New upstream version 1.5.0+dfsgupstream/1.5.0+dfsg

1 files changed, 17 insertions, 9 deletions

diff --git a/conf.d/health.d/disks.conf b/conf.d/health.d/disks.conf
index cc7a47660..0549bac26 100644
--- a/conf.d/health.d/disks.conf
+++ b/conf.d/health.d/disks.conf
@@ -4,11 +4,12 @@
 # for mount points
 template: disk_space_last_collected_secs
       on: disk.space
+families: *
     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))
+    warn: $this > (($status >= $WARNING)  ? ($update_every) : ( 5 * $update_every))
+    crit: $this > (($status == $CRITICAL) ? ($update_every) : (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
@@ -16,11 +17,12 @@ template: disk_space_last_collected_secs
 # for block devices
 template: disk_last_collected_secs
       on: disk.io
+families: *
     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))
+    warn: $this > (($status >= $WARNING)  ? ($update_every) : ( 5 * $update_every))
+    crit: $this > (($status == $CRITICAL) ? ($update_every) : (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
@@ -35,22 +37,24 @@ template: disk_last_collected_secs
 
 template: disk_space_usage
       on: disk.space
+families: *
     calc: $used * 100 / ($avail + $used)
    units: %
    every: 1m
-    warn: $this > (($status >= $WARNING ) ? (70) : (80))
-    crit: $this > (($status == $CRITICAL) ? (85) : (95))
+    warn: $this > (($status >= $WARNING ) ? (80) : (90))
+    crit: $this > (($status == $CRITICAL) ? (90) : (98))
    delay: up 1m down 15m multiplier 1.5 max 1h
     info: current disk space usage
       to: sysadmin
 
 template: disk_inode_usage
       on: disk.inodes
+families: *
     calc: $used * 100 / ($avail + $used)
    units: %
    every: 1m
-    warn: $this > (($status >= $WARNING)  ? (75) : (80))
-    crit: $this > (($status == $CRITICAL) ? (90) : (95))
+    warn: $this > (($status >= $WARNING)  ? (80) : (90))
+    crit: $this > (($status == $CRITICAL) ? (90) : (98))
    delay: up 1m down 15m multiplier 1.5 max 1h
     info: current disk inode usage
       to: sysadmin
@@ -69,6 +73,7 @@ template: disk_inode_usage
 
 template: disk_fill_rate
       on: disk.space
+families: *
   lookup: min -10m at -50m unaligned of avail
     calc: ($this - $avail) / (($now - $after) / 3600)
    every: 1m
@@ -82,7 +87,8 @@ template: disk_fill_rate
 
 template: out_of_disk_space_time
       on: disk.space
-    calc: $avail / $disk_fill_rate
+families: *
+    calc: ($disk_fill_rate > 0) ? ($avail / $disk_fill_rate) : (0)
    units: hours
    every: 10s
     warn: $this > 0 and $this < (($status >= $WARNING)  ? (48) : (8))
@@ -101,6 +107,7 @@ template: out_of_disk_space_time
 
 template: 10min_disk_utilization
       on: disk.util
+families: *
   lookup: average -10m unaligned
    units: %
    every: 1m
@@ -120,6 +127,7 @@ template: 10min_disk_utilization
 
 template: 10min_disk_backlog
       on: disk.backlog
+families: *
   lookup: average -10m unaligned
    units: ms
    every: 1m