ClusterCockpit home table for two configured clusters
The entrypoint for each login via the login mask is a table containing each configured cluster as a row with the following columns:
Name: The configured clusters’ name
Running Jobs: Number of Jobs currently running longer than 5 minutes (or configured shortRunning amount of time)
Clicking the Link will forward to the job list with preset filters for cluster and running jobs
Total Jobs: Number of Jobs in the respective job-archive
Clicking the Link will forward to the job list with preset filter for cluster
Status View: Link to the status view of the respective cluster
This column is only shown for users with admin authority.
Systems View: Link to the nodes view view of the respective cluster
This column is only shown for users with admin authority.
Navigation Bar
The navigation bar allows direct access to ClusterCockpits’ different views and functions. Depending on the users’ authorization, the selectable views can differ.
For most viewports, the navigation bar is rendered fully expanded:
On smaller viewports, the navigation bar will be rendered in one of two collapsed states:
Partially collapsed navigation bar. ‘Groups’ will expand to show links for Users, Projects, Tags, and Nodes views. ‘Stats’ will expand to show links for Analysis and Status views. Searchbar, Logout and Settings not shown here, but are still rendered explicitly in this case.
On mobile devices, the navigation bar as a whole is reduced into a burger navigation icon, and will display all views, as well as the searchbar, as stacked navigation menu.
1 - Settings
Webinterface Settings Page
The settings view allows non-privileged users to customize how metric plots are rendered. This includes line width, number of plots per row (where applicable), whether backgrounds should be colored, and the color scheme of multi-line metric plots.
Privileged users will also find an administrative interface for handling local user accounts. This includes creating local accounts from the interface, editing user roles, listing and deleting existing users, generating JSON Web Tokens for API usage, and delegating managed projects for manager role users.
Plotting Options
Field
Options
Note
Line Width
# Pixels
Width of the lines in the timeseries plots
Plots Per Row
# Plots
How many plots to show next to each other on pages such as the job or nodes views
Colored Backgrounds
Yes / No
Color plot backgrounds indicating mean values within warning thresholds
Color Scheme
See Below
Render multi-line metric plots in different color ranges
Color Schemes
Name
Colors
Default
Autumn
Beach
BlueRed
Rainbow
Binary
GistEarth
BlueWaves
BlueGreenRedYellow
Administration Options
Create User
New users can be created directly via the web interface. On successful creation a green response message will be returned, and the user is directly visible in the “Special Users” table - If the user has at least two roles, or a single role other than user.
Error messages will also be displayed if the user creation process failed. No user account is saved to the database in this case.
Please note: Users are usually imported via LDAP on ClusterCockpit startup.
Field
Option
Note
Username (ID)
string
Required, must be unique
Password
string
Only API users are allowed to have a blank password, users with a blank password can only authenticate via JW tokens
Allows to inspect jobs and users of all projects, has no admin view or settings access
Admin
General access
Special Users
This table does not contain users who only have user as their only role saved in the database. This is the case for all users created by LDAP import, and thus, these users will not be shown here. However, LDAP users’ roles can still be edited, and will appear in the table as soon as a authority higher than user or two authorities were granted.
All other special case users, e.g. new users manually created with support role, will appear in the list.
User accounts can be deleted by pressing the respective function displayed for each user entry - A verification pop-up window will appear to stop accidental user deletion.
Additionally, JWT tokens for specific users can be generated here as well.
Column
Example
Description
Username
abcd1
Username of this user
Name
Paul Atreides
Name of this user
Project(s)
abcd
Managed project(s) of this user
Email
demo@demo.com
Email adress of this user
Roles
admin,api
Role(s) of this user
JWT
Press button to reveal freshly generated token
Generate a JWT for this user for use with the CC REST API endpoints
Delete
Press button to verify deletion
Delete this user
Edit User Role
On creation, users can only have one role. However, it is allowed to assign multiple roles to an user account. The addition or removal of roles is performed here.
Enter an existing username and select an existing (for removal) or new (for addition) role in the drop-down menu.
Then press the respective button to remove or add the selected authority from the user account. Errors will be displayed if existing roles are added or non-existing roles are removed.
Edit Managed Projects
On creation, users can only have one managed project. However, it is allowed to assign multiple projects to a manager account. The addition or removal of projects is performed here.
Enter an existing username and select an existing (for removal) or new (for addition) project by entering the respective projectId.
