summaryrefslogtreecommitdiffstats
path: root/health
diff options
context:
space:
mode:
authorIlya Mashchenko <ilya@netdata.cloud>2019-08-12 10:01:36 +0300
committerPaul Emm. Katsoulakis <34388743+paulkatsoulakis@users.noreply.github.com>2019-08-12 10:01:36 +0300
commit381553a63c5572d3dc5cbea55ffe55dd2c73efd8 (patch)
tree5276896d268747365ddcaedcbc33e64829602384 /health
parentcf6e42273c64fdfdf7a11254d9983b3cff87849c (diff)
vsphere collector: charts descritpion and alarms (#6572)
* add vsphere to the dashboard_info.js * swap charts desc fix * add some useful links to the mem charts desc * add vsphere alarms * only specific charts are memory charts * fix alarms * minor * minor
Diffstat (limited to 'health')
-rw-r--r--health/Makefile.am1
-rw-r--r--health/health.d/vsphere.conf157
2 files changed, 158 insertions, 0 deletions
diff --git a/health/Makefile.am b/health/Makefile.am
index 5310bd8aa8..e9fceddb79 100644
--- a/health/Makefile.am
+++ b/health/Makefile.am
@@ -84,6 +84,7 @@ dist_healthconfig_DATA = \
health.d/tcp_resets.conf \
health.d/udp_errors.conf \
health.d/varnish.conf \
+ health.d/vsphere.conf \
health.d/web_log.conf \
health.d/wmi.conf \
health.d/x509check.conf \
diff --git a/health/health.d/vsphere.conf b/health/health.d/vsphere.conf
new file mode 100644
index 0000000000..d8b2be1907
--- /dev/null
+++ b/health/health.d/vsphere.conf
@@ -0,0 +1,157 @@
+
+# you can disable an alarm notification by setting the 'to' line to: silent
+
+# -----------------------------------------------VM Specific------------------------------------------------------------
+# Memory
+
+template: vsphere_vm_mem_usage
+ on: vsphere.vm_mem_usage_percentage
+ hosts: *
+ calc: $used
+ units: %
+ every: 20s
+ warn: $this > (($status >= $WARNING) ? (80) : (90))
+ crit: $this > (($status == $CRITICAL) ? (90) : (98))
+ delay: down 15m multiplier 1.5 max 1h
+ info: used RAM
+
+# -----------------------------------------------HOST Specific----------------------------------------------------------
+# Memory
+
+template: vsphere_host_mem_usage
+ on: vsphere.host_mem_usage_percentage
+ hosts: *
+ calc: $used
+ units: %
+ every: 20s
+ warn: $this > (($status >= $WARNING) ? (80) : (90))
+ crit: $this > (($status == $CRITICAL) ? (90) : (98))
+ delay: down 15m multiplier 1.5 max 1h
+ info: used RAM
+
+# Network errors
+
+template: vsphere_inbound_packets_errors
+ on: vsphere.net_errors_total
+ hosts: *
+families: *
+ lookup: sum -10m unaligned absolute match-names of rx
+ units: packets
+ every: 1m
+ warn: $this >= 5
+ delay: down 1h multiplier 1.5 max 2h
+ info: interface inbound dropped packets in the last 10 minutes
+ to: sysadmin
+
+template: vsphere_outbound_packets_errors
+ on: vsphere.net_errors_total
+ hosts: *
+families: *
+ lookup: sum -10m unaligned absolute match-names of tx
+ units: packets
+ every: 1m
+ warn: $this >= 5
+ delay: down 1h multiplier 1.5 max 2h
+ info: interface outbound dropped packets in the last 10 minutes
+ to: sysadmin
+
+# Network errors ratio
+
+template: vsphere_inbound_packets_errors_ratio
+ on: vsphere.net_packets_total
+ hosts: *
+families: *
+ lookup: sum -10m unaligned absolute match-names of rx
+ calc: (($vsphere_inbound_packets_errors != nan AND $this > 0) ? ($vsphere_inbound_packets_errors * 100 / $this) : (0))
+ units: %
+ every: 1m
+ warn: $this >= 0.1
+ crit: $this >= 2
+ delay: down 1h multiplier 1.5 max 2h
+ info: the ratio of inbound errors vs the total number of received packets of the network interface, during the last 10 minutes
+ to: sysadmin
+
+template: vsphere_outbound_packets_errors_ratio
+ on: vsphere.net_packets_total
+ hosts: *
+families: *
+ lookup: sum -10m unaligned absolute match-names of tx
+ calc: (($vsphere_outbound_packets_errors != nan AND $this > 0) ? ($vsphere_outbound_packets_errors * 100 / $this) : (0))
+ units: %
+ every: 1m
+ warn: $this >= 0.1
+ crit: $this >= 2
+ delay: down 1h multiplier 1.5 max 2h
+ info: the ratio of outbound errors vs the total number of sent packets of the network interface, during the last 10 minutes
+ to: sysadmin
+
+# -----------------------------------------------Common-------------------------------------------------------------------
+# CPU
+
+template: vsphere_cpu_usage
+ on: vsphere.cpu_usage_total
+ hosts: *
+ lookup: average -10m unaligned match-names of used
+ units: %
+ every: 20s
+ warn: $this > (($status >= $WARNING) ? (75) : (85))
+ crit: $this > (($status == $CRITICAL) ? (85) : (95))
+ delay: down 15m multiplier 1.5 max 1h
+ info: cpu utilization for the last 10 minutes
+ to: sysadmin
+
+# Network drops
+
+template: vsphere_inbound_packets_dropped
+ on: vsphere.net_drops_total
+ hosts: *
+families: *
+ lookup: sum -10m unaligned absolute match-names of rx
+ units: packets
+ every: 1m
+ warn: $this >= 5
+ delay: down 1h multiplier 1.5 max 2h
+ info: interface inbound dropped packets in the last 10 minutes
+ to: sysadmin
+
+template: vsphere_outbound_packets_dropped
+ on: vsphere.net_drops_total
+ hosts: *
+families: *
+ lookup: sum -10m unaligned absolute match-names of tx
+ units: packets
+ every: 1m
+ warn: $this >= 5
+ delay: down 1h multiplier 1.5 max 2h
+ info: interface outbound dropped packets in the last 10 minutes
+ to: sysadmin
+
+# Network drops ratio
+
+template: vsphere_inbound_packets_dropped_ratio
+ on: vsphere.net_packets_total
+ hosts: *
+families: *
+ lookup: sum -10m unaligned absolute match-names of rx
+ calc: (($vsphere_inbound_packets_dropped != nan AND $this > 0) ? ($vsphere_inbound_packets_dropped * 100 / $this) : (0))
+ units: %
+ every: 1m
+ warn: $this >= 0.1
+ crit: $this >= 2
+ delay: down 1h multiplier 1.5 max 2h
+ info: the ratio of inbound dropped packets vs the total number of received packets of the network interface, during the last 10 minutes
+ to: sysadmin
+
+template: vsphere_outbound_packets_dropped_ratio
+ on: vsphere.net_packets_total
+ hosts: *
+families: *
+ lookup: sum -10m unaligned absolute match-names of tx
+ calc: (($vsphere_outbound_packets_dropped != nan AND $this > 0) ? ($vsphere_outbound_packets_dropped * 100 / $this) : (0))
+ units: %
+ every: 1m
+ warn: $this >= 0.1
+ crit: $this >= 2
+ delay: down 1h multiplier 1.5 max 2h
+ info: the ratio of outbound dropped packets vs the total number of sent packets of the network interface, during the last 10 minutes
+ to: sysadmin