@cryptotaxi247 / netdata-1 / commits / b7261c269

updated alarms to take into account the alarm status examination

Costa Tsaousis (ktsaou) committed Sep 15, 2016 at 01:31 UTC b7261c269139a576e98c3c03a5dc4d2337044f8f
15 files changed +74 -74
conf.d/health.d/apache.conf
+3 -3
@@ -6,9 +6,9 @@ template: apache_last_collected_secs
6 calc: $now - $last_collected_t
7 units: seconds ago
8 every: 10s
9 - warn: $this > ( 5 * $update_every)
10 - crit: $this > (60 * $update_every)
11 - delay: up 0 down 15m multiplier 1.5 max 1h
9 + warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10 + crit: $this > (($status == $CRITICAL) ? (0) : (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
14
conf.d/health.d/cpu.conf
+9 -9
@@ -4,9 +4,9 @@ template: 10min_cpu_usage
4 lookup: average -10m unaligned of user,system,nice,softirq,irq,guest,guest_nice
5 units: %
6 every: 1m
7 - warn: $this > 80
8 - crit: $this > 90
9 - delay: up 0 down 15m multiplier 1.5 max 1h
7 + warn: $this > (($status >= $WARNING) ? (70) : (80))
8 + crit: $this > (($status == $CRITICAL) ? (80) : (90))
9 + delay: down 15m multiplier 1.5 max 1h
10 info: average cpu utilization for the last 10 minutes
11 to: sysadmin
12
@@ -15,9 +15,9 @@ template: 10min_cpu_iowait
15 lookup: average -10m unaligned of iowait
16 units: %
17 every: 1m
18 - warn: $this > 10
19 - crit: $this > 30
20 - delay: up 0 down 15m multiplier 1.5 max 1h
18 + warn: $this > (($status >= $WARNING) ? (5) : (10))
19 + crit: $this > (($status == $CRITICAL) ? (20) : (30))
20 + delay: down 15m multiplier 1.5 max 1h
21 info: average CPU wait I/O for the last 10 minutes
22 to: sysadmin
23
@@ -26,8 +26,8 @@ template: 20min_steal_cpu
26 lookup: average -20m unaligned of steal
27 units: %
28 every: 5m
29 - warn: $this > 10
30 - crit: $this > 30
31 - delay: up 0 down 15m multiplier 1.5 max 1h
29 + warn: $this > (($status >= $WARNING) ? (5) : (10))
30 + crit: $this > (($status == $CRITICAL) ? (20) : (30))
31 + delay: down 15m multiplier 1.5 max 1h
32 info: average CPU steal time for the last 20 minutes
33 to: sysadmin
conf.d/health.d/disks.conf
+19 -19
@@ -7,9 +7,9 @@ template: disk_space_last_collected_secs
7 calc: $now - $last_collected_t
8 units: seconds ago
9 every: 10s
10 - warn: $this > ( 5 * $update_every)
11 - crit: $this > (60 * $update_every)
12 - delay: up 0 down 15m multiplier 1.5 max 1h
10 + warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
11 + crit: $this > (($status == $CRITICAL) ? (0) : (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
15
@@ -19,9 +19,9 @@ template: disk_last_collected_secs
19 calc: $now - $last_collected_t
20 units: seconds ago
21 every: 10s
22 - warn: $this > ( 5 * $update_every)
23 - crit: $this > (60 * $update_every)
24 - delay: up 0 down 15m multiplier 1.5 max 1h
22 + warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
23 + crit: $this > (($status == $CRITICAL) ? (0) : (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
27
@@ -38,8 +38,8 @@ template: disk_space_usage
38 calc: $used * 100 / ($avail + $used)
39 units: %
40 every: 1m
41 - warn: $this > 80
42 - crit: $this > 95
41 + warn: $this > (($status >= $WARNING ) ? (70) : (80))
42 + crit: $this > (($status == $CRITICAL) ? (85) : (95))
43 delay: up 1m down 15m multiplier 1.5 max 1h
44 info: current disk space usage
45 to: sysadmin
@@ -49,8 +49,8 @@ template: disk_inode_usage
49 calc: $used * 100 / ($avail + $used)
50 units: %
51 every: 1m
52 - warn: $this > 80
53 - crit: $this > 95
52 + warn: $this > (($status >= $WARNING) ? (75) : (80))
53 + crit: $this > (($status == $CRITICAL) ? (90) : (95))
54 delay: up 1m down 15m multiplier 1.5 max 1h
55 info: current disk inode usage
56 to: sysadmin
@@ -85,9 +85,9 @@ template: out_of_disk_space_time
85 calc: $avail / $disk_fill_rate
86 units: hours
87 every: 10s
88 - warn: $this > 0 and $this < 8
89 - crit: $this > 0 and $this < 2
90 - delay: up 0 down 15m multiplier 1.5 max 1h
88 + warn: $this > 0 and $this < (($status >= $WARNING) ? (48) : (8))
89 + crit: $this > 0 and $this < (($status == $CRITICAL) ? (24) : (2))
90 + delay: down 15m multiplier 1.2 max 1h
91 info: estimated time the disk will run out of space, if the system continues to add data with the rate of the last hour