Then press the respective button to remove or add the selected project from the manager account. Errors will be displayed if existing projects are added, non-existing projects are removed, or if the user account is not authorized to manage projects at all.
2 - Searchbar
Toplevel Searchbar Functionality
ClusterCockpit Searchbar
The top searchbar will handle page wide searches either by entering a searchterm directly as <query>, or by using a “keyword” implemented in the form of <keyword>:<query>. Entering a searchterm directly will start a hierarchical search which will return the first match in the hierarchy (see table below). It is recommended to supply the search with a keyword to specify the searched entity. For example, jobName:myJobName will specifically search for all jobs which have the queried string (or a part thereof) in their metadata jobName field. For all keywords with examples, see the table below.
Both keywords and queries are trimmed of all spaces before performing the search, returning the same results independently of location and number of spaces, e.g. name : Paul and name: paul are both handled identically.
Unprocessable queries will return a message detailing the cause of the error.
Available Keywords
Please note: Hovering over the information icon right of the query field will list all keywords in the webinterface.
Only active users are returned; Users without jobs are not shown. Also, a Last 30 Days is active by default and might filter out expected users. Admin Only
Works with partial queries. Only active users are returned; Users without jobs are not shown. Also, a Last 30 Days is active by default and might filter out expected users. Admin Only
Most plots visible in the ClusterCockpit webinterface are implemented via uPlot or Chart.js, which both offer various functionality to the user.
Metric Plots
The main plot component of ClusterCockpit renders the metric values retrieved from the systems in a time dependent manner.
Interactivity
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.
Conditional Legends
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.
Example
Eight datasets result in an average value within expected parameters, the background remains white. The legend displays each allocated hostname as dataset identifier.
Colored Backgrounds
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.
Example
Two datasets result in an average value of less than the configured ‘alert’ threshold: The legend displays both identifiers with their respective color, while the background is colored in red to indicate suboptimal metric performance.
Statistics Variant
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.
Example
A job with a high count of allocated nodes, running well within expected metric parameters. Since, by definition, the colors for this statistical render are always identical, only the runtime and the statistic datasets’ identifiers are shown.
Histograms
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.
Example
Duration distribution of selected jobs. The legends will display the X-Axis value label first, then the Y-Axis value label. The legend is shown for each bar individually when hovering the selection crosshair over the inspected bar. A highlight will show as white dot at the top.
Roofline Plot
A roofline plot, or roofline model, represents the utilization of available resources as the relation between computation and memory usage.
Dotted Roofline
Roofline models rendered as dotted plots display the utilization of hardware resources over time.
Please Note: The roofline models rendered in the status view are not job-derived, but display the utilization of single nodes at the moment of data-collection. Therefore, no time information is required, and alle dots are colored blue.
Example
Roofline model as shown for a single job. Time information is encoded in the color range, starting from blue dots and ending in red dots.
Heatmap Roofline
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.
Please note: The plot is rendered in double-logarithmic scaling, yet the lines in the background seem linear: The heatmap roofline is rendered manually (and directly) using only HTML canvas, while the dotted roofline model is rendered with the help of the uPlot package, which allows easy display of double-log scales.
Example
In this example, the selected jobs perform in near optimal, as depicted by increased job activity right below the first ‘knee’ of the roofline model.
Polar Plots
A polar, or radar, plot represents the utilization of three key metrics: flops_any, mem_used, and 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.
Example
In this example, the selected job performs quite well, as depicted in the acceptable and equally distributed usage of core metrics. On average, all three metrics are utilized at about 20% (0.2) of the configured hardware maximum. At a point in time, the maximum even reached close to 100% (1.0) of the memory bandwidth (mem_bw).
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.
Example
In this example, the selected metrics are accelerator clock on the X-axis and accelerator temperature on the Y-axis. Expectedly, long running, high-clock jobs accumulate in the top-right corner, while jobs with less demanding (less clocking) jobs remain cooler.
4 - Filters
Webinterface Filter Options
Filter Button as displayed in Job List Views
The ClusterCockpit filter component is used for reducing the number of jobs, either for direct display in job list views, or to specifiy the data-source for collecting information displayed in user or project tables, as well as the analysis view.
Filter Options
Three active filters have reduced the total job count considerably
Multiple filters can be easily combined by selecting more than one option of the available filters.
By clicking on the respective filter pill, colored in blue, and located right of the filter component, one can directly access the respective filters’ menu for editing, or removing, the filter.
At the moment, the following filters are implemented:
Cluster/Partition
Select a configured cluster, or a specified partition of a given cluster, and display only jobs started on that cluster (and partition).
