|
8 | 8 |
|
9 | 9 | There are two types of {PM-shortname} dashboards. Both provide different levels of details around power consumption metrics for a single cluster:
|
10 | 10 |
|
11 |
| -[discrete] |
12 |
| -== Power Monitoring / Overview dashboard |
| 11 | +[id="power-monitoring-overview-dashboard_{context}"] |
| 12 | +== Power Monitor / Overview dashboard |
13 | 13 |
|
14 |
| -With this dashboard, you can observe the following information: |
| 14 | +This dashboard allows you to view the following information: |
15 | 15 |
|
16 |
| -* An aggregated view of CPU architecture and its power source (`rapl-sysfs`, `rapl-msr`, or `estimator`) along with total nodes with this configuration |
| 16 | +Cluster-wide power consumption:: View current total, active, and idle CPU power consumption, grouped by zones. |
| 17 | +Node-level power details:: Analyze historical and current power consumption (total, active, and idle) for individual nodes. |
| 18 | +Hardware information:: Display CPU model and core counts for each node in the cluster. |
| 19 | +Time-series analysis:: Track power consumption trends over time with graphs that can be filtered by node and zone. This provides a comprehensive view of your cluster's energy usage. |
17 | 20 |
|
18 |
| -* Total energy consumption by a cluster in the last 24 hours (measured in kilowatt-hour) |
| 21 | +[id="power-monitor-namespace-pods-dashboard_{context}"] |
| 22 | +== Power Monitor / Namespace (Pods) dashboard |
19 | 23 |
|
20 |
| -* The amount of power consumed by the top 10 namespaces in a cluster in the last 24 hours |
| 24 | +This dashboard allows you to monitor and analyze power consumption for Kubernetes namespaces and pods. It provides the following information: |
21 | 25 |
|
22 |
| -* Detailed node information, such as its CPU architecture and component power source |
23 |
| - |
24 |
| -These features allow you to effectively monitor the energy consumption of the cluster without needing to investigate each namespace separately. |
25 |
| - |
26 |
| -[WARNING] |
27 |
| -==== |
28 |
| -Ensure that the *Components Source* column does not display `estimator` as the power source. |
29 |
| -
|
30 |
| -.The Detailed Node Information table with `rapl-sysfs` as the component power source |
31 |
| -image::power-monitoring-component-power-source.png[] |
32 |
| -
|
33 |
| -If {PM-kepler} is unable to obtain hardware power consumption metrics, the *Components Source* column displays `estimator` as the power source, which is not supported in Technology Preview. If that happens, then the values from the nodes are not accurate. |
34 |
| -==== |
35 |
| - |
36 |
| -[discrete] |
37 |
| -== Power Monitoring / Namespace dashboard |
38 |
| - |
39 |
| -This dashboard allows you to view metrics by namespace and pod. You can observe the following information: |
40 |
| - |
41 |
| -* The power consumption metrics, such as consumption in DRAM and PKG |
42 |
| - |
43 |
| -* The energy consumption metrics in the last hour, such as consumption in DRAM and PKG for core and uncore components |
44 |
| - |
45 |
| -This feature allows you to investigate key peaks and easily identify the primary root causes of high consumption. |
| 26 | +Top ten power consuming namespaces:: A real-time table showing the top ten namespaces based on their current power usage. This helps you quickly identify the most resource-intensive workloads. |
| 27 | +Total namespace power consumption:: A historical graph showing the total power consumption of pods within a selected namespace over time, grouped by zone. This helps you see trends and understand an application's or service's total power use. |
| 28 | +Individual pod power consumption:: A detailed graph showing the power consumption of individual pods, so you can analyze them in detail. |
0 commit comments