92 to: sysadmin
93
@@ -106,9 +106,9 @@ template: 10min_disk_utilization
106 every: 1m
107 green: 90
108 red: 98
109 - warn: $this > $green
110 - crit: $this > $red
111 - delay: up 0 down 30m multiplier 1.5 max 1h
109 + warn: $this > $green * (($status >= $WARNING) ? (0.7) : (1))
110 + crit: $this > $red * (($status == $CRITICAL) ? (0.7) : (1))
111 + delay: down 15m multiplier 1.2 max 1h
112 info: the percentage of time the disk was busy, during the last 10 minutes
113 to: sysadmin
114
@@ -125,8 +125,8 @@ template: 10min_disk_backlog
125 every: 1m
126 green: 2000
127 red: 5000
128 - warn: $this > $green
129 - crit: $this > $red
130 - delay: up 1m down 30m multiplier 1.5 max 1h
128 + warn: $this > $green * (($status >= $WARNING) ? (0.7) : (1))
129 + crit: $this > $red * (($status == $CRITICAL) ? (0.7) : (1))
130 + delay: down 15m multiplier 1.2 max 1h
131 info: average of the kernel estimated disk backlog, for the last 10 minutes
132 to: sysadmin
conf.d/health.d/entropy.conf
+2 -2
@@ -8,7 +8,7 @@
8 lookup: min -1h unaligned
9 units: entries
10 every: 5m
11 - warn: $this < 100
12 - delay: up 0 down 1h multiplier 1.5 max 1h
11 + warn: $this < (($status >= $WARNING) ? (200) : (100))
12 + delay: down 1h multiplier 1.5 max 1h
13 info: minimum entries in the random numbers pool in the last 30 minutes
14 to: sysadmin
conf.d/health.d/memcached.conf
+8 -8
@@ -6,9 +6,9 @@ template: memcached_last_collected_secs
6 calc: $now - $last_collected_t
7 units: seconds ago
8 every: 10s
9 - warn: $this > ( 5 * $update_every)
10 - crit: $this > (60 * $update_every)
11 - delay: up 0 down 15m multiplier 1.5 max 1h
9 + warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10 + crit: $this > (($status == $CRITICAL) ? (0) : (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
14
@@ -20,8 +20,8 @@ template: memcached_cache_memory_usage
20 calc: $used * 100 / ($used + $available)
21 units: %
22 every: 10s
23 - warn: $this > 80
24 - crit: $this > 90
23 + warn: $this > (($status >= $WARNING) ? (70) : (80))
24 + crit: $this > (($status == $CRITICAL) ? (80) : (90))
25 delay: up 0 down 15m multiplier 1.5 max 1h
26 info: current cache memory usage
27 to: dba
@@ -45,8 +45,8 @@ template: out_of_cache_space_time
45 calc: $available / $cache_fill_rate
46 units: hours
47 every: 10s
48 - warn: $this > 0 and $this < 8
49 - crit: $this > 0 and $this < 2
50 - delay: up 0 down 15m multiplier 1.5 max 1h
48 + warn: $this > 0 and $this < (($status >= $WARNING) ? (48) : (8))
49 + crit: $this > 0 and $this < (($status == $CRITICAL) ? (24) : (2))
50 + delay: down 15m multiplier 1.5 max 1h
51 info: estimated time the cache will run out of space, if the system continues to add data with the rate of the last hour
52 to: dba
conf.d/health.d/mysql.conf
+3 -3
@@ -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 > ( 5 * $update_every)
10 - crit: $this > (60 * $update_every)
11 - delay: up 0 down 15m multiplier 1.5 max 1h
9 + warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10 + crit: $this > (($status == $CRITICAL) ? (0) : (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
+3 -3
@@ -6,9 +6,9 @@ template: named_last_collected_secs
6 calc: $now - $last_collected_t
7 units: seconds ago
8 every: 10s
9 - warn: $this > ( 5 * $update_every)
10 - crit: $this > (60 * $update_every)
11 - delay: up 0 down 15m multiplier 1.5 max 1h
9 + warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10 + crit: $this > (($status == $CRITICAL) ? (0) : (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
14
conf.d/health.d/net.conf
+5 -5
@@ -6,9 +6,9 @@ template: interface_last_collected_secs
6 calc: $now - $last_collected_t
7 units: seconds ago
8 every: 10s
9 - warn: $this > ( 5 * $update_every)
10 - crit: $this > (60 * $update_every)
11 - delay: up 0 down 15m multiplier 1.5 max 1h
9 + warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10 + crit: $this > (($status == $CRITICAL) ? (0) : (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
14
@@ -25,7 +25,7 @@ template: 1hour_packet_drops
25 units: packets
26 every: 1m
27 warn: $this > 0
28 - delay: up 0 down 15m multiplier 1.5 max 1h