Options: All cluster names, and nested partition names, configured in config.json
Default: Any Cluster (Any Partition)
Job States
Select one or more job states, and display only jobs matching the selected criteria.
Select the timeframe in which jobs were started, and display only jobs matching the selected criteria.
Options: Free selection of date dd.mm.YYYY and time hh:mm for from and to limits.
Default: All Starttimes
Preset: Jobs started one month ago until $now
Duration
Select the duration of jobs, and display only jobs matching the selected criteria.
Options: Duration less than hh:mm, duration more than hh:mm, duration between two duration selections. Only one of the three options can be used at a time.
Default: All Durations
Tags
Select one or more job tags, and display only jobs tagged with the selected tags.
Options: All available tags. It is possible to search within the list of tags.
Default: No selection
Resources
Select a named node or specify an amount of used resources, and display only jobs matching the selected criteria.
Options:
Named node free text field: Enter a hostname here to only return jobs which were ran on this node.
Range selectors: Select a range of allocated job resources ranging from the minimal to the maximum configured resource count of all clusters. If the cluster filter is set, the ranges are limited to the respective resources’ configuration. Available resources are:
Nodes
HWThreads
Accelerators (if available)
Default: No named node, full resource ranges of all configured clusters
Statistics
Specify ranges of metric statistics, and display only jobs matching the selected criteria.
Options:
FLOPs (Avg.): Select Range From-To by dragging the slider or entering values directly.
Memory Bandwith (Avg.): Select Range From-To by dragging the slider or entering values directly.
Load (Avg.): Select Range From-To by dragging the slider or entering values directly.
Memory Used (Max.): Select Range From-To by dragging the slider or entering values directly.
Default: Full metric statistics ranges as configured
Start Time Quick Selections
Please note: Not available in all views!
Quickly select a preconfigured range of job start times. Will display as named start time filter.
Options:Last 6 hours, Last 24 hours, Last 7 Days, Last 30 Days
Default: No selection
5 - Views
View-Specific Frontend Usage Information.
Usage descriptions for each view of the ClusterCockpit web interface.
5.1 - My Jobs
All Jobs as Table of the Active User
Personal User Job View. Similar to the general job list view, this view expands it by user-specific meta data, as well as distributions histograms.
The “My Jobs” View is available to all users regardless of authority and displays the users personal jobs, i.e. jobs started by this users username on the cluster systems.
The view is a personal variant of the user job view and therefore also consists of three components: Basic Information about the users jobs, selectable statistic histograms of the jobs, and a generalized job list.
Users are able to change the sorting, select and reorder the rendered metrics, filter, and activate a periodic reload of the data.
User Information and Basic Distributions
The top row always displays personal usage information, independent of the selected filters.
Additional histograms depicting the distribution of job duration and number of nodes occupied by the returned jobs are affected by the selected filters.
Information displayed:
Username
Total Jobs
Short Jobs (as defined by the configuration, default: less than 300 second runtime)
Total Walltime
Total Core Hours
Selectable Histograms
Histograms depicting the distribution of the selected jobs’ statistics can be selected from the top navbar “Select Histograms” button. The displayed data is based on the jobs returned from active filters, and will be pulled from the database, or in case of running jobs, calculated from the available metric data directly.
Available Metrics for Histograms:cpu_load, flops_any, mem_used, mem_bw, net_bw, file_bw
Job List
The job list displays all jobs started by your username on the systems. Additional filters will always respect this limitation. For a detailed description of the job list component, see the related documentation.
5.2 - User Jobs
All Jobs as Table of a Selected User
User Job View. Similar to the general job list view, this view expands it by user-specific meta data, as well as distribution histograms.
The “User Jobs” View is only available to management and supporting staff and displays jobs of the selected user, i.e. jobs started by this users username on the cluster systems.
The view consists of three components: Basic Information about the users jobs, selectable statistic histograms of the jobs, and a generalized job list.
Users are able to change the sorting, select and reorder the rendered metrics, filter, and activate a periodic reload of the data.
User Information and Basic Distributions
The top row always displays information about the user, independent of the selected filters.
Additional histograms depicting the distribution of job duration and number of nodes occupied by the returned jobs are affected by the selected filters.
