User’s Guide: Substantial work has gone into making the XDMoD user interface easy to use. However, given its powerful analytical capabilities, it can nonetheless be challenging for users to fully exploit its capability. To help remedy this, a User’s Guide and FAQ, available through the Help Button on the top right hand side of the XDMoD Portal window have been developed. The user guide provides detailed instructions for utilizing all aspects of XDMoD from obtaining an account to explaining common user interface elements and getting the most out of powerful tools such as the Metric Explorer. Access to the guide is context sensitive providing direct access to the most relevant portions of the guide based on what the user was viewing when they requested the help. For example, if one accesses the user guide while viewing the Metric Explorer tab they will be brought directly to the section of the manual describing that tab. In addition to the user manual, a “quick start” guide is provided directly within XDMoD for several tools including the Metric Explorer, Application Kernel Explorer, Report Generator and Job Viewer tab. As shown in Figure 1-1, when a user views the Metric Explorer tab and has not created a query, visual assistance is provided to guide them in quickly getting started.

Figure 1-1: XDMoD Help. The XDMoD Quick Start Guide for the Metric Explorer Tab

2 Introduction

XD Metrics on Demand (XDMoD) provides metrics pertaining to resource utilization and performance of high performance computing (HPC) resources, and the impact these resources have in terms of scholarship and research. While initially focused on the National Science Foundation (NSF) TeraGrid and follow-on XSEDE (XD) and ACCESS programs, XDMoD has a wide applicability to any HPC system. The goals of XDMoD framework are to

1. Provide the end-user community with a tool to more effectively and efficiently use their allocations and optimize their use of cyber-infrastructure (CI) resources.

2. Provide operational staff with the ability to monitor and tune the performance of hardware , system software, and applications to ensure optimal resource performance.

3. Provide management with a diagnostic tool to facilitate CI planning and analysis as well as monitor resource utilization and performance.

4. Provide metrics such as publications, awards, and citations to help ensure that the resources are effectively enabling research and scholarship.

The framework also provides a computationally lightweight and flexible application kernel auditing system that reflects best-in-class performance kernels to measure overall system performance with respect to existing applications that are being run by users. This allows continuous resource usage analysis and measurement of all aspects of system performance, including: global file-system performance, local processor-memory bandwidth, allocable shared memory, processing speed, and network latency and bandwidth. <XSEDE>Metrics that focus on scientific impact, such as publications and external funding, are also included to help demonstrate the important role such centers play in advancing research and scholarship as well as to help justify the continued investment in these resources.</XSEDE>

2.1 XDMoD User Interface Overview

Here we provide a brief introduction to the XDMoD user interface. Greater detail is provided throughout the manual. The XDMoD user interface, shown in Figure 2-1, is organized into multiple tabs that provide functionality tied to the role of the user.

XDMoD utilizes user roles to restrict access to data and elements of the user interface such as tabs. Supported roles include a public (unauthenticated user), User, Principal Investigator, and Center Director. A detailed description of each role as it applies to data access is as follows.

<XSEDE>In addition, the ACCESS version of XDMoD includes a Campus Champion and Program Officer roles.</XSEDE>

Public Role: With no user account required, the public role provides non-authenticated users with access to overall utilization broken down by center or service provider (if more than one are available), resource, field of science, allocation time, etc.; and the ability to view specific time periods, and export images. Quality of service data via the Application Kernel suite is not publically available, nor is specific user data.

User: Users are able to view all data available to the Public Role as well as their personal utilization information. They are also able to view information regarding their allocations, quality of service data via the Application Kernel Explorer, and generate custom reports.

Principal Investigator (PI): A principal investigator is a user who is listed as a PI on one or more allocation or project. A PI has access to all data available to a user, as well as detailed information for any users included on their allocations or project.

<XSEDE>Campus Champion: The campus champion role is still a work in progress. A typical campus champion will include one or more users on their allocations while assisting them, giving the champion the same access to detailed information about those users that a PI would have. we will be collaboration with the Campus Champion working group to develop other tools to facilitate their work in the future.</XSEDE>

Center Director/Center Staff: The director of a service provider or center will have access to detailed usage information for any user that has run jobs at their center. In addition, they will have access to detailed application kernel results for runs at their center. Directors are also able to delegate access to their center’s data to other users who assist in the operations of their center. Directors may also have access to other information for their center to ensure that the proper information is being consistently reported.

