summaryrefslogtreecommitdiffstats
path: root/health/health.d/postgres.conf
blob: 67b25673bc2bb8bf08330cf0f1c061325242d63f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
# you can disable an alarm notification by setting the 'to' line to: silent

 template: postgres_total_connection_utilization
       on: postgres.connections_utilization
    class: Utilization
     type: Database
component: PostgreSQL
    hosts: *
   lookup: average -1m unaligned of used
    units: %
    every: 1m
     warn: $this > (($status >= $WARNING)  ? (70) : (80))
     crit: $this > (($status == $CRITICAL) ? (80) : (90))
    delay: down 15m multiplier 1.5 max 1h
     info: average total connection utilization over the last minute
       to: dba

 template: postgres_acquired_locks_utilization
       on: postgres.locks_utilization
    class: Utilization
     type: Database
component: PostgreSQL
    hosts: *
   lookup: average -1m unaligned of used
    units: %
    every: 1m
     warn: $this > (($status >= $WARNING)  ? (15) : (20))
    delay: down 15m multiplier 1.5 max 1h
     info: average acquired locks utilization over the last minute
       to: dba

 template: postgres_txid_exhaustion_perc
       on: postgres.txid_exhaustion_perc
    class: Utilization
     type: Database
component: PostgreSQL
    hosts: *
     calc: $txid_exhaustion	
    units: %
    every: 1m
     warn: $this > 90
    delay: down 15m multiplier 1.5 max 1h
     info: percent towards TXID wraparound
       to: dba

# Database alarms

 template: postgres_db_cache_io_ratio
       on: postgres.db_cache_io_ratio
    class: Workload
     type: Database
component: PostgreSQL
    hosts: *
   lookup: average -1m unaligned of miss
     calc: 100 - $this
    units: %
    every: 1m
     warn: $this < (($status >= $WARNING)  ? (70) : (60))
     crit: $this < (($status == $CRITICAL) ? (60) : (50))
    delay: down 15m multiplier 1.5 max 1h
     info: average cache hit ratio in db ${label:database} over the last minute
       to: dba

 template: postgres_db_transactions_rollback_ratio	
       on: postgres.db_transactions_ratio
    class: Workload
     type: Database
component: PostgreSQL
    hosts: *
   lookup: average -5m unaligned of rollback
    units: %
    every: 1m
     warn: $this > (($status >= $WARNING)  ? (0) : (2))
    delay: down 15m multiplier 1.5 max 1h
     info: average aborted transactions percentage in db ${label:database} over the last five minutes
       to: dba

 template: postgres_db_deadlocks_rate
       on: postgres.db_deadlocks_rate
    class: Errors
     type: Database
component: PostgreSQL
    hosts: *
   lookup: sum -1m unaligned of deadlocks
    units: deadlocks
    every: 1m
     warn: $this > (($status >= $WARNING)  ? (0) : (10))
    delay: down 15m multiplier 1.5 max 1h
     info: number of deadlocks detected in db ${label:database} in the last minute
       to: dba

# Table alarms

 template: postgres_table_cache_io_ratio
       on: postgres.table_cache_io_ratio
    class: Workload
     type: Database
component: PostgreSQL
    hosts: *
   lookup: average -1m unaligned of miss
     calc: 100 - $this
    units: %
    every: 1m
     warn: $this < (($status >= $WARNING)  ? (70) : (60))
     crit: $this < (($status == $CRITICAL) ? (60) : (50))
    delay: down 15m multiplier 1.5 max 1h
     info: average cache hit ratio in db ${label:database} table ${label:table} over the last minute
       to: dba

 template: postgres_table_index_cache_io_ratio
       on: postgres.table_index_cache_io_ratio
    class: Workload
     type: Database
component: PostgreSQL
    hosts: *
   lookup: average -1m unaligned of miss
     calc: 100 - $this
    units: %
    every: 1m
     warn: $this < (($status >= $WARNING)  ? (70) : (60))
     crit: $this < (($status == $CRITICAL) ? (60) : (50))
    delay: down 15m multiplier 1.5 max 1h
     info: average index cache hit ratio in db ${label:database} table ${label:table} over the last minute
       to: dba

 template: postgres_table_toast_cache_io_ratio
       on: postgres.table_toast_cache_io_ratio
    class: Workload
     type: Database
component: PostgreSQL
    hosts: *
   lookup: average -1m unaligned of miss
     calc: 100 - $this
    units: %
    every: 1m
     warn: $this < (($status >= $WARNING)  ? (70) : (60))
     crit: $this < (($status == $CRITICAL) ? (60) : (50))
    delay: down 15m multiplier 1.5 max 1h
     info: average TOAST hit ratio in db ${label:database} table ${label:table} over the last minute
       to: dba

 template: postgres_table_toast_index_cache_io_ratio
       on: postgres.table_toast_index_cache_io_ratio
    class: Workload
     type: Database
component: PostgreSQL
    hosts: *
   lookup: average -1m unaligned of miss
     calc: 100 - $this
    units: %
    every: 1m
     warn: $this < (($status >= $WARNING)  ? (70) : (60))
     crit: $this < (($status == $CRITICAL) ? (60) : (50))
    delay: down 15m multiplier 1.5 max 1h
     info: average index TOAST hit ratio in db ${label:database} table ${label:table} over the last minute
       to: dba

 template: postgres_table_bloat_size_perc
       on: postgres.table_bloat_size_perc
    class: Errors
     type: Database
component: PostgreSQL
    hosts: *
     calc: ($table_size > (1024 * 1024 * 100)) ? ($bloat) : (0)
    units: %
    every: 1m
     warn: $this > (($status >= $WARNING)  ? (60) : (70))
     crit: $this > (($status == $CRITICAL) ? (70) : (80))
    delay: down 15m multiplier 1.5 max 1h
     info: bloat size percentage in db ${label:database} table ${label:table}
       to: dba

 template: postgres_table_last_autovacuum_time
       on: postgres.table_autovacuum_since_time
    class: Errors
     type: Database
component: PostgreSQL
    hosts: !*
     calc: $time
    units: seconds
    every: 1m
     warn: $this != nan AND $this > (60 * 60 * 24 * 7)
     info: time elapsed since db ${label:database} table ${label:table} was vacuumed by the autovacuum daemon
       to: dba

 template: postgres_table_last_autoanalyze_time
       on: postgres.table_autoanalyze_since_time
    class: Errors
     type: Database
component: PostgreSQL
    hosts: !*
     calc: $time
    units: seconds
    every: 1m
     warn: $this != nan AND $this > (60 * 60 * 24 * 7)
     info: time elapsed since db ${label:database} table ${label:table} was analyzed by the autovacuum daemon
       to: dba

# Index alarms

 template: postgres_index_bloat_size_perc
       on: postgres.index_bloat_size_perc
    class: Errors
     type: Database
component: PostgreSQL
    hosts: *
     calc: ($index_size > (1024 * 1024 * 10)) ? ($bloat) : (0)
    units: %
    every: 1m
     warn: $this > (($status >= $WARNING)  ? (60) : (70))
     crit: $this > (($status == $CRITICAL) ? (70) : (80))
    delay: down 15m multiplier 1.5 max 1h
     info: bloat size percentage in db ${label:database} table ${label:table} index ${label:index}
       to: dba