Information displayed:
Username
Total Jobs
Short Jobs (as defined by the configuration, default: less than 300 second runtime)
Total Walltime
Total Core Hours
Selectable Histograms
Histograms depicting the distribution of the selected jobs’ statistics can be selected from the top navbar “Select Histograms” button. The displayed data is based on the jobs returned from active filters, and will be pulled from the database, or in case of running jobs, calculated from the available metric data directly.
Available Metrics for Histograms:cpu_load, flops_any, mem_used, mem_bw, net_bw, file_bw
Job List
The job list displays all jobs started by this users username on the systems. Additional filters will always respect this limitation. For a detailed description of the job list component, see the related documentation.
5.3 - Job List
A Configurable Table Displaying Jobs According to Filters
Job List. In this example, the optional footprint is displayed, two filters are active, and the table is refreshed every minute. The first job has a high node count, therefore the plots are rendered in the statistics variant. The ‘mem_bw’ metric likely has artifacts as shown by the grey footprint. The second job has tags and displays less than optimal performance in the ‘flops_any’ metric, coloring the respective plot background in orange.
The primary view of ClusterCockpits webinterface is the tabular listing of jobs, which displays various information about the jobs returned by the selected filters. This information includes the jobs’ full meta data, such as runtime or job state, as well as an optional footprint, allowing quick assessment of the jobs performance.
Most importantly, the list displays a selectable array of metrics as time dependent metric plots, which allows detailed insight into the jobs performance at a glance.
Default Users: For users without additional roles, this view is labelled as ‘Job Search’. Displayed jobs are limited to jobs started by the active user, otherwise the functionality is identical, e.g. filtering or footprint display.
Manager Users: For users with additional manager role, this view is labelled as ‘Managed Jobs’. Displayed jobs are limited to jobs started by users of the managed projects (usergroups), otherwise the functionality is identical, e.g. filtering or footprint display.
Job List Toolbar
Several options allow configuration of the displayed data, which are also persisted for each user individually, either for general usage or by cluster.
Sorting
Basic selection of sorting parameter and direction. By default, jobs are sorted by starting timestamp in descending order (latest jobs first). Other selections to sort by are
Duration
Number of Nodes
Maximum Memory Used
Average FLOPs
Average Memory Bandwidth
Average Network Bandwidth
Switching of the sort direction is achieved by clicking on the arrow icon next to the desired sorting parameter.
Metrics
Selection of metrics shown in the tabular view for each job. The list is compiled from all available configured metrics of the ClusterCockpit instance, and the tabular view will be updated upon applying the changes.
In addition to the metric names themselves, the availability by cluster is indicated as comma seperated list next to the metric identifier. This information will change to the availablility by partition if the cluster filer is active.
It is furthermore possible to edit the order of the selected metrics. This can be achieved by dragging and dropping the metric selectors to the desired order, where the topmost metric will be displayed next to the “Job Info” column, and additional metrics will be added on the right side.
Lastly, the optional “Footprint” Column can be activated (and deactivated) here. It will always be rendered next to the “Job Info” column, while metrics start right of the “Footprint” column, if activated.
Job Count
The total number of jobs returned by the backend for the given set of filters.
Filters
Selection of filters applied to the queried jobs. By default, no filters are activated if the view was opened via the navigation bar. At multiple location throughout the web-interface, direct links will lead to this view with one or more preset filters active, e.g. selecting a clusters’ “running jobs” from the home page will open this view displaying only running jobs of that cluster.
Possible options are:
Cluster/Partition: Filter by configured cluster (and partitions thereof)
Job State: Filter by defined job state(s)
Start Time: Filter by start timestamp
Duration: Filter by job duration
Tags: Filter by tags assigned to jobs
Resources: Filter by allocated resources or named node
Statistics: Filter by average usage of defined metrics
Each filter and its default value is described in detail here.
Search and Reload
Search for specific username or project using the searchbox, force a complete reload of the table data, or set a timed periodic reload (30, 60, 120, 300 Seconds).
Job List Table
The main component of the job list view renders data pulled from the database, the job archive (completed jobs) and the configured metric data source (running jobs).
Job Info
The meta data containing general information about the job is represented in the “Job Info” column, which is always the first column to be rendered. From here, users can navigate to the detailed view of one specific job as well as the user or project specific job lists.
Field
Example
Description
Destination
Job Id
123456
The JobId of the job assigned by the scheduling daemon
Indicator for the allocated resources. Single resources will be displayed by name, i.e. exclusive single-node jobs or shared resources. Multiples of resources will be indicated by icons for nodes, CPU Threads, and accelerators.
