Fine tune various alarm values. (#7322)

* Fix formatting in alarm configurations.

This makes sure everything is lined up properly so that the alarm
definitions are easier to read.

* Make TCP Accept Queue alarms much less aggressive.

This switches the alarms to use averages instead of sums, and bumps up
the trip points to be more aggressive, as both of these may be non-zero
even in normal operation of a system.

* Make softnet alarms less aggressive.

This decreases the sampling window from 10 minutes to 1 minute, switches
to using an average instead of a sum, and adjusts the trigger thresholds
to be more aggressive.

This one will need to be watched, as the resultant values may be too
lenient for some systems.

* Tweak UDP alarms to work like the TCP alarms.

Just to ensure consistency.

1 files changed, 44 insertions, 46 deletions

diff --git a/health/health.d/pihole.conf b/health/health.d/pihole.conf
index 4a1217239d..b255d35f90 100644
--- a/health/health.d/pihole.conf
+++ b/health/health.d/pihole.conf
@@ -1,5 +1,5 @@
 
- # Make sure Pi-hole is responding.
+# Make sure Pi-hole is responding.
 
 template: pihole_last_collected_secs
       on: pihole.dns_queries_total
@@ -12,56 +12,54 @@ template: pihole_last_collected_secs
     info: number of seconds since the last successful data collection
       to: webmaster
 
-  # Blocked DNS queries.
+# Blocked DNS queries.
 
- template: pihole_blocked_queries
-       on: pihole.dns_queries_percentage
-    every: 10s
-    units: %
-     calc: $blocked
-     warn: $this > ( ($status >= $WARNING ) ? ( 45 ) : ( 55 ) )
-     crit: $this > ( ($status >= $CRITICAL) ? ( 55 ) : ( 75 ) )
-    delay: up 2m down 5m
-     info: percentage of blocked dns queries for the last 24 hour
-       to: sysadmin
-
-
-  # Blocklist last update time.
-  # Default update interval is a week.
+template: pihole_blocked_queries
+      on: pihole.dns_queries_percentage
+   every: 10s
+   units: %
+    calc: $blocked
+    warn: $this > ( ($status >= $WARNING ) ? ( 45 ) : ( 55 ) )
+    crit: $this > ( ($status >= $CRITICAL) ? ( 55 ) : ( 75 ) )
+   delay: up 2m down 5m
+    info: percentage of blocked dns queries for the last 24 hour
+      to: sysadmin
 
- template: pihole_blocklist_last_update
-       on: pihole.blocklist_last_update
-    every: 10s
-    units: seconds
-     calc: $ago
-     warn: $this > 60 * 60 * 24 * 8
-     crit: $this > 60 * 60 * 24 * 8 * 2
-     info: blocklist last update time
-       to: sysadmin
 
+# Blocklist last update time.
+# Default update interval is a week.
 
-  # Gravity file check (gravity.list).
+template: pihole_blocklist_last_update
+      on: pihole.blocklist_last_update
+   every: 10s
+   units: seconds
+    calc: $ago
+    warn: $this > 60 * 60 * 24 * 8
+    crit: $this > 60 * 60 * 24 * 8 * 2
+    info: blocklist last update time
+      to: sysadmin
 
- template: pihole_blocklist_gravity_file
-       on: pihole.blocklist_last_update
-    every: 10s
-    units: boolean
-     calc: $file_exists
-     crit: $this != 1
-    delay: up 2m down 5m
-     info: gravity file existence
-       to: sysadmin
+# Gravity file check (gravity.list).
 
+template: pihole_blocklist_gravity_file
+      on: pihole.blocklist_last_update
+   every: 10s
+   units: boolean
+    calc: $file_exists
+    crit: $this != 1
+   delay: up 2m down 5m
+    info: gravity file existence
+      to: sysadmin
 
-  # Pi-hole's ability to block unwanted domains.
-  # Should be enabled. The whole point of Pi-hole!
+# Pi-hole's ability to block unwanted domains.
+# Should be enabled. The whole point of Pi-hole!
 
- template: pihole_status
-       on: pihole.unwanted_domains_blocking_status
-    every: 10s
-    units: boolean
-     calc: $enabled
-     warn: $this != 1
-    delay: up 2m down 5m
-     info: unwanted domains blocking status
-       to: sysadmin
+template: pihole_status
+      on: pihole.unwanted_domains_blocking_status
+   every: 10s
+   units: boolean
+    calc: $enabled
+    warn: $this != 1
+   delay: up 2m down 5m
+    info: unwanted domains blocking status
+      to: sysadmin