28 + delay: down 30m multiplier 1.5 max 1h
29 info: interface dropped packets in the last hour
30 to: sysadmin
31
@@ -43,6 +43,6 @@ template: 1hour_fifo_errors
43 units: errors
44 every: 1m
45 warn: $this > 0
46 - delay: up 0 down 15m multiplier 1.5 max 1h
46 + delay: down 30m multiplier 1.5 max 1h
47 info: interface fifo errors in the last hour
48 to: sysadmin
conf.d/health.d/nginx.conf
+3 -3
@@ -6,9 +6,9 @@ template: nginx_last_collected_secs
6 calc: $now - $last_collected_t
7 units: seconds ago
8 every: 10s
9 - warn: $this > ( 5 * $update_every)
10 - crit: $this > (60 * $update_every)
11 - delay: up 0 down 15m multiplier 1.5 max 1h
9 + warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10 + crit: $this > (($status == $CRITICAL) ? (0) : (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
14
conf.d/health.d/qos.conf
+1 -1
@@ -8,7 +8,7 @@
8 # lookup: sum -10m unaligned absolute
9 # every: 30s
10 # warn: $this > 0
11 -# delay: up 0 down 15m multiplier 1.5 max 1h
11 +# delay: up 0 down 30m multiplier 1.5 max 1h
12 # units: packets
13 # info: dropped packets in the last 30 minutes
14 # to: sysadmin
conf.d/health.d/ram.conf
+3 -3
@@ -4,8 +4,8 @@
4 calc: $used * 100 / ($used + $cached + $free)
5 units: %
6 every: 10s
7 - warn: $this > 80
8 - crit: $this > 90
9 - delay: up 1m down 15m multiplier 1.5 max 1h
7 + warn: $this > (($status >= $WARNING) ? (70) : (80))
8 + crit: $this > (($status == $CRITICAL) ? (80) : (90))
9 + delay: down 15m multiplier 1.5 max 1h
10 info: system RAM usage
11 to: sysadmin
conf.d/health.d/redis.conf
+3 -3
@@ -6,9 +6,9 @@ template: redis_last_collected_secs
6 calc: $now - $last_collected_t
7 units: seconds ago
8 every: 10s
9 - warn: $this > ( 5 * $update_every)
10 - crit: $this > (60 * $update_every)
11 - delay: up 0 down 15m multiplier 1.5 max 1h
9 + warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10 + crit: $this > (($status == $CRITICAL) ? (0) : (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
14
conf.d/health.d/retroshare.conf
+5 -5
@@ -5,9 +5,9 @@ template: retroshare_last_collected_secs
5 calc: $now - $last_collected_t
6 units: seconds ago
7 every: 10s
8 - warn: $this > ( 5 * $update_every)
9 - crit: $this > (60 * $update_every)
10 - delay: up 0 down 15m multiplier 1.5 max 1h
8 + warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
9 + crit: $this > (($status == $CRITICAL) ? (0) : (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
13
@@ -18,8 +18,8 @@ template: retroshare_dht_working
18 calc: $dht_size_all
19 units: peers
20 every: 1m
21 - warn: $this < 100
22 - crit: $this == 0
21 + warn: $this < (($status >= $WARNING) ? (120) : (100))
22 + crit: $this < (($status == $CRITICAL) ? (10) : (1))
23 delay: up 0 down 15m multiplier 1.5 max 1h
24 info: Checks if the DHT has enough peers to operate
25 to: sysadmin
conf.d/health.d/squid.conf
+3 -3
@@ -6,9 +6,9 @@ template: squid_last_collected_secs
6 calc: $now - $last_collected_t
7 units: seconds ago
8 every: 10s
9 - warn: $this > ( 5 * $update_every)
10 - crit: $this > (60 * $update_every)
11 - delay: up 0 down 15m multiplier 1.5 max 1h
9 + warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every))
10 + crit: $this > (($status == $CRITICAL) ? (0) : (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
14
conf.d/health.d/swap.conf
+4 -4
@@ -6,8 +6,8 @@
6 calc: $this / 1024 * 100 / ( $system.ram.used + $system.ram.cached + $system.ram.free )
7 units: % of RAM
8 every: 1m
9 - warn: $this > 10
10 - crit: $this > 20
9 + warn: $this > (($status >= $WARNING) ? (5) : (10))
10 + crit: $this > (($status == $CRITICAL) ? (15) : (20))
11 delay: up 0 down 15m multiplier 1.5 max 1h
12 info: the amount of memory swapped in the last 30 minutes, as a percentage of the system RAM
13 to: sysadmin
@@ -17,8 +17,8 @@
17 calc: $used * 100 / ( $system.ram.used + $system.ram.cached + $system.ram.free )
18 units: % of RAM
19 every: 10s
20 - warn: $this > 20
21 - crit: $this > 50
20 + warn: $this > (($status >= $WARNING) ? (15) : (20))
21 + crit: $this > (($status == $CRITICAL) ? (40) : (50))
22 delay: up 0 down 15m multiplier 1.5 max 1h
23 info: the swap memory used, as a percentage of the system RAM
24 to: sysadmin