<XSEDE>Program Officer/ACCESS Management: Program Officers and ACCESS management have no restrictions on the information available to them. They may view data across all service providers, including data reporting compliance reports and custom queries (both described below).</XSEDE>

The XDMoD User Interface contains a wealth of information and has been organized into tabs to compartmentalize the data without overwhelming the user. For illustrative purposes, we will focus on the highest level role.<XSEDE> The tabs which are described in greater detail below are: Summary tab, Usage tab, Metric Explorer tab, Allocations tab, App Kernels tab, Report Generator tab, Custom Query tab, Job Viewer tab, and Compliance tab.</XSEDE> <Open>The tabs which are described in greater detail below are: Summary tab, Usage tab, Metric Explorer tab, App Kernels tab, Job Viewer tab, and Report Generator tab </Open>

The Summary tab (Figure 2-1) provides a snapshot overview of selected data with several small summary charts visible that can be expanded to full size charts through a simple mouse click. The default is to show utilization over the previous month, but the user may select from a number of preset date ranges (week, month, quarter, year to date, etc) or choose a custom date range. The user can also customize the summary by adding charts , see the section on the Metric Explorer.<XSEDE>

Figure 2-1: XDMoD Summary Tab. Summary tab contains a series of user configurable summary plots of usage. In this case the summary plots are for all XSEDE in 2012.

</XSEDE>

<Open>

Figure 2-1: XDMoD Summary Tab. Summary tab contains a series of user configurable summary plots of usage.

</Open>

<XSEDE>The Usage tab, shown in Figure 2-2, provides access to an expansive set of resource-wide metrics that are accessible through the tree-structure on the left-hand side of the portal window, including summaries of usage, allocations, accounts, and SUPReMM performance data. Usage metrics provided by XDMoD include: number of jobs, total and average SUs (service units) charged, total and average NUs (normalized units) provided, number of CPUs used, wait time, wall time, minimum, maximum and average job size, average CPU used, average wall time, average wait time and user expansion factor. In addition a suite of SUPReMM performance metrics are available for most resources. These metrics can be broken down by: field of science, gateway, institution, job size, job wall time, NSF directorate, NSF user status, parent science, person, principal investigator, and by resource. Many of the plots are context sensitive and allow users to click on a data element within the plot to further analyze the data. For example, in Figure 2-2, which shows the distribution of total CPU hours by job size in 2012 for all of XSEDE, one can click on any of the columns to obtain a more detailed analysis for the selected job size range. The plot can also be made available to the custom report generator by clicking the box that reads “Available For Report”. It can also be exported in either PNG (portable network graphics), PDF (portable document format) or SVG (scalable vector graphics) format. The data itself can be exported in either CSV (comma separated values) or XML (extensible markup language) format.</XSEDE>

<Open>The Usage tab, shown in Figure 2-2, provides access to an expansive set of resource-wide metrics that are accessible through the tree-structure on the left-hand side of the portal window, including summaries of usage, allocations, accounts, and performance data, as well as allocations and accounts. Usage metrics provided by XDMoD include: number of jobs, total and average CPU-hours charged, number of CPUs used, wait time, wall time, minimum, maximum and average job size, average CPU used, average wall time, average wait time and user expansion factor. If installed, a suite of SUPReMM performance metrics may also be available. These metrics can be broken down by: job size, job wall time, person, principal investigator, by resource, and by organizational hierarchy (if available). Many of the plots are context sensitive and allow users to click on a data element within the plot to further analyze the data. For example, in Figure 2-2, which shows the distribution of total CPU hours by job size in 2012, one can click on any of the columns to obtain a more detailed analysis for the selected job size range. The plot can also be made available to the custom report generator by clicking the box that reads “Available For Report”. It can also be exported in either PNG (portable network graphics), PDF (portable document format) or SVG (scalable vector graphics) format. The data itself can be exported in either CSV (comma separated values) or XML (extensible markup language) format.</Open>

<XSEDE>

Figure 2-2: XDMoD Usage Tab. A Usage plot showing the total CPU hours broken out by job size on all XSEDE resources for 2012.</XSEDE>

<Open>

Figure 2-3: XDMoD Usage Tab. A Usage plot showing the total CPU hours broken out per job on all available resources.</Open>

The Metric Explorer tab provides a powerful tool for organizing and comparing the data from a wide variety of metrics. The Metric Explorer tab, which also provides access to all of the metrics available through the Usage tab, facilitates comparison among the various metrics by allowing multi-axis plots, as shown in Figure 2-3.<XSEDE> Displayed in the window is a plot that shows the number of jobs (left hand axis) and average core count (right hand axis) broken down by NSF Directorate in 2012 for all XSEDE resources. Biological Sciences rival Mathematical and Physical Sciences in total number of jobs but the biological-based jobs tend to use a smaller number of processors on average. As shown in Figure 2-4, the data can be filtered in a variety of ways to display only