Permalink
Browse files

updated alarms to take into account the alarm status examination

  • Loading branch information...
1 parent ab90e33 commit b7261c269139a576e98c3c03a5dc4d2337044f8f @ktsaou ktsaou committed Sep 14, 2016
@@ -6,9 +6,9 @@ template: apache_last_collected_secs
calc: $now - $last_collected_t
units: seconds ago
every: 10s
- warn: $this > ( 5 * $update_every)
- crit: $this > (60 * $update_every)
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
info: number of seconds since the last successful data collection
to: webmaster
@@ -4,9 +4,9 @@ template: 10min_cpu_usage
lookup: average -10m unaligned of user,system,nice,softirq,irq,guest,guest_nice
units: %
every: 1m
- warn: $this > 80
- crit: $this > 90
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (70) : (80))
+ crit: $this > (($status == $CRITICAL) ? (80) : (90))
+ delay: down 15m multiplier 1.5 max 1h
info: average cpu utilization for the last 10 minutes
to: sysadmin
@@ -15,9 +15,9 @@ template: 10min_cpu_iowait
lookup: average -10m unaligned of iowait
units: %
every: 1m
- warn: $this > 10
- crit: $this > 30
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (5) : (10))
+ crit: $this > (($status == $CRITICAL) ? (20) : (30))
+ delay: down 15m multiplier 1.5 max 1h
info: average CPU wait I/O for the last 10 minutes
to: sysadmin
@@ -26,8 +26,8 @@ template: 20min_steal_cpu
lookup: average -20m unaligned of steal
units: %
every: 5m
- warn: $this > 10
- crit: $this > 30
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (5) : (10))
+ crit: $this > (($status == $CRITICAL) ? (20) : (30))
+ delay: down 15m multiplier 1.5 max 1h
info: average CPU steal time for the last 20 minutes
to: sysadmin
@@ -7,9 +7,9 @@ template: disk_space_last_collected_secs
calc: $now - $last_collected_t
units: seconds ago
every: 10s
- warn: $this > ( 5 * $update_every)
- crit: $this > (60 * $update_every)
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
info: number of seconds since the last successful data collection of the mount point
to: sysadmin
@@ -19,9 +19,9 @@ template: disk_last_collected_secs
calc: $now - $last_collected_t
units: seconds ago
every: 10s
- warn: $this > ( 5 * $update_every)
- crit: $this > (60 * $update_every)
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
info: number of seconds since the last successful data collection of the block device
to: sysadmin
@@ -38,8 +38,8 @@ template: disk_space_usage
calc: $used * 100 / ($avail + $used)
units: %
every: 1m
- warn: $this > 80
- crit: $this > 95
+ warn: $this > (($status >= $WARNING ) ? (70) : (80))
+ crit: $this > (($status == $CRITICAL) ? (85) : (95))
delay: up 1m down 15m multiplier 1.5 max 1h
info: current disk space usage
to: sysadmin
@@ -49,8 +49,8 @@ template: disk_inode_usage
calc: $used * 100 / ($avail + $used)
units: %
every: 1m
- warn: $this > 80
- crit: $this > 95
+ warn: $this > (($status >= $WARNING) ? (75) : (80))
+ crit: $this > (($status == $CRITICAL) ? (90) : (95))
delay: up 1m down 15m multiplier 1.5 max 1h
info: current disk inode usage
to: sysadmin
@@ -85,9 +85,9 @@ template: out_of_disk_space_time
calc: $avail / $disk_fill_rate
units: hours
every: 10s
- warn: $this > 0 and $this < 8
- crit: $this > 0 and $this < 2
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > 0 and $this < (($status >= $WARNING) ? (48) : (8))
+ crit: $this > 0 and $this < (($status == $CRITICAL) ? (24) : (2))
+ delay: down 15m multiplier 1.2 max 1h
info: estimated time the disk will run out of space, if the system continues to add data with the rate of the last hour
