take into account the chart update frequency to detect that last_collected alarms are CLEAR
Costa Tsaousis (ktsaou) committed
Oct 28, 2016 at 21:34 UTC
b8921c24c47c895ccdf35ff1c6424293b0933764
11 files changed
+24
-24
conf.d/health.d/apache.conf
+2
-2
@@ -6,8 +6,8 @@ template: apache_last_collected_secs
6
calc: $now - $last_collected_t
7
units: seconds ago
8
every: 10s
9
- warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10
- crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
9
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
10
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
11
delay: down 5m multiplier 1.5 max 1h
12
info: number of seconds since the last successful data collection
13
to: webmaster
conf.d/health.d/disks.conf
+4
-4
@@ -7,8 +7,8 @@ template: disk_space_last_collected_secs
7
calc: $now - $last_collected_t
8
units: seconds ago
9
every: 10s
10
- warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
11
- crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
10
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
11
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
12
delay: down 5m multiplier 1.5 max 1h
13
info: number of seconds since the last successful data collection of the mount point
14
to: sysadmin
@@ -19,8 +19,8 @@ template: disk_last_collected_secs
19
calc: $now - $last_collected_t
20
units: seconds ago
21
every: 10s
22
- warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
23
- crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
22
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
23
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
24
delay: down 5m multiplier 1.5 max 1h
25
info: number of seconds since the last successful data collection of the block device
26
to: sysadmin
conf.d/health.d/memcached.conf
+2
-2
@@ -6,8 +6,8 @@ template: memcached_last_collected_secs
6
calc: $now - $last_collected_t
7
units: seconds ago
8
every: 10s
9
- warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10
- crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
9
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
10
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
11
delay: down 5m multiplier 1.5 max 1h
12
info: number of seconds since the last successful data collection
13
to: dba
conf.d/health.d/mysql.conf
+2
-2
@@ -6,8 +6,8 @@ template: mysql_last_collected_secs
6
calc: $now - $last_collected_t
7
units: seconds ago
8
every: 10s
9
- warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10
- crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
9
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
10
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
11
delay: down 5m multiplier 1.5 max 1h
12
info: number of seconds since the last successful data collection
13
to: dba
conf.d/health.d/named.conf
+2
-2
@@ -6,8 +6,8 @@ template: named_last_collected_secs
6
calc: $now - $last_collected_t
7
units: seconds ago
8
every: 10s
9
- warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10
- crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
9
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
10
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
11
delay: down 5m multiplier 1.5 max 1h
12
info: number of seconds since the last successful data collection
13
to: domainadmin
conf.d/health.d/net.conf
+2
-2
@@ -6,8 +6,8 @@ template: interface_last_collected_secs
6
calc: $now - $last_collected_t
7
units: seconds ago
8
every: 10s
9
- warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10
- crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
9
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
10
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
11
delay: down 5m multiplier 1.5 max 1h
12
info: number of seconds since the last successful data collection
13
to: sysadmin
conf.d/health.d/nginx.conf
+2
-2
@@ -6,8 +6,8 @@ template: nginx_last_collected_secs
6
calc: $now - $last_collected_t
7
units: seconds ago
8
every: 10s
9
- warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10
- crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
9
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
10
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
11
delay: down 5m multiplier 1.5 max 1h
12
info: number of seconds since the last successful data collection
13
to: webmaster
conf.d/health.d/redis.conf
+2
-2
@@ -6,8 +6,8 @@ template: redis_last_collected_secs
6
calc: $now - $last_collected_t
7
units: seconds ago
8
every: 10s
9
- warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10
- crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
9
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
10
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
11
delay: down 5m multiplier 1.5 max 1h
12
info: number of seconds since the last successful data collection
13
to: dba
conf.d/health.d/retroshare.conf
+2
-2
@@ -5,8 +5,8 @@ template: retroshare_last_collected_secs
5
calc: $now - $last_collected_t
6
units: seconds ago
7
every: 10s
8
- warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
9
- crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
8
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
9
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
10
delay: down 5m multiplier 1.5 max 1h
11
info: number of seconds since the last successful data collection
12
to: sysadmin
conf.d/health.d/squid.conf
+2
-2
@@ -6,8 +6,8 @@ template: squid_last_collected_secs
6
calc: $now - $last_collected_t
7
units: seconds ago
8
every: 10s
9
- warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10
- crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
9
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
10
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
11
delay: down 5m multiplier 1.5 max 1h
12
info: number of seconds since the last successful data collection
13
to: proxyadmin
conf.d/health.d/tcp_resets.conf
+2
-2
@@ -5,8 +5,8 @@
5
calc: $now - $last_collected_t
6
units: seconds ago
7
every: 10s
8
- warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
9
- crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
8
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
9
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
10
delay: up 0 down 5m multiplier 1.5 max 1h
11
info: number of seconds since the last successful data collection
12
to: sysadmin