Monitor VMware ESXi with Grafana and Telegraf

# CentOS
sudo yum -y install telegraf

# Ubuntu
sudo apt-get -y install telegraf

sudo vim /etc/telegraf/telegraf.conf

# Configuration for sending metrics to InfluxDB
[[outputs.influxdb]]
    urls = ["http://10.10.1.20:8086"]
    database = "vmware"
    timeout = "0s"
    username = "monitoring"
    password = "DBPassword"

# Read metrics from VMware vCenter [[inputs.vsphere]] ## List of vCenter URLs to be monitored. These three lines must be uncommented ## and edited for the plugin to work. vcenters = [ “https://10.10.1.2/sdk” ] username = “[email protected]” password = “AdminPassword” # ## VMs ## Typical VM metrics (if omitted or empty, all metrics are collected) vm_metric_include = [ “cpu.demand.average”, “cpu.idle.summation”, “cpu.latency.average”, “cpu.readiness.average”, “cpu.ready.summation”, “cpu.run.summation”, “cpu.usagemhz.average”, “cpu.used.summation”, “cpu.wait.summation”, “mem.active.average”, “mem.granted.average”, “mem.latency.average”, “mem.swapin.average”, “mem.swapinRate.average”, “mem.swapout.average”, “mem.swapoutRate.average”, “mem.usage.average”, “mem.vmmemctl.average”, “net.bytesRx.average”, “net.bytesTx.average”, “net.droppedRx.summation”, “net.droppedTx.summation”, “net.usage.average”, “power.power.average”, “virtualDisk.numberReadAveraged.average”, “virtualDisk.numberWriteAveraged.average”, “virtualDisk.read.average”, “virtualDisk.readOIO.latest”, “virtualDisk.throughput.usage.average”, “virtualDisk.totalReadLatency.average”, “virtualDisk.totalWriteLatency.average”, “virtualDisk.write.average”, “virtualDisk.writeOIO.latest”, “sys.uptime.latest”, ] # vm_metric_exclude = [] ## Nothing is excluded by default # vm_instances = true ## true by default # ## Hosts ## Typical host metrics (if omitted or empty, all metrics are collected) host_metric_include = [ “cpu.coreUtilization.average”, “cpu.costop.summation”, “cpu.demand.average”, “cpu.idle.summation”, “cpu.latency.average”, “cpu.readiness.average”, “cpu.ready.summation”, “cpu.swapwait.summation”, “cpu.usage.average”, “cpu.usagemhz.average”, “cpu.used.summation”, “cpu.utilization.average”, “cpu.wait.summation”, “disk.deviceReadLatency.average”, “disk.deviceWriteLatency.average”, “disk.kernelReadLatency.average”, “disk.kernelWriteLatency.average”, “disk.numberReadAveraged.average”, “disk.numberWriteAveraged.average”, “disk.read.average”, “disk.totalReadLatency.average”, “disk.totalWriteLatency.average”, “disk.write.average”, “mem.active.average”, “mem.latency.average”, “mem.state.latest”, “mem.swapin.average”, “mem.swapinRate.average”, “mem.swapout.average”, “mem.swapoutRate.average”, “mem.totalCapacity.average”, “mem.usage.average”, “mem.vmmemctl.average”, “net.bytesRx.average”, “net.bytesTx.average”, “net.droppedRx.summation”, “net.droppedTx.summation”, “net.errorsRx.summation”, “net.errorsTx.summation”, “net.usage.average”, “power.power.average”, “storageAdapter.numberReadAveraged.average”, “storageAdapter.numberWriteAveraged.average”, “storageAdapter.read.average”, “storageAdapter.write.average”, “sys.uptime.latest”, ] # host_metric_exclude = [] ## Nothing excluded by default # host_instances = true ## true by default # ## Clusters cluster_metric_include = [] ## if omitted or empty, all metrics are collected # cluster_metric_exclude = [] ## Nothing excluded by default # cluster_instances = false ## false by default # ## Datastores datastore_metric_include = [] ## if omitted or empty, all metrics are collected # datastore_metric_exclude = [] ## Nothing excluded by default # datastore_instances = false ## false by default for Datastores only # ## Datacenters datacenter_metric_include = [] ## if omitted or empty, all metrics are collected # datacenter_metric_exclude = [ “*” ] ## Datacenters are not collected by default. # datacenter_instances = false ## false by default for Datastores only # ## Plugin Settings ## separator character to use for measurement and field names (default: “_”) # separator = “_” # ## number of objects to retreive per query for realtime resources (vms and hosts) ## set to 64 for vCenter 5.5 and 6.0 (default: 256) # max_query_objects = 256 # ## number of metrics to retreive per query for non-realtime resources (clusters and datastores) ## set to 64 for vCenter 5.5 and 6.0 (default: 256) # max_query_metrics = 256 # ## number of go routines to use for collection and discovery of objects and metrics # collect_concurrency = 1 # discover_concurrency = 1 # ## whether or not to force discovery of new objects on initial gather call before collecting metrics ## when true for large environments this may cause errors for time elapsed while collecting metrics ## when false (default) the first collection cycle may result in no or limited metrics while objects are discovered # force_discover_on_init = false # ## the interval before (re)discovering objects subject to metrics collection (default: 300s) # object_discovery_interval = “300s” # ## timeout applies to any of the api request made to vcenter # timeout = “60s” # ## Optional SSL Config # ssl_ca = “/path/to/cafile” # ssl_cert = “/path/to/certfile” # ssl_key = “/path/to/keyfile” ## Use SSL but skip chain & host verification insecure_skip_verify = true

insecure_skip_verify = true

sudo systemctl restart telegraf
sudo systemctl enable telegraf

$ influx -username 'username' -password 'DBPassword'
Connected to http://localhost:8086 version 1.6.4
InfluxDB shell version: 1.6.4

$ influx
Connected to http://localhost:8086 version 1.6.4
InfluxDB shell version: 1.6.4

> USE vmware
Using database vmware 

> SHOW MEASUREMENTS
name: measurements
name
----
cpu
disk
diskio
kernel
mem
processes
swap
system
vsphere_cluster_clusterServices
vsphere_cluster_mem
vsphere_cluster_vmop
vsphere_datacenter_vmop
vsphere_datastore_datastore
vsphere_datastore_disk
vsphere_host_cpu
vsphere_host_disk
vsphere_host_mem
vsphere_host_net
vsphere_host_power
vsphere_host_storageAdapter
vsphere_host_sys
vsphere_vm_cpu
vsphere_vm_mem
vsphere_vm_net
vsphere_vm_power
vsphere_vm_sys
vsphere_vm_virtualDisk
>