman
+-- infinite_time_partitions so a gap in metrics does not stop partman from
+-- premaking forward, which is what leaves everything in the default.
 UPDATE partman.part_config
 SET retention = :'retention_days' || ' days',
     retention_keep_table = false,
-    premake = 7
+    premake = 7,
+    infinite_time_partitions = true
 WHERE parent_table LIKE 'telegraf.%';
 \endif
 EOSQL
diff --git a/salt/postgres/tools/sbin/so-telegraf-repair b/salt/postgres/tools/sbin/so-telegraf-repair
index 2076ea1a4..ddfa5f7d7 100644
--- a/salt/postgres/tools/sbin/so-telegraf-repair
+++ b/salt/postgres/tools/sbin/so-telegraf-repair
@@ -102,9 +102,12 @@ parents=$(psql_tg -tAc \
 stranded=$(psql_tg -tAc "SELECT coalesce(sum(default_rows), 0) FROM ( $REPORT ) t")
 behind=$(psql_tg -tAc \
   "SELECT count(*) FROM ( $REPORT ) t WHERE coalesce(days_ahead, -1) < 1")
-low_premake=$(psql_tg -tAc \
+# premake < 7, or infinite_time_partitions off: without the latter partman
+# refuses to premake forward across the gap the stall left behind.
+misconfigured=$(psql_tg -tAc \
   "SELECT count(*) FROM partman.part_config
-    WHERE parent_table LIKE 'telegraf.%' AND premake < $PREMAKE")
+    WHERE parent_table LIKE 'telegraf.%'
+      AND (premake < $PREMAKE OR NOT infinite_time_partitions)")
 
 # Both columns are matched because which one carries the launcher's name varies
 # with the pg_cron version.
@@ -124,14 +127,15 @@ if [[ -n "$cron_db" ]]; then
   [[ -n "$last_run" ]] || last_run=never
 fi
 
-# A grid that has never written a metric has nothing to recover.
+# A grid that has never written a metric has nothing to recover, and an empty
+# cron_db means pg_cron is not loaded at all, which no restart fixes.
 restart_needed=false
-[[ "$launcher" -eq 0 && "$parents" -gt 0 ]] && restart_needed=true
+[[ "$launcher" -eq 0 && "$parents" -gt 0 && -n "$cron_db" ]] && restart_needed=true
 
 repair_needed=false
 [[ "$stranded" -gt 0 ]] && repair_needed=true
 [[ "$behind" -gt 0 ]] && repair_needed=true
-[[ "$low_premake" -gt 0 ]] && repair_needed=true
+[[ "$misconfigured" -gt 0 ]] && repair_needed=true
 $restart_needed && repair_needed=true
 
 echo "Telegraf partition status:"
@@ -151,7 +155,7 @@ if $CHECK_ONLY; then
   echo "Repair is needed:"
   [[ "$stranded" -gt 0 ]]    && echo "  * $stranded row(s) stranded in default partitions"
   [[ "$behind" -gt 0 ]]      && echo "  * $behind parent(s) with no partition for the current window"
-  [[ "$low_premake" -gt 0 ]] && echo "  * $low_premake parent(s) premaking fewer than $PREMAKE days ahead"
+  [[ "$misconfigured" -gt 0 ]] && echo "  * $misconfigured parent(s) with stale partman settings"
   $restart_needed            && echo "  * pg_cron's launcher is dead; maintenance is not running at all"
   echo
   echo "Re-run without --check to repair."
@@ -167,11 +171,13 @@ if [[ "$stranded" -gt 0 ]] && ! $ASSUME_YES; then
   [[ "$answer" =~ ^[Yy]$ ]] || { echo "Aborted."; exit 0; }
 fi
 
-if [[ "$low_premake" -gt 0 ]]; then
-  echo "Raising premake to $PREMAKE on $low_premake parent(s)."
-  # GREATEST so an operator who raised it further keeps their value.
+if [[ "$misconfigured" -gt 0 ]]; then
+  echo "Reconciling partman settings on $misconfigured parent(s)."
+  # GREATEST so an operator who raised premake further keeps their value.
   psql_tg -v ON_ERROR_STOP=1 -c \
-    "UPDATE partman.part_config SET premake = GREATEST(premake, $PREMAKE)
+    "UPDATE partman.part_config
+        SET premake = GREATEST(premake, $PREMAKE),
+            infinite_time_partitions = true
       WHERE parent_table LIKE 'telegraf.%'"
 fi