-
Partition
main
The cluster partition this job was startet at
-
Start Timestamp
10.1.2024, 10:00:00
The epoch timestamp the job was started at, formatted for human readability
-
Duration
0:21:10
The runtime of the job, will be updated for running jobs on reload. Additionally indicates the state of the job as colored pill
-
Walltime
24:00:00
The allocated walltime for the job as per job submission script
-
Footprint
The optional footprint column will show base metrics for job performance at a glance, and will hint to performance (and performance problems) in regard to configurable metric thresholds.
Field
Description
Note
cpu_load
Average CPU utilization
-
flops_any
Floprate calculated as f_any = (f_double x 2) + f_single
-
mem_bw
Average memory bandwidth used
Non-GPU Cluster only
mem_used
Maximum memory used
Non-GPU Cluster only
acc_utilization
Average accelerator utilization
GPU Cluster Only
Colors and icons differentiate between the different warning states based on the configured threshold of the metrics. Reported metric values below the warning threshold simply report bad performance in one or more metrics, and should therefore be inspected by the user for future performance improvement.
Metric values colored in blue, however, usually report performance above the expected levels - Which is exactly why these metrics should be inspected as well. The “maximum” thresholds are often the theoretically achievable performance by the respective hardware component, but rarely are they actually reached. Inspecting jobs reporting back such levels can lead to averaging errors, unrealistic spikes in the metric data or even bugs in the code of ClusterCockpit.
Color
Level
Description
Note
Blue
Info
Metric value below maximum configured peak threshold
Selected metrics are rendered here in the selected order as metric lineplots. Aspects of the rendering can be configured at the settings page.
5.4 - Job
Detailed Single Job Information View
Job View. This example shows a completed, shared job with lacking ‘flops_any’ performance.
The job view displays all data related to one specific job in full detail, and allows detailed inspection of all metrics at several scopes, as well as manual tagging of the job.
Top Bar
The top bar of each job view replicates the “Job Info” and “Footprint” seen in the job list, and additionally renders general metric information in specialized plots.
For shared jobs, a list of jobs which run (or ran) concurrently is shown as well.
Job Info
Identical to the job list equivalent, this component displays meta data containing general information about the job. From here, users can navigate to the detailed view of one specific job as well as the user or project specific job lists.
Field
Example
Description
Destination
Job Id
123456
The JobId of the job assigned by the scheduling daemon
Indicator for the allocated resources. Single resources will be displayed by name, i.e. exclusive single-node jobs or shared resources. Multiples of resources will be indicated by icons for nodes, CPU Threads, and accelerators.
-
Partition
main
The cluster partition this job was startet at
-
Start Timestamp
10.1.2024, 10:00:00
The epoch timestamp the job was started at, formatted for human readability
-
Duration
0:21:10
The runtime of the job, will be updated for running jobs on reload. Additionally indicates the state of the job as colored pill
-
Walltime
24:00:00
The allocated walltime for the job as per job submission script
-
Footprint
Identical to the job list equivalent, this component will show base metrics for job performance at a glance, and will hint to job quality and problems in regard to configurable metric thresholds. In contrast to the job list, it is always active and shown in the detailed job view.
Field
Description
Note
cpu_load
Average CPU utilization
-
flops_any
Floprate calculated as f_any = (f_double x 2) + f_single
-
mem_bw
Average memory bandwidth used
-
mem_used
Maximum memory used
Non-GPU Cluster only
acc_utilization
Average accelerator utilization
GPU Cluster Only
Colors and icons differentiate between the different warning states based on the configured thresholds of the metrics. Reported metric values below the warning threshold simply report bad performance in one or more metrics, and should therefore be inspected by the user for future performance improvement.
Metric values colored in blue, however, usually report performance above the expected levels - Which is exactly why these metrics should be inspected as well. The “maximum” thresholds are often the theoretically achievable performance by the respective hardware component, but rarely are they actually reached. Inspecting jobs reporting back such levels can lead to averaging errors, unrealistic spikes in the metric data or even bugs in the code of ClusterCockpit.
Color
Level
Description
Note
Blue
Info
Metric value below maximum configured peak threshold
Job performance impacted with high probability - Inspection recommended
Dark Grey
Error
Metric value extremely above maximum configured threshold
Inspection required - Metric spikes in affected metrics can lead to errorneous average values
Specific to the job view: In the job view, the footprint component also allows for 1:1 rendering of HTML code, saved within the jobs’ meta data secton of the database. This is intended for administrative messages towards the user who created the job, e.g. for displaying warning, hints, or contact information.
