New upstream version 1.4.0+dfsgupstream/1.4.0+dfsg

1 files changed, 71 insertions, 24 deletions

diff --git a/conf.d/health.d/disks.conf b/conf.d/health.d/disks.conf
index c38f1a0a0..cc7a47660 100644
--- a/conf.d/health.d/disks.conf
+++ b/conf.d/health.d/disks.conf
@@ -1,18 +1,59 @@
 # -----------------------------------------------------------------------------
+# make sure we collect values for each disk
+
+# for mount points
+template: disk_space_last_collected_secs
+      on: disk.space
+    calc: $now - $last_collected_t
+   units: seconds ago
+   every: 10s
+    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
+
+# for block devices
+template: disk_last_collected_secs
+      on: disk.io
+    calc: $now - $last_collected_t
+   units: seconds ago
+   every: 10s
+    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
+
+
+# -----------------------------------------------------------------------------
 # low disk space
 
 # checking the latest collected values
 # raise an alarm if the disk is low on
 # available disk space
 
-template: disk_full_percent
+template: disk_space_usage
       on: disk.space
     calc: $used * 100 / ($avail + $used)
-   every: 1m
-    warn: $this > 80
-    crit: $this > 95
    units: %
+   every: 1m
+    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
+
+template: disk_inode_usage
+      on: disk.inodes
+    calc: $used * 100 / ($avail + $used)
+   units: %
+   every: 1m
+    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
 
 
 # -----------------------------------------------------------------------------
@@ -20,7 +61,7 @@ template: disk_full_percent
 
 # calculate the rate the disk fills
 # use as base, the available space change
-# during the last 30 minutes
+# during the last hour
 
 # this is just a calculation - it has no alarm
 # we will use it in the next template to find
@@ -28,25 +69,27 @@ template: disk_full_percent
 
 template: disk_fill_rate
       on: disk.space
-  lookup: max -1s at -30m unaligned of avail
-    calc: ($this - $avail) / ($now - $after)
-   every: 15s
-   units: MB/s
-    info: average rate the disk fills up (positive), or frees up (negative) space, for the last 30 minutes
+  lookup: min -10m at -50m unaligned of avail
+    calc: ($this - $avail) / (($now - $after) / 3600)
+   every: 1m
+   units: GB/hour
+    info: average rate the disk fills up (positive), or frees up (negative) space, for the last hour
 
 
 # calculate the hours remaining
 # if the disk continues to fill
 # in this rate
 
-template: disk_full_after_hours
+template: out_of_disk_space_time
       on: disk.space
-    calc: $avail / $disk_fill_rate / 3600
-   every: 10s
-    warn: $this > 0 and $this < 48
-    crit: $this > 0 and $this < 24
+    calc: $avail / $disk_fill_rate
    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
+   every: 10s
+    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
 
 
 # -----------------------------------------------------------------------------
@@ -59,13 +102,15 @@ template: disk_full_after_hours
 template: 10min_disk_utilization
       on: disk.util
   lookup: average -10m unaligned
+   units: %
    every: 1m
    green: 90
      red: 98
-    warn: $this > $green
-    crit: $this > $red
-   units: %
+    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
 
 
 # raise an alarm if the disk backlog
@@ -76,10 +121,12 @@ template: 10min_disk_utilization
 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
+   every: 1m
+   green: 2000
+     red: 5000
+    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