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
Ilya Mashchenko committed
Sep 17, 2019 at 17:25 UTC
74074e815bc02c5d6b28d7f6f90b9872ee5ba5de
3 files changed
+162
-1
health/Makefile.am
+1
@@ -85,6 +85,7 @@ dist_healthconfig_DATA = \
85
health.d/tcp_resets.conf \
86
health.d/udp_errors.conf \
87
health.d/varnish.conf \
88
+ health.d/vcsa.conf \
89
health.d/vsphere.conf \
90
health.d/web_log.conf \
91
health.d/wmi.conf \
health/health.d/vcsa.conf
new
+122
@@ -0,0 +1,122 @@
1
+
2
+# make sure vcsa is running and responding
3
+
4
+template: vcsa_last_collected_secs
5
+ on: vcsa.system_health
6
+ calc: $now - $last_collected_t
7
+ units: seconds ago
8
+ every: 10s
9
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
10
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
11
+ delay: down 5m multiplier 1.5 max 1h
12
+ info: number of seconds since the last successful data collection
13
+ to: sysadmin
14
+
15
+# Overall system health:
16
+# - 0: all components are healthy.
17
+# - 1: one or more components might become overloaded soon.
18
+# - 2: one or more components in the appliance might be degraded.
19
+# - 3: one or more components might be in an unusable status and the appliance might become unresponsive soon.
20
+# - 4: no health data is available.
21
+
22
+template: vcsa_system_health
23
+ on: vcsa.system_health
24
+ lookup: max -10s unaligned of system
25
+ units: status
26
+ every: 10s
27
+ warn: ($this == 1) || ($this == 2)
28
+ crit: $this == 3
29
+ delay: down 1m multiplier 1.5 max 1h
30
+ info: overall system health status
31
+ to: sysadmin
32
+
33
+# Components health:
34
+# - 0: healthy.
35
+# - 1: healthy, but may have some problems.
36
+# - 2: degraded, and may have serious problems.
37
+# - 3: unavailable, or will stop functioning soon.
38
+# - 4: no health data is available.
39
+
40
+template: vcsa_swap_health
41
+ on: vcsa.components_health
42
+ lookup: max -10s unaligned of swap
43
+ units: status
44
+ every: 10s
45
+ warn: $this == 1
46
+ crit: ($this == 2) || ($this == 3)
47
+ delay: down 1m multiplier 1.5 max 1h
48
+ info: swap health status
49
+ to: sysadmin
50
+
51
+template: vcsa_storage_health
52
+ on: vcsa.components_health
53
+ lookup: max -10s unaligned of storage
54
+ units: status
55
+ every: 10s
56
+ warn: $this == 1
57
+ crit: ($this == 2) || ($this == 3)
58
+ delay: down 1m multiplier 1.5 max 1h
59
+ info: storage health status
60
+ to: sysadmin
61
+
62
+template: vcsa_mem_health
63
+ on: vcsa.components_health
64
+ lookup: max -10s unaligned of mem
65
+ units: status
66
+ every: 10s
67
+ warn: $this == 1
68
+ crit: ($this == 2) || ($this == 3)
69
+ delay: down 1m multiplier 1.5 max 1h
70
+ info: mem health status
71
+ to: sysadmin
72
+
73
+template: vcsa_load_health
74
+ on: vcsa.components_health
75
+ lookup: max -10s unaligned of load
76
+ units: status
77
+ every: 10s
78
+ warn: $this == 1
79
+ crit: ($this == 2) || ($this == 3)
80
+ delay: down 1m multiplier 1.5 max 1h
81
+ info: load health status
82
+ to: sysadmin
83
+
84
+template: vcsa_database_storage_health
85
+ on: vcsa.components_health
86
+ lookup: max -10s unaligned of database_storage
87
+ units: status
88
+ every: 10s
89
+ warn: $this == 1
90
+ crit: ($this == 2) || ($this == 3)
91
+ delay: down 1m multiplier 1.5 max 1h
92
+ info: database storage health status
93
+ to: sysadmin
94
+
95
+template: vcsa_applmgmt_health
96
+ on: vcsa.components_health
97
+ lookup: max -10s unaligned of applmgmt
98
+ units: status
99
+ every: 10s
100
+ warn: $this == 1
101
+ crit: ($this == 2) || ($this == 3)
102
+ delay: down 1m multiplier 1.5 max 1h
103
+ info: appl mgmt health status
104
+ to: sysadmin
105
+
106
+
107
+# Software updates health:
108
+# - 0: no updates available.
109
+# - 2: non-security updates are available.
110
+# - 3: security updates are available.
111
+# - 4: an error retrieving information on software updates.
112
+
113
+template: vcsa_software_updates_health
114
+ on: vcsa.software_updates_health
115
+ lookup: max -10s unaligned of software_packages
116
+ units: status
117
+ every: 10s
118
+ warn: $this == 4
119
+ crit: $this == 3
120
+ delay: down 1m multiplier 1.5 max 1h
121
+ info: software packages health status
122
+ to: sysadmin
web/gui/dashboard_info.js
+39
-1
@@ -498,6 +498,12 @@ netdataDashboard.menu = {
498
title: 'vSphere',
499
icon: '<i class="fas fa-server"></i>',
500
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.'
501
+ },
502
+
503
+ 'vcsa': {
504
+ title: 'VCSA',
505
+ icon: '<i class="fas fa-server"></i>',
506
+ 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>.'
507
}
508
};
509
@@ -2587,5 +2593,37 @@ netdataDashboard.context = {
2593
2594
'vsphere.overall_status': {
2595
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.'
2590
- }
2596
+ },
2597
+
2598
+ // ------------------------------------------------------------------------
2599
+ // VCSA
2600
+ 'vcsa.system_health': {
2601
+ info:
2602
+ '<code>-1</code>: unknown; ' +
2603
+ '<code>0</code>: all components are healthy; ' +
2604
+ '<code>1</code>: one or more components might become overloaded soon; ' +
2605
+ '<code>2</code>: one or more components in the appliance might be degraded; ' +
2606
+ '<code>3</code>: one or more components might be in an unusable status and the appliance might become unresponsive soon; ' +
2607
+ '<code>4</code>: no health data is available.'
2608
+ },
2609
+
2610
+ 'vcsa.components_health': {
2611
+ info:
2612
+ '<code>-1</code>: unknown; ' +
2613
+ '<code>0</code>: healthy; ' +
2614
+ '<code>1</code>: healthy, but may have some problems; ' +
2615
+ '<code>2</code>: degraded, and may have serious problems; ' +
2616
+ '<code>3</code>: unavailable, or will stop functioning soon; ' +
2617
+ '<code>4</code>: no health data is available.'
2618
+ },
2619
+
2620
+ 'vcsa.software_updates_health': {
2621
+ info:
2622
+ '<code>softwarepackages</code> represents information on available software updates available in the remote vSphere Update Manager repository.<br>' +
2623
+ '<code>-1</code>: unknown; ' +
2624
+ '<code>0</code>: no updates available; ' +
2625
+ '<code>2</code>: non-security updates are available; ' +
2626
+ '<code>3</code>: security updates are available; ' +
2627
+ '<code>4</code>: an error retrieving information on software updates.'
2628
+ }
2629
};