to: sysadmin
@@ -106,9 +106,9 @@ template: 10min_disk_utilization
every: 1m
green: 90
red: 98
- warn: $this > $green
- crit: $this > $red
- delay: up 0 down 30m multiplier 1.5 max 1h
+ warn: $this > $green * (($status >= $WARNING) ? (0.7) : (1))
+ crit: $this > $red * (($status == $CRITICAL) ? (0.7) : (1))
+ delay: down 15m multiplier 1.2 max 1h
info: the percentage of time the disk was busy, during the last 10 minutes
to: sysadmin
@@ -125,8 +125,8 @@ template: 10min_disk_backlog
every: 1m
green: 2000
red: 5000
- warn: $this > $green
- crit: $this > $red
- delay: up 1m down 30m multiplier 1.5 max 1h
+ warn: $this > $green * (($status >= $WARNING) ? (0.7) : (1))
+ crit: $this > $red * (($status == $CRITICAL) ? (0.7) : (1))
+ delay: down 15m multiplier 1.2 max 1h
info: average of the kernel estimated disk backlog, for the last 10 minutes
to: sysadmin
@@ -8,7 +8,7 @@
lookup: min -1h unaligned
units: entries
every: 5m
- warn: $this < 100
- delay: up 0 down 1h multiplier 1.5 max 1h
+ warn: $this < (($status >= $WARNING) ? (200) : (100))
+ delay: down 1h multiplier 1.5 max 1h
info: minimum entries in the random numbers pool in the last 30 minutes
to: sysadmin
@@ -6,9 +6,9 @@ template: memcached_last_collected_secs
calc: $now - $last_collected_t
units: seconds ago
every: 10s
- warn: $this > ( 5 * $update_every)
- crit: $this > (60 * $update_every)
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
info: number of seconds since the last successful data collection
to: dba
@@ -20,8 +20,8 @@ template: memcached_cache_memory_usage
calc: $used * 100 / ($used + $available)
units: %
every: 10s
- warn: $this > 80
- crit: $this > 90
+ warn: $this > (($status >= $WARNING) ? (70) : (80))
+ crit: $this > (($status == $CRITICAL) ? (80) : (90))
delay: up 0 down 15m multiplier 1.5 max 1h
info: current cache memory usage
to: dba
@@ -45,8 +45,8 @@ template: out_of_cache_space_time
calc: $available / $cache_fill_rate
units: hours
every: 10s
- warn: $this > 0 and $this < 8
- crit: $this > 0 and $this < 2
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > 0 and $this < (($status >= $WARNING) ? (48) : (8))
+ crit: $this > 0 and $this < (($status == $CRITICAL) ? (24) : (2))
+ delay: down 15m multiplier 1.5 max 1h
info: estimated time the cache will run out of space, if the system continues to add data with the rate of the last hour
to: dba
@@ -6,8 +6,8 @@ template: mysql_last_collected_secs
calc: $now - $last_collected_t
units: seconds ago
every: 10s
- warn: $this > ( 5 * $update_every)
- crit: $this > (60 * $update_every)
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
info: number of seconds since the last successful data collection
to: dba
@@ -6,9 +6,9 @@ template: named_last_collected_secs
calc: $now - $last_collected_t
units: seconds ago
every: 10s
- warn: $this > ( 5 * $update_every)
- crit: $this > (60 * $update_every)
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
info: number of seconds since the last successful data collection
to: domainadmin
@@ -6,9 +6,9 @@ template: interface_last_collected_secs
calc: $now - $last_collected_t
units: seconds ago
every: 10s
- warn: $this > ( 5 * $update_every)
- crit: $this > (60 * $update_every)
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
info: number of seconds since the last successful data collection
to: sysadmin
@@ -25,7 +25,7 @@ template: 1hour_packet_drops
units: packets
every: 1m
warn: $this > 0
- delay: up 0 down 15m multiplier 1.5 max 1h
