Imported Upstream version 1.3.0+dfsgupstream/1.3.0+dfsg

1 files changed, 85 insertions, 0 deletions

diff --git a/conf.d/health.d/disks.conf b/conf.d/health.d/disks.conf
new file mode 100644
index 00000000..c38f1a0a
--- /dev/null
+++ b/conf.d/health.d/disks.conf
@@ -0,0 +1,85 @@
+# -----------------------------------------------------------------------------
+# low disk space
+
+# checking the latest collected values
+# raise an alarm if the disk is low on
+# available disk space
+
+template: disk_full_percent
+      on: disk.space
+    calc: $used * 100 / ($avail + $used)
+   every: 1m
+    warn: $this > 80
+    crit: $this > 95
+   units: %
+    info: current disk space usage
+
+
+# -----------------------------------------------------------------------------
+# disk fill rate
+
+# calculate the rate the disk fills
+# use as base, the available space change
+# during the last 30 minutes
+
+# this is just a calculation - it has no alarm
+# we will use it in the next template to find
+# the hours remaining
+
+template: disk_fill_rate
+      on: disk.space
+  lookup: max -1s at -30m unaligned of avail
+    calc: ($this - $avail) / ($now - $after)
+   every: 15s
+   units: MB/s
+    info: average rate the disk fills up (positive), or frees up (negative) space, for the last 30 minutes
+
+
+# calculate the hours remaining
+# if the disk continues to fill
+# in this rate
+
+template: disk_full_after_hours
+      on: disk.space
+    calc: $avail / $disk_fill_rate / 3600
+   every: 10s
+    warn: $this > 0 and $this < 48
+    crit: $this > 0 and $this < 24
+   units: hours
+    info: estimated time the disk will run out of space, if the system continues to add data with the rate of the last 30 minutes
+
+
+# -----------------------------------------------------------------------------
+# disk congestion
+
+# raise an alarm if the disk is congested
+# by calculating the average disk utilization
+# for the last 10 minutes
+
+template: 10min_disk_utilization
+      on: disk.util
+  lookup: average -10m unaligned
+   every: 1m
+   green: 90
+     red: 98
+    warn: $this > $green
+    crit: $this > $red
+   units: %
+    info: the percentage of time the disk was busy, during the last 10 minutes
+
+
+# raise an alarm if the disk backlog
+# is above 1000ms (1s) per second
+# for 10 minutes
+# (i.e. the disk cannot catch up)
+
+template: 10min_disk_backlog
+      on: disk.backlog
+  lookup: average -10m unaligned
+   every: 1m
+   green: 1000
+     red: 2000
+    warn: $this > $green
+    crit: $this > $red
+   units: ms
+    info: average of the kernel estimated disk backlog, for the last 10 minutes