1 # -----------------------------------------------------------------------------
4 # checking the latest collected values
5 # raise an alarm if the disk is low on
8 template: disk_space_usage
11 calc: $used * 100 / ($avail + $used)
14 warn: $this > (($status >= $WARNING ) ? (80) : (90))
15 crit: $this > (($status == $CRITICAL) ? (90) : (98))
16 delay: up 1m down 15m multiplier 1.5 max 1h
17 info: current disk space usage
20 template: disk_inode_usage
23 calc: $used * 100 / ($avail + $used)
26 warn: $this > (($status >= $WARNING) ? (80) : (90))
27 crit: $this > (($status == $CRITICAL) ? (90) : (98))
28 delay: up 1m down 15m multiplier 1.5 max 1h
29 info: current disk inode usage
33 # -----------------------------------------------------------------------------
36 # calculate the rate the disk fills
37 # use as base, the available space change
38 # during the last hour
40 # this is just a calculation - it has no alarm
41 # we will use it in the next template to find
44 template: disk_fill_rate
47 lookup: min -10m at -50m unaligned of avail
48 calc: ($this - $avail) / (($now - $after) / 3600)
51 info: average rate the disk fills up (positive), or frees up (negative) space, for the last hour
54 # calculate the hours remaining
55 # if the disk continues to fill
58 template: out_of_disk_space_time
61 calc: ($disk_fill_rate > 0) ? ($avail / $disk_fill_rate) : (inf)
64 warn: $this > 0 and $this < (($status >= $WARNING) ? (48) : (8))
65 crit: $this > 0 and $this < (($status == $CRITICAL) ? (24) : (2))
66 delay: down 15m multiplier 1.2 max 1h
67 info: estimated time the disk will run out of space, if the system continues to add data with the rate of the last hour
71 # -----------------------------------------------------------------------------
74 # raise an alarm if the disk is congested
75 # by calculating the average disk utilization
76 # for the last 10 minutes
78 template: 10min_disk_utilization
81 lookup: average -10m unaligned
86 warn: $this > $green * (($status >= $WARNING) ? (0.7) : (1))
87 crit: $this > $red * (($status == $CRITICAL) ? (0.7) : (1))
88 delay: down 15m multiplier 1.2 max 1h
89 info: the percentage of time the disk was busy, during the last 10 minutes
93 # raise an alarm if the disk backlog
94 # is above 1000ms (1s) per second
96 # (i.e. the disk cannot catch up)
98 template: 10min_disk_backlog
101 lookup: average -10m unaligned
106 warn: $this > $green * (($status >= $WARNING) ? (0.7) : (1))
107 crit: $this > $red * (($status == $CRITICAL) ? (0.7) : (1))
108 delay: down 15m multiplier 1.2 max 1h
109 info: average of the kernel estimated disk backlog, for the last 10 minutes