+ delay: down 30m multiplier 1.5 max 1h
info: interface dropped packets in the last hour
to: sysadmin
@@ -43,6 +43,6 @@ template: 1hour_fifo_errors
units: errors
every: 1m
warn: $this > 0
- delay: up 0 down 15m multiplier 1.5 max 1h
+ delay: down 30m multiplier 1.5 max 1h
info: interface fifo errors in the last hour
to: sysadmin
@@ -6,9 +6,9 @@ template: nginx_last_collected_secs
calc: $now - $last_collected_t
units: seconds ago
every: 10s
- warn: $this > ( 5 * $update_every)
- crit: $this > (60 * $update_every)
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
info: number of seconds since the last successful data collection
to: webmaster
@@ -8,7 +8,7 @@
# lookup: sum -10m unaligned absolute
# every: 30s
# warn: $this > 0
-# delay: up 0 down 15m multiplier 1.5 max 1h
+# delay: up 0 down 30m multiplier 1.5 max 1h
# units: packets
# info: dropped packets in the last 30 minutes
# to: sysadmin
@@ -4,8 +4,8 @@
calc: $used * 100 / ($used + $cached + $free)
units: %
every: 10s
- warn: $this > 80
- crit: $this > 90
- delay: up 1m down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (70) : (80))
+ crit: $this > (($status == $CRITICAL) ? (80) : (90))
+ delay: down 15m multiplier 1.5 max 1h
info: system RAM usage
to: sysadmin
@@ -6,9 +6,9 @@ template: redis_last_collected_secs
calc: $now - $last_collected_t
units: seconds ago
every: 10s
- warn: $this > ( 5 * $update_every)
- crit: $this > (60 * $update_every)
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
info: number of seconds since the last successful data collection
to: dba
@@ -5,9 +5,9 @@ template: retroshare_last_collected_secs
calc: $now - $last_collected_t
units: seconds ago
every: 10s
- warn: $this > ( 5 * $update_every)
- crit: $this > (60 * $update_every)
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
info: number of seconds since the last successful data collection
to: sysadmin
@@ -18,8 +18,8 @@ template: retroshare_dht_working
calc: $dht_size_all
units: peers
every: 1m
- warn: $this < 100
- crit: $this == 0
+ warn: $this < (($status >= $WARNING) ? (120) : (100))
+ crit: $this < (($status == $CRITICAL) ? (10) : (1))
delay: up 0 down 15m multiplier 1.5 max 1h
info: Checks if the DHT has enough peers to operate
to: sysadmin
@@ -6,9 +6,9 @@ template: squid_last_collected_secs
calc: $now - $last_collected_t
units: seconds ago
every: 10s
- warn: $this > ( 5 * $update_every)
- crit: $this > (60 * $update_every)
- delay: up 0 down 15m multiplier 1.5 max 1h
+ warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
info: number of seconds since the last successful data collection
to: proxyadmin
@@ -6,8 +6,8 @@
calc: $this / 1024 * 100 / ( $system.ram.used + $system.ram.cached + $system.ram.free )
units: % of RAM
every: 1m
- warn: $this > 10
- crit: $this > 20
+ warn: $this > (($status >= $WARNING) ? (5) : (10))
+ crit: $this > (($status == $CRITICAL) ? (15) : (20))
delay: up 0 down 15m multiplier 1.5 max 1h
info: the amount of memory swapped in the last 30 minutes, as a percentage of the system RAM
to: sysadmin
@@ -17,8 +17,8 @@
calc: $used * 100 / ( $system.ram.used + $system.ram.cached + $system.ram.free )
units: % of RAM
every: 10s
- warn: $this > 20
- crit: $this > 50
+ warn: $this > (($status >= $WARNING) ? (15) : (20))
+ crit: $this > (($status == $CRITICAL) ? (40) : (50))
delay: up 0 down 15m multiplier 1.5 max 1h
info: the swap memory used, as a percentage of the system RAM
to: sysadmin

0 comments on commit b7261c2

Please sign in to comment.