Examples
Footprint of a job with performance well within expected parameters, ‘mem_bw’ even overperforms.
Footprint of an accelerated job with mixed performance parameters.
Footprint of a job with performance averages way above the expected maxima - Look for artifacts!
Concurrent Jobs
In the case of a shared job, this component will display all jobs, which were run on the same hardware at the same time. “At the same time” is defined as “has a starting or ending time which lies between the starting and ending time of the reference job” for this purpose.
A cautious period of five minutes is applied to both limits, in order to restrict display of jobs which have too little overlap, and would just clutter the resulting list of jobs.
Each overlapping job is listed with its jobId as a link leading to this jobs detailed job view.
Polar Representation
A polar plot representing the utilization of three key metrics: flops_any, mem_used, and mem_bw. Both the maximum and the average are rendered. In principle, this is a graphic representation of data also shown in the footprint component.
Roofline Representation
A roofline plot representing the utilization of available resources as the relation between computation and memory usage over time (color scale blue -> red).
Metric Plot Table
The views’ middle section consists of metric plots for each metric selected in the “Metrics” selector, which defaults to all configured metrics.
The data shown per metric defaults to the smallest available granularity of the metric with data of all nodes, but can be changed at will by using the drop down selectors above each plot.
Please note: The statistical representation is not yet available for metric plots in this view. Jobs with high allocated node counts will be showing one line for each core if switched to this granilarity!
Tagging
Manual tagging of jobs is performed by using the “Manage Tags” option.
Existing tags are listed, and can be added to the jobs’ database entry simply by pressing the respective button.
The list can be filtered for specific tags by using the “Search Tags” prompt.
New tags can be created by entering a new type:name combination in the search prompt, which will display a button for creating this new tag.
Statistics and Meta Data
Statistics Table. ‘cpu_power’ granularity is set to ‘socket’. Tabs above switch the contents to the job script or slurm information, both read from the jobs metadata field.
On the bottom of the job view, additional information about the job is collected. By default, the statistics of selected metrics are shown in tabular form, each in their metrics’ native granularity.
Statistics Table
The statistics table collects all metric statistical values (min, max, avg) for each allocated node and each granularity.
The metrics to be displayed can be selected using the “Metrics” selection pop-up window. In the header, next to the metric name, a second drop down allows the selection of the displayed granularity.
Core and Accelerator metrics default to their respective native granularities automatically.
Job Script
This tab displays the job script with which whis job was started on the systems.
Slurm Info
THis tab displays information returned drom the SLURM batch process management software.
5.5 - Users
Table of All Users Running Jobs on the Clusters
User Table, sorted by ‘Total Jobs’ in descending order. In addition, active filters reduce the underlying data to jobs with more than one hour runtime, started on the GPU accelerated cluster.
This view lists all users which are, and were, active on the configured clusters. Information about the total number of jobs, walltimes and calculation usages are shown.
It is possible to filter the list by username using the equally named prompt, which also accepts partial queries.
The filter component allows limitation of the returned users based on job parameters like start timestamp or memory usage.
The table can be sorted by clicking the respective icon next to the column headers.
Please Note: By default, a “Last 30 Days” filter is activated by default when opening this view.
Managers Only: For users with manager authority, this view will be titled ‘Managed Users’ in the navigation bar. Managers will only be able to see other user accounts of the managed projects.
Details
Column
Description
Note
User Name
The user jobs are associated with
Links to the users’ job list with preset filter returning only jobs of this user and additional histograms
Total Jobs
Users’ total of all started jobs
Total Walltime
Users’ total requested walltime
Total Core Hours
Users’ total of all used core hours
Total Accelerator Hours
Users’ total of all used accelerator hours
Please Note: This column is always shown, and will return 0 for clusters without installed accelerators
5.6 - Projects
Table of All Projects Running Jobs on the Clusters
Project Table, sorted by ‘Total Jobs’ in descending order. In addition, active filters reduce the underlying data to jobs with less than six hours runtime, started on the CPU exclusive cluster.
This view lists all projects (usergroups) which are, and were, active on the configured clusters. Information about the total number of jobs, walltimes and calculation usages are shown.
It is possible to filter the list by project name using the equally named prompt, which also accepts partial queries.
The filter component allows limitation of the returned projects based on job parameters like start timestamp or memory usage.
The table can be sorted by clicking the respective icon next to the column headers.
