varnish_plugin: remove from conf file not ascii characters

[netdata.git] / conf.d / health.d / disks.conf

diff --git a/conf.d/health.d/disks.conf b/conf.d/health.d/disks.conf
index ddd48d7c814acb8c871f136ed45db1f1139c2c1c..ff2d6a605ad3bdae4b9fa3e519356295bc7cb9f5 100644 (file)
--- a/conf.d/health.d/disks.conf
+++ b/conf.d/health.d/disks.conf
@@ -1,3 +1,33 @@
+# -----------------------------------------------------------------------------
+# make sure we collect values for each disk
+
+# 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 >= $WARNING)  ? ($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
+
+# 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 >= $WARNING)  ? ($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
+
+
 # -----------------------------------------------------------------------------
 # low disk space
 
@@ -7,14 +37,28 @@
 
 template: disk_space_usage
       on: disk.space
+families: *
     calc: $used * 100 / ($avail + $used)
-   every: 1m
-    warn: $this > 80
-    crit: $this > 95
    units: %
+   every: 1m
+    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)  ? (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
+
 
 # -----------------------------------------------------------------------------
 # disk fill rate
@@ -29,6 +73,7 @@ template: disk_space_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
@@ -42,11 +87,13 @@ template: disk_fill_rate
 
 template: out_of_disk_space_time
       on: disk.space
-    calc: $avail / $disk_fill_rate
-   every: 10s
-    warn: $this > 0 and $this < 8
-    crit: $this > 0 and $this < 2
+families: *
+    calc: ($disk_fill_rate > 0) ? ($avail / $disk_fill_rate) : (inf)
    units: hours
+   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
 
@@ -60,13 +107,15 @@ template: out_of_disk_space_time
 
 template: 10min_disk_utilization
       on: disk.util
+families: *
   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
 
@@ -78,12 +127,14 @@ template: 10min_disk_utilization
 
 template: 10min_disk_backlog
       on: disk.backlog
+families: *
   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