Put instance, alias and job in quotes in Proemtheus alert messages

Author: DifferentialOrange

example/prometheus/alerts.yml

@@ -8,8 +8,8 @@ groups:
     labels:
       severity: page
     annotations:
-      summary: "Instance {{ $labels.instance }} ({{ $labels.job }}) down"
-      description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than a minute."
+      summary: "Instance '{{ $labels.instance }}' ('{{ $labels.job }}') down"
+      description: "'{{ $labels.instance }}' of job '{{ $labels.job }}' has been down for more than a minute."
 
 
 - name: tarantool-common
@@ -21,8 +21,8 @@ groups:
     labels:
       severity: warning
     annotations:
-      summary: "Instance {{ $labels.alias }} ({{ $labels.job }}) Lua runtime warning"
-      description: "{{ $labels.alias }} instance of job {{ $labels.job }} uses too much Lua memory
+      summary: "Instance '{{ $labels.alias }}' ('{{ $labels.job }}') Lua runtime warning"
+      description: "'{{ $labels.alias }}' instance of job '{{ $labels.job }}' uses too much Lua memory
         and may hit threshold soon."
 
   # Alert for any instance that uses too Lua runtime memory.
@@ -32,8 +32,8 @@ groups:
     labels:
       severity: page
     annotations:
-      summary: "Instance {{ $labels.alias }} ({{ $labels.job }}) Lua runtime alert"
-      description: "{{ $labels.alias }} instance of job {{ $labels.job }} uses too much Lua memory
+      summary: "Instance '{{ $labels.alias }}' ('{{ $labels.job }}') Lua runtime alert"
+      description: "'{{ $labels.alias }}' instance of job '{{ $labels.job }}' uses too much Lua memory
         and likely to hit threshold soon."
 
   # Warning for any instance that have low remaining arena memory.
@@ -43,8 +43,8 @@ groups:
     labels:
       severity: warning
     annotations:
-      summary: "Instance {{ $labels.alias }} ({{ $labels.job }}) low arena memory remaining"
-      description: "Low arena memory (tuples and indexes) remaining for {{ $labels.alias }} instance of job {{ $labels.job }}.
+      summary: "Instance '{{ $labels.alias }}' ('{{ $labels.job }}') low arena memory remaining"
+      description: "Low arena memory (tuples and indexes) remaining for '{{ $labels.alias }}' instance of job '{{ $labels.job }}'.
         Consider increasing memtx_memory or number of storages in case of sharded data."
 
   # Alert for any instance that have low remaining arena memory.
@@ -54,8 +54,8 @@ groups:
     labels:
       severity: page
     annotations:
-      summary: "Instance {{ $labels.alias }} ({{ $labels.job }}) low arena memory remaining"
-      description: "Low arena memory (tuples and indexes) remaining for {{ $labels.alias }} instance of job {{ $labels.job }}.
+      summary: "Instance '{{ $labels.alias }}' ('{{ $labels.job }}') low arena memory remaining"
+      description: "Low arena memory (tuples and indexes) remaining for '{{ $labels.alias }}' instance of job '{{ $labels.job }}'.
       You are likely to hit limit soon.
       It is strongly recommended to increase memtx_memory or number of storages in case of sharded data."
 
@@ -66,8 +66,8 @@ groups:
     labels:
       severity: warning
     annotations:
-      summary: "Instance {{ $labels.alias }} ({{ $labels.job }}) low items memory remaining"
-      description: "Low items memory (tuples) remaining for {{ $labels.alias }} instance of job {{ $labels.job }}.
+      summary: "Instance '{{ $labels.alias }}' ('{{ $labels.job }}') low items memory remaining"
+      description: "Low items memory (tuples) remaining for '{{ $labels.alias }}' instance of job '{{ $labels.job }}'.
         Consider increasing memtx_memory or number of storages in case of sharded data."
 
   # Alert for any instance that have low remaining arena memory.
@@ -77,8 +77,8 @@ groups:
     labels:
       severity: page
     annotations:
-      summary: "Instance {{ $labels.alias }} ({{ $labels.job }}) low items memory remaining"
-      description: "Low items memory (tuples) remaining for {{ $labels.alias }} instance of job {{ $labels.job }}.
+      summary: "Instance '{{ $labels.alias }}' ('{{ $labels.job }}') low items memory remaining"
+      description: "Low items memory (tuples) remaining for '{{ $labels.alias }}' instance of job '{{ $labels.job }}'.
         You are likely to hit limit soon.
         It is strongly recommended to increase memtx_memory or number of storages in case of sharded data."
 
