diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2018-11-07 12:19:29 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2018-11-07 12:20:17 +0000 |
commit | a64a253794ac64cb40befee54db53bde17dd0d49 (patch) | |
tree | c1024acc5f6e508814b944d99f112259bb28b1be /health/health.d/load.conf | |
parent | New upstream version 1.10.0+dfsg (diff) | |
download | netdata-upstream/1.11.0+dfsg.tar.xz netdata-upstream/1.11.0+dfsg.zip |
New upstream version 1.11.0+dfsgupstream/1.11.0+dfsg
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to '')
-rw-r--r-- | health/health.d/load.conf | 56 |
1 files changed, 56 insertions, 0 deletions
diff --git a/health/health.d/load.conf b/health/health.d/load.conf new file mode 100644 index 000000000..ee0c54b8e --- /dev/null +++ b/health/health.d/load.conf @@ -0,0 +1,56 @@ + +# you can disable an alarm notification by setting the 'to' line to: silent + +# Calculate the base trigger point for the load average alarms. +# This is the maximum number of CPU's in the system over the past 1 +# minute, with a special case for a single CPU of setting the trigger at 2. + alarm: load_trigger + on: system.load + os: linux + hosts: * + calc: ($active_processors == nan or $active_processors == inf or $active_processors < 2) ? ( 2 ) : ( $active_processors ) + units: cpus + every: 1m + info: trigger point for load average alarms + +# Send alarms if the load average is unusually high. +# These intentionally _do not_ calculate the average over the sampled +# time period because the values being checked already are averages. + alarm: load_average_15 + on: system.load + os: linux + hosts: * + lookup: max -1m unaligned of load15 + units: load + every: 1m + warn: $this > (($status >= $WARNING) ? (1.75 * $load_trigger) : (2 * $load_trigger)) + crit: $this > (($status == $CRITICAL) ? (3.5 * $load_trigger) : (4 * $load_trigger)) + delay: down 15m multiplier 1.5 max 1h + info: fifteen-minute load average + to: sysadmin + + alarm: load_average_5 + on: system.load + os: linux + hosts: * + lookup: max -1m unaligned of load5 + units: load + every: 1m + warn: $this > (($status >= $WARNING) ? (3.5 * $load_trigger) : (4 * $load_trigger)) + crit: $this > (($status == $CRITICAL) ? (7 * $load_trigger) : (8 * $load_trigger)) + delay: down 15m multiplier 1.5 max 1h + info: five-minute load average + to: sysadmin + + alarm: load_average_1 + on: system.load + os: linux + hosts: * + lookup: max -1m unaligned of load1 + units: load + every: 1m + warn: $this > (($status >= $WARNING) ? (7 * $load_trigger) : (8 * $load_trigger)) + crit: $this > (($status == $CRITICAL) ? (14 * $load_trigger) : (16 * $load_trigger)) + delay: down 15m multiplier 1.5 max 1h + info: one-minute load average + to: sysadmin |