Use the Network Top Talkers dashboard to monitor network demand in your IaaS. In a shared environment, a few VMs generating excessive activity can impact the entire data center. While a single VM might not cause a serious problem, a few of them can.

Design Considerations

The Network Top Talkers dashboard helps you analyze how hard these VMs hit your IaaS. It classifies the workload into two: short bursts and sustained hits. A short burst lasts for a short period, maybe for a few minutes. A sustained hit can last for an hour and cause serious problems.

The Network Top Talker dashboard forms a pair with the Storage Heavy Hitter dashboard. To understand the IO demand in your environment, use both of them concurrently.

The Network Top Talkers dashboard displays sustained hits that last for an hour, as they can cause serious problems in a shared IaaS environment. You can identify the villain VMs and compare their demands with the capabilities of the underlying IaaS.

How to Use the Dashboard

The dashboard shows the current workload. This is the total network load (received and transmitted) from all the vSphere environments monitored by vRealize Operations Cloud. The idea is to give you an indicator on how hard the overall load is.

  • Select a data center from the data centers list.
    • The columns show the number of clusters, ESXi hosts, and VMs for each data center. The VM count includes the powered off VM. To only see the running VM count, edit the widget.
    • If you want to see information from all the data centers, select the vSphere world row.
    • Upon selection, the Total Demand Line chart and the Top Talkers tables fill up.
  • Total Demand Line Chart
    • The total throughput (received and transmitted) in the selected data center.
    • Displays both, the five minute peak and the hourly average in one line chart. You can click the metric name to hide it.
  • Top Talkers Table
    • The table shows the most demanding VM. You can identify the villain VM and compare their demands with the capabilities of the underlying IaaS. Knowing the infrastructure capability is important. For example, an ESXi with 2 x10 GB port can theoretically handle 20 GB TX + 20 GB RX as its full duplex.

Points to Note

  • Understanding high demand helps you monitor IaaS and plan your capacity. IaaS provides four services, CPU, memory, disk, and network. While CPU, memory, and disk are bound, an active VM can consume all your network bandwidth, packet per second capacity, and the storage IOPS capcity. A VM with 4 vCPU and 16 GB memory cannot consume more than this amount, the same applies to disk space. A VM configured with 100 GB disk space cannot consume more than that.
  • Network throughput, disk throughput, and disk IOPS can spike as their physical limits are very high per VM. This means that IaaS has enough capacity for all workloads and performs well until the VMs start consuming abnormally high amounts of network and disk bandwidth.