@@ -89,8 +89,8 @@ groups:
     labels:
       severity: warning
     annotations:
-      summary: "Instance {{ $labels.alias }} ({{ $labels.job }}) has 'warning'-level Cartridge issues"
-      description: "Instance {{ $labels.alias }} of job {{ $labels.job }} has 'warning'-level Cartridge issues.
+      summary: "Instance '{{ $labels.alias }}' ('{{ $labels.job }}') has 'warning'-level Cartridge issues"
+      description: "Instance '{{ $labels.alias }}' of job '{{ $labels.job }}' has 'warning'-level Cartridge issues.
         Possible reasons: high replication lag, replication long idle,
         failover or switchover issues, clock issues, memory fragmentation,
         configuration issues, alien members."
@@ -102,8 +102,8 @@ groups:
     labels:
       severity: page
     annotations:
-      summary: "Instance {{ $labels.alias }} ({{ $labels.job }}) has 'critical'-level Cartridge issues"
-      description: "Instance {{ $labels.alias }} of job {{ $labels.job }} has 'critical'-level Cartridge issues.
+      summary: "Instance '{{ $labels.alias }}' ('{{ $labels.job }}') has 'critical'-level Cartridge issues"
+      description: "Instance '{{ $labels.alias }}' of job '{{ $labels.job }}' has 'critical'-level Cartridge issues.
         Possible reasons: replication process critical fail,
         running out of available memory."
 
@@ -114,8 +114,8 @@ groups:
     labels:
       severity: warning
     annotations:
-      summary: "Instance {{ $labels.alias }} ({{ $labels.job }}) have high replication lag"
-      description: "Instance {{ $labels.alias }} of job {{ $labels.job }} have high replication lag,
+      summary: "Instance '{{ $labels.alias }}' ('{{ $labels.job }}') have high replication lag"
+      description: "Instance '{{ $labels.alias }}' of job '{{ $labels.job }}' have high replication lag,
         check up your network and cluster state."
 
 - name: tarantool-business
@@ -130,9 +130,9 @@ groups:
     labels:
       severity: warning
     annotations:
-      summary: "Instance {{ $labels.alias }} ({{ $labels.job }}) high HTTP latency"
+      summary: "Instance '{{ $labels.alias }}' ('{{ $labels.job }}') high HTTP latency"
       description: "Some {{ $labels.method }} requests to {{ $labels.path }} path with {{ $labels.status }} response status
-        on {{ $labels.alias }} instance of job {{ $labels.job }} are processed too long."
+        on '{{ $labels.alias }}' instance of job '{{ $labels.job }}' are processed too long."
 
   # Warning for any endpoint of an instance in tarantool_app job that sends too much 4xx responses.
   # Beware that metric name depends on name of the collector you use in HTTP metrics middleware
@@ -144,9 +144,9 @@ groups:
     labels:
       severity: warning
     annotations:
-      summary: "Instance {{ $labels.alias }} ({{ $labels.job }}) high rate of client error responses"
+      summary: "Instance '{{ $labels.alias }}' ('{{ $labels.job }}') high rate of client error responses"
       description: "Too many {{ $labels.method }} requests to {{ $labels.path }} path 
-        on {{ $labels.alias }} instance of job {{ $labels.job }} get client error (4xx) responses."
+        on '{{ $labels.alias }}' instance of job '{{ $labels.job }}' get client error (4xx) responses."
 
   # Warning for any endpoint in tarantool_app job that sends too much 4xx responses (cluster overall).
   # Beware that metric name depends on name of the collector you use in HTTP metrics middleware
@@ -158,9 +158,9 @@ groups:
     labels:
       severity: warning
     annotations:
-      summary: "Job {{ $labels.job }} high rate of client error responses"
+      summary: "Job '{{ $labels.job }}' high rate of client error responses"
       description: "Too many {{ $labels.method }} requests to {{ $labels.path }} path
-        on instances of job {{ $labels.job }} get client error (4xx) responses."
+        on instances of job '{{ $labels.job }}' get client error (4xx) responses."
 
   # Warning for any endpoint of an instance in tarantool_app job that sends 5xx responses.
   # Beware that metric name depends on name of the collector you use in HTTP metrics middleware
@@ -172,9 +172,9 @@ groups:
     labels:
       severity: warning
     annotations:
-      summary: "Instance {{ $labels.alias }} ({{ $labels.job }}) server error responses"
+      summary: "Instance '{{ $labels.alias }}' ('{{ $labels.job }}') server error responses"
       description: "Some {{ $labels.method }} requests to {{ $labels.path }} path 
-        on {{ $labels.alias }} instance of job {{ $labels.job }} get server error (5xx) responses."
+        on '{{ $labels.alias }}' instance of job '{{ $labels.job }}' get server error (5xx) responses."
 
   # Warning for any endpoint of a router instance (with "router" in alias) in tarantool_app job that gets too little requests.
   # Beware that metric name depends on name of the collector you use in HTTP metrics middleware
@@ -186,6 +186,6 @@ groups:
     labels:
       severity: warning
     annotations:
-      summary: "Router {{ $labels.alias }} ({{ $labels.job }}) low activity"
-      description: Router {{ $labels.alias }} instance of job {{ $labels.job }} gets too little requests.
+      summary: "Router '{{ $labels.alias }}' ('{{ $labels.job }}') low activity"
+      description: Router '{{ $labels.alias }}' instance of job '{{ $labels.job }}' gets too little requests.
         Please, check up your balancer middleware."