Merging upstream version 1.31.0.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 80 insertions, 53 deletions

diff --git a/health/health.d/ram.conf b/health/health.d/ram.conf
index 2daecc489..0e3cc29fa 100644
--- a/health/health.d/ram.conf
+++ b/health/health.d/ram.conf
@@ -1,65 +1,92 @@
 
 # you can disable an alarm notification by setting the 'to' line to: silent
 
-   alarm: used_ram_to_ignore
-      on: system.ram
-      os: linux freebsd
-   hosts: *
-    calc: ($zfs.arc_size.arcsz = nan)?(0):($zfs.arc_size.arcsz - $zfs.arc_size.min)
-   every: 10s
-    info: amount of memory reported as used, \
-          but it is actually capable for resizing itself based on the system needs (eg. ZFS ARC)
+    alarm: used_ram_to_ignore
+       on: system.ram
+    class: System
+component: Memory
+     type: Utilization
+       os: linux freebsd
+    hosts: *
+     calc: ($zfs.arc_size.arcsz = nan)?(0):($zfs.arc_size.arcsz - $zfs.arc_size.min)
+    every: 10s
+     info: amount of memory reported as used, \
+           but it is actually capable for resizing itself based on the system needs (eg. ZFS ARC)
 
-   alarm: ram_in_use
-      on: system.ram
-      os: linux
-   hosts: *
-#   calc: $used * 100 / ($used + $cached + $free)
-    calc: ($used - $used_ram_to_ignore) * 100 / ($used  + $cached + $free)
-   units: %
-   every: 10s
-    warn: $this > (($status >= $WARNING)  ? (80) : (90))
-    crit: $this > (($status == $CRITICAL) ? (90) : (98))
-   delay: down 15m multiplier 1.5 max 1h
-    info: system memory utilization
-      to: sysadmin
+    alarm: ram_in_use
+       on: system.ram
+    class: System
+component: Memory
+     type: Utilization
+       os: linux
+    hosts: *
+#    calc: $used * 100 / ($used + $cached + $free)
+     calc: ($used - $used_ram_to_ignore) * 100 / ($used  + $cached + $free)
+    units: %
+    every: 10s
+     warn: $this > (($status >= $WARNING)  ? (80) : (90))
+     crit: $this > (($status == $CRITICAL) ? (90) : (98))
+    delay: down 15m multiplier 1.5 max 1h
+     info: system memory utilization
+       to: sysadmin
+
+    alarm: ram_available
+       on: mem.available
+    class: System
+component: Memory
+     type: Utilization
+       os: linux
+    hosts: *
+     calc: ($avail + $system.ram.used_ram_to_ignore) * 100 / ($system.ram.used + $system.ram.cached + $system.ram.free + $system.ram.buffers)
+    units: %
+    every: 10s
+     warn: $this < (($status >= $WARNING)  ? (15) : (10))
+     crit: $this < (($status == $CRITICAL) ? (10) : ( 5))
+    delay: down 15m multiplier 1.5 max 1h
+     info: percentage of estimated amount of RAM available for userspace processes, without causing swapping
+       to: sysadmin
 
-   alarm: ram_available
-      on: mem.available
+   alarm: oom_kill
+      on: mem.oom_kill
       os: linux
    hosts: *
-    calc: ($avail + $system.ram.used_ram_to_ignore) * 100 / ($system.ram.used + $system.ram.cached + $system.ram.free + $system.ram.buffers)
-   units: %
+  lookup: sum -1m unaligned
+   units: kills
    every: 10s
-    warn: $this < (($status >= $WARNING)  ? (15) : (10))
-    crit: $this < (($status == $CRITICAL) ? (10) : ( 5))
-   delay: down 15m multiplier 1.5 max 1h
-    info: percentage of estimated amount of RAM available for userspace processes, without causing swapping
+    warn: $this > 0
+   delay: down 5m
+    info: number of out of memory kills in the last minute
       to: sysadmin
 
 ## FreeBSD
-   alarm: ram_in_use
-      on: system.ram
-      os: freebsd
-   hosts: *
-    calc: ($active + $wired + $laundry + $buffers - $used_ram_to_ignore) * 100 / ($active + $wired + $laundry + $buffers - $used_ram_to_ignore + $cache + $free + $inactive)
-   units: %
-   every: 10s
-    warn: $this > (($status >= $WARNING)  ? (80) : (90))
-    crit: $this > (($status == $CRITICAL) ? (90) : (98))
-   delay: down 15m multiplier 1.5 max 1h
-    info: system memory utilization
-      to: sysadmin
+    alarm: ram_in_use
+       on: system.ram
+    class: System
+component: Memory
+     type: Utilization
+       os: freebsd
+    hosts: *
+     calc: ($active + $wired + $laundry + $buffers - $used_ram_to_ignore) * 100 / ($active + $wired + $laundry + $buffers - $used_ram_to_ignore + $cache + $free + $inactive)
+    units: %
+    every: 10s
+     warn: $this > (($status >= $WARNING)  ? (80) : (90))
+     crit: $this > (($status == $CRITICAL) ? (90) : (98))
+    delay: down 15m multiplier 1.5 max 1h
+     info: system memory utilization
+       to: sysadmin
 
-   alarm: ram_available
-      on: system.ram
-      os: freebsd
-   hosts: *
-    calc: ($free + $inactive + $used_ram_to_ignore) * 100 / ($free + $active + $inactive + $wired + $cache + $laundry + $buffers)
-   units: %
-   every: 10s
-    warn: $this < (($status >= $WARNING)  ? (15) : (10))
-    crit: $this < (($status == $CRITICAL) ? (10) : ( 5))
-   delay: down 15m multiplier 1.5 max 1h
-    info: percentage of estimated amount of RAM available for userspace processes, without causing swapping
-      to: sysadmin
+    alarm: ram_available
+       on: system.ram
+    class: System
+component: Memory
+     type: Utilization
+       os: freebsd
+    hosts: *
+     calc: ($free + $inactive + $used_ram_to_ignore) * 100 / ($free + $active + $inactive + $wired + $cache + $laundry + $buffers)
+    units: %
+    every: 10s
+     warn: $this < (($status >= $WARNING)  ? (15) : (10))
+     crit: $this < (($status == $CRITICAL) ? (10) : ( 5))
+    delay: down 15m multiplier 1.5 max 1h
+     info: percentage of estimated amount of RAM available for userspace processes, without causing swapping
+       to: sysadmin