Please Note: By default, a “Last 30 Days” filter is activated by default when opening this view.
Details
Column
Description
Note
Project Name
The project (usergoup) jobs are associated with
Links to a job list with preset filter returning only jobs of this project
Total Jobs
Project total of all started Jobs
Total Walltime
Project total requested walltime
Total Core Hours
Project total of all used core hours used
Total Accelerator Hours
Project total of all used accelerator hours
Please Note: This column is always shown, and will return 0 for clusters without installed accelerators
5.7 - Tags
Lists Active Tags Used in the Frontend
This view lists all tags currently used within the ClusterCockpit instance:
The type of the tag(s) is displayed as dark grey header, collecting all tags which share it.
The names of all tags sharing one type are rendered as yellow pills below the header.
How often a tag was applied to a job is shown in the number following the tags name
Each tags’ pill is clickable, and leads to a job list with a preset filter matching only jobs tagged with this specific label.
Please note: Creating tags and adding them to jobs is either done by using the respective REST API call, or manually from the job view.
5.8 - Nodes
Node Based Metric Information of one Cluster
Nodes View. This example shows the last two hours of the ‘clock’ metric of eight nodes. Node ‘f0147’ of the ‘main’ partition has an average below the configured ‘alert’ threshold, and is colored in red.
The nodes view, or systems view, is always called in respect to one specified cluster. It displays the current state of all nodes in that cluster in respect to one selected metric, rendered in form of metric plots, and independent of job meta data, i.e. without consideration for job start and end timestamps.
Please note: The X-Axis of all plots rendered in this view are relative to the latest data point received from the collector daemon, and thus, the time displayed reaches backward as indicated by negative X-axis labels.
Selection Bar
Selections regarding the display, and update, of the plots rendered in the node table can be performed here:
(Periodic) Reload: Force reload of fresh data from the backend or set a periodic reload in specified intervals
30 Seconds, 60 Seconds, 120 Seconds, 5 Minutes
Displayed Time: Select the timeframe to be rendered in the node table
Custom: Select timestamp from and to in which the data should be fetched. It is possible to select date and time.
Metric:: Select the metric to be fetched for all nodes. If no data can be fetched, messages are displayed per node.
Find Node:: Filter the node table by hostname. Partial queries are possible.
Node Table
Nodes (hosts) are ordered alphanumerically in this table, rendering the selected metric in the selected timeframe.
Each heading links to the singular node view of the respective host.
5.9 - Node
All Metrics of One Selected Node
Node View. This example shows the last twelve hours of all metrics of the specified node ‘a0122’. The metric ‘acc_mem_used’ has an average below the configured ‘alert’ threshold, and is colored in red.
The node view is always called in respect to one specified cluster and one specified node (host). It displays the current state of all metrics for that node, rendered in form of metric plots, and independent of job meta data, i.e. without consideration for job start and end timestamps.
Please note: The X-Axis of all plots rendered in this view are relative to the latest data point received from the collector daemon, and thus, the time displayed reaches backward as indicated by negative X-axis labels.
Selection Bar
Information and selections regarding the data of the plots rendered in the node table can be performed here:
Name: The hostname of the inspected node
Concurrent Jobs: Number of jobs currently allocated to this node. Exclusively used nodes will always display 1 if a job is running at the moment, or 0 if not.
A link is provided which leads to the joblist with preset filter fetching only currently allocated jobs.
(Periodic) Reload: Force reload of fresh data from the backend or set a periodic reload in specified intervals
30 Seconds, 60 Seconds, 120 Seconds, 5 Minutes
Displayed Time: Select the timeframe to be rendered in the node table
Custom: Select timestamp from and to in which the data should be fetched. It is possible to select date and time.
Metrics are ordered alphanumerically in this table, rendering each metric in the selected timeframe.
5.10 - Analysis
Metric Data Analysis View
Analysis View General Information Section. Two filters are active, the pie chart displays top user node hour utilization fractions.
The analysis view is always called in respect to one specified cluster. It collects and renders data based on the jobs returned by the active filters, which can be specified to a high detail, allowing analysis of specific aspects.
Please note: By default, the requested data is limited by a preset start time filter to jobs started within the last 6 hours. In addition, some results are not calculated when the returned amount of jobs exceeds 500 entries, in order to save on rendering time.
General Information
The general information section of the analysis view is always rendered and consists of the following elements
Totals
Total counts of collected data based on the returned jobs matching the requested filters:
Total Jobs
Total Short Jobs (By default defined as jobs shorter than 5 minutes)
Total Walltime
Total Node Hours
Total Core Hours
Total Accelerator Hours
Top Users and Projects
The ten most active users or projects are rendered in a combination of pie chart and tabular legend with values displayed. By default, the top ten users with the most jobs matching the selected filters will be shown.
Hovering over one of the pie chart fractions will display a legend featuring the identifier and value of the selected parameter.
The selection can be changed directly in the headers of the pie chart and the table, and can be changed to
The selection is saved for each user and cluster, and will select the last chosen types of list as default the next time this view is opened.
“User Names” and “Project Codes” are rendered as links, leading to user job lists or project job lists with preset filters for cluster and entity ID.
Please note: The legend colors are fixed by their position, and not by their respective identifier. This means that the orange fraction will always be the largest fraction, even if the contributing user or project changes.
Heatmap Roofline
A roofline plot representing the utilization of available resources as the relation between computation and memory for all jobs matching the filters. In order to represent the data in a meaningful way, the time information of the raw data is abstracted and represented as a heat map, with increasingly red sections of the roofline plot being the most populated regions of utilization.
Histograms
Two histograms depicting the duration and number of allocated cores distributions for the returned jobs matching the filters.
Selectable Data Representations
The second half of the analysis view consists of areas reserved for rendering user-selected data representations.
Select Plots for Histograms: Opens a selector listing all configured metrics of the respective cluster. One or more metrics can be selected, and the data returned will be rendered as average distributions normalized by node hours (core hours, accelerator hours; depending on the metric).
Select Plots in Scatter Plots: Opens a selector which allows selection of user chosen combinations of configured metrics for the respective cluster. Selected duplets will be rendered as scatter bubble plots for each selected pair of metrics.
Three pairs of metrics are already selected for scatter representation. Remove a selected pair by pressing the ‘x’ button, add a new pair by selecting two metric from the dropdown menu, and confirming by pressing ‘Add Plot’.
Average Distribution Histograms
Three selected metrics are represented as normalized, average distributions based on returned jobs.
These histograms show the distribution of the normalized averages of all jobs matching the filters, split into 50 bins for high detail.
Normalization is achieved by weighting the selected metric data job averages by node hours (default), or by either accelerator hours (for native accelerator scope metrics) or core hours (for native core scope metrics).
Please note: Metrics, which are disabled for specific subclusters as per metric configuration file, will be returned as null values if data is requested for the whole cluster, which can affect the rendered distributions. Select a specific partition using the cluster filter to evade this artifact.
User Defined Scatterplots
Three user defined scatter plots.
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.
5.11 - Status
Hardware Usage Information
The status view is always called in respect to one specified cluster. It displays the current state of utilization of the respective clusters resources, as well as user and project top lists and distribution histograms of the allocated resources per job.
Please note: By default, the periodic reload function is set to 2 Minutes.
Utilization Information
For each subluster, utilization is displayed in two parts rendered in one row.
Gauges
Simple gauge representation of the current utilization of available resources
Field
Description
Note
Allocated Nodes
Number of nodes currently allocated in respect to maximum available
-
Flop Rate (Any)
Currently achieved flop rate in respect to theoretical maximum
Floprate calculated as f_any = (f_double x 2) + f_single
MemBW Rate
Currently achieved memory bandwidth in respect to technical maximum
-
Roofline
A roofline plot representing the utilization of available resources as the relation between computation and memory for each currently allocated, running job at the time of the latest data retrieval. Therefore, no time information is represented (all dots in blue, representing one job each).
Top Users and Projects
The ten most active users or projects are rendered in a combination of pie chart and tabular legend. By default, the top ten users or projects with the most allocated, running jobs are listed.
The selection can be changed directly in the tables header at Number of ..., and can be changed to
Jobs (Default)
Nodes
Cores
Accelerators
The selection is saved for each user and cluster, and will select the last chosen type of list as default the next time this view is rendered.
Hovering over one of the pie chart fractions will display a legend featuring the identifier and value of the selected parameter.
“User Names” and “Project Codes” are rendered as links, leading to user job lists or project job lists with preset filters for cluster, entity ID, and state == running.
Please note: The legend colors are fixed by their position, and not by their respective identifier. This means that the orange fraction will always be the largest fraction, even if the contributing user or project changes.
Statistic Histograms
Several histrograms depicting the utilization of the clusters resources, based on all currently running jobs are rendered here:
