vcsa collector: charts description and alarms (#6772)

* add vcsa to dashboard_info.js

* add vcsa alarms

* update dashboard_info.js

* update dashboard_info.js

* update alarms

* availability alarm fix

3 files changed, 162 insertions, 1 deletions

diff --git a/health/Makefile.am b/health/Makefile.am
index 383696ef64..a682b594c1 100644
--- a/health/Makefile.am
+++ b/health/Makefile.am
@@ -85,6 +85,7 @@ dist_healthconfig_DATA = \
     health.d/tcp_resets.conf \
     health.d/udp_errors.conf \
     health.d/varnish.conf \
+    health.d/vcsa.conf \
     health.d/vsphere.conf \
     health.d/web_log.conf \
     health.d/wmi.conf \
diff --git a/health/health.d/vcsa.conf b/health/health.d/vcsa.conf
new file mode 100644
index 0000000000..7bb98a9bad
--- /dev/null
+++ b/health/health.d/vcsa.conf
@@ -0,0 +1,122 @@
+
+# make sure vcsa is running and responding
+
+template: vcsa_last_collected_secs
+      on: vcsa.system_health
+    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 * $update_every))
+   delay: down 5m multiplier 1.5 max 1h
+    info: number of seconds since the last successful data collection
+      to: sysadmin
+
+# Overall system health:
+#  - 0: all components are healthy.
+#  - 1: one or more components might become overloaded soon.
+#  - 2: one or more components in the appliance might be degraded.
+#  - 3: one or more components might be in an unusable status and the appliance might become unresponsive soon.
+#  - 4: no health data is available.
+
+template: vcsa_system_health
+      on: vcsa.system_health
+  lookup: max -10s unaligned of system
+   units: status
+   every: 10s
+    warn: ($this == 1) || ($this == 2)
+    crit: $this == 3
+   delay: down 1m multiplier 1.5 max 1h
+    info: overall system health status
+      to: sysadmin
+
+# Components health:
+#  - 0: healthy.
+#  - 1: healthy, but may have some problems.
+#  - 2: degraded, and may have serious problems.
+#  - 3: unavailable, or will stop functioning soon.
+#  - 4: no health data is available.
+
+template: vcsa_swap_health
+      on: vcsa.components_health
+  lookup: max -10s unaligned of swap
+   units: status
+   every: 10s
+    warn: $this == 1
+    crit: ($this == 2) || ($this == 3)
+   delay: down 1m multiplier 1.5 max 1h
+    info: swap health status
+      to: sysadmin
+
+template: vcsa_storage_health
+      on: vcsa.components_health
+  lookup: max -10s unaligned of storage
+   units: status
+   every: 10s
+    warn: $this == 1
+    crit: ($this == 2) || ($this == 3)
+   delay: down 1m multiplier 1.5 max 1h
+    info: storage health status
+      to: sysadmin
+
+template: vcsa_mem_health
+      on: vcsa.components_health
+  lookup: max -10s unaligned of mem
+   units: status
+   every: 10s
+    warn: $this == 1
+    crit: ($this == 2) || ($this == 3)
+   delay: down 1m multiplier 1.5 max 1h
+    info: mem health status
+      to: sysadmin
+
+template: vcsa_load_health
+      on: vcsa.components_health
+  lookup: max -10s unaligned of load
+   units: status
+   every: 10s
+    warn: $this == 1
+    crit: ($this == 2) || ($this == 3)
+   delay: down 1m multiplier 1.5 max 1h
+    info: load health status
+      to: sysadmin
+
+template: vcsa_database_storage_health
+      on: vcsa.components_health
+  lookup: max -10s unaligned of database_storage
+   units: status
+   every: 10s
+    warn: $this == 1
+    crit: ($this == 2) || ($this == 3)
+   delay: down 1m multiplier 1.5 max 1h
+    info: database storage health status
+      to: sysadmin
+
+template: vcsa_applmgmt_health
+      on: vcsa.components_health
+  lookup: max -10s unaligned of applmgmt
+   units: status
+   every: 10s
+    warn: $this == 1
+    crit: ($this == 2) || ($this == 3)
+   delay: down 1m multiplier 1.5 max 1h
+    info: appl mgmt health status
+      to: sysadmin
+
+
+# Software updates health:
+#  - 0: no updates available.
+#  - 2: non-security updates are available.
+#  - 3: security updates are available.
+#  - 4: an error retrieving information on software updates.
+
+template: vcsa_software_updates_health
+      on: vcsa.software_updates_health
+  lookup: max -10s unaligned of software_packages
+   units: status
+   every: 10s
+    warn: $this == 4
+    crit: $this == 3
+   delay: down 1m multiplier 1.5 max 1h
+    info: software packages health status
+      to: sysadmin
diff --git a/web/gui/dashboard_info.js b/web/gui/dashboard_info.js
index 661d40fd8e..3f65718164 100644
--- a/web/gui/dashboard_info.js
+++ b/web/gui/dashboard_info.js
@@ -498,6 +498,12 @@ netdataDashboard.menu = {
         title: 'vSphere',
         icon: '<i class="fas fa-server"></i>',
         info: 'Performance statistics for ESXI hosts and virtual machines. Data collected from <a href="https://www.vmware.com/products/vcenter-server.html">VMware vCenter Server</a> using <code><a href="https://github.com/vmware/govmomi"> govmomi</a></code>  library.'
+    },
+
+    'vcsa': {
+        title: 'VCSA',
+        icon: '<i class="fas fa-server"></i>',
+        info: 'vCenter Server Appliance health statistics. Data collected from <a href="https://vmware.github.io/vsphere-automation-sdk-rest/vsphere/index.html#SVC_com.vmware.appliance.health">Health API</a>.'
     }
 };
 
@@ -2587,5 +2593,37 @@ netdataDashboard.context = {
 
     'vsphere.overall_status': {
         info: '<code>0</code> is unknown, <code>1</code> is OK, <code>2</code> is might have a problem, <code>3</code> is definitely has a problem.'
-    }
+    },
+
+    // ------------------------------------------------------------------------
+    // VCSA
+    'vcsa.system_health': {
+        info:
+            '<code>-1</code>: unknown; ' +
+            '<code>0</code>: all components are healthy; ' +
+            '<code>1</code>: one or more components might become overloaded soon; ' +
+            '<code>2</code>: one or more components in the appliance might be degraded; ' +
+            '<code>3</code>: one or more components might be in an unusable status and the appliance might become unresponsive soon; ' +
+            '<code>4</code>: no health data is available.'
+            },
+
+    'vcsa.components_health': {
+        info:
+            '<code>-1</code>: unknown; ' +
+            '<code>0</code>: healthy; ' +
+            '<code>1</code>: healthy, but may have some problems; ' +
+            '<code>2</code>: degraded, and may have serious problems; ' +
+            '<code>3</code>: unavailable, or will stop functioning soon; ' +
+            '<code>4</code>: no health data is available.'
+            },
+
+    'vcsa.software_updates_health': {
+        info:
+            '<code>softwarepackages</code> represents information on available software updates available in the remote vSphere Update Manager repository.<br>' +
+            '<code>-1</code>: unknown; ' +
+            '<code>0</code>: no updates available; ' +
+            '<code>2</code>: non-security updates are available; ' +
+            '<code>3</code>: security updates are available; ' +
+            '<code>4</code>: an error retrieving information on software updates.'
+            }
 };