The main plot component of ClusterCockpit renders the metric values retrieved from the systems in a time dependent manner.
A selector crosshair is shown when hovering over the rendered data, data points corresponding to the legend are highlighted.
It is possible to zoom in by dragging a selection square with your mouse. Double-Clicking into the plot will reset the zoom.
Hovering over the rendered data will display a legend as hovering box colored in yellow. Depending on the amount of data shown, this legend will render differently:
- Single Dataset: Runtime and Dataset Identifier Only
- 2 to 6 Datasets: Runtime, Line Color and Dataset Identifier
- 7 to 12 Datasets: Runtime and Dataset Identifier Only
- More than 12 Datasets: No Legend
- Statistics Datasets: Runtime and Dataset Identifier Only (See below)
The “no legend” case is required to not clutter the display in case of high data volume, e.g. core granularity data for more than 128 cores, which would result in 128 legend entries, possibly blocking the plotting area of metric graphs below.
The plots’ background is colored depending the average value of the viewed metric in respect to its configured threshold values. The three cases are
- White: Metric average within expected parameters. No performance impact.
- Yellow: Metric average below expected parameters, but not yet critical. Possible performace impact.
- Red: Metric average unexpectedly low. Indicator for suboptimal usage of resources. Performance impact to be expected.
In the job list views, high amounts of data are by default rendered as a statistical representation of the numerous, single datasets:
- Maximum: The maximum values of the base datasets of each point in time, over time. Colored in green.
- Average: The average values of the base datasets of each point in time, over time. Colored in black.
- Minimum: The minimal values of the base datasets of each point in time, over time. Colored in red.
Histograms display (binned) data allowing distributions of the repective data source to be visualized. Data highlighting, zooming, and resetting the zoom work as described for metric plots.
A roofline plot, or roofline model, represents the utilization of available resources as the relation between computation and memory usage.
Roofline models rendered as dotted plots display the utilization of hardware resources over time.
The roofline model shown in the analysis view, as the single exception, is rendered as a heatmap. This is due to the data being displayed is derived from a number of jobs greater than one, since the analysis view returns all jobs matching the selected filters. The roofline therefore colors regions of accumulated activity in increasing shades of red, depicting the regions below the roofs in which the returned jobs primarily perform.
A polar, or radar, plot represents the utilization of three key metrics:
mem_bw. Both the maximum and the average utilization as a fraction of the 100% theoretical maximum (labelled as
1.0) are rendered on three axes. This leads to an increasing area, which in return marks increasingly optimal resource usage. In principle, this is a graphic representation of data also shown in the footprint component.
By clicking on one of the two legends, the respective dataset will be hidden. This can be useful if high overlap reduces visibility.
Scatter / Bubble Plot
Bubble scatter plots show the position of the averages of two selected metrics in relation to each other.
Each circle represents one job, while the size of a circle is proportional to its node hours. Darker circles mean multiple jobs have the same averages for the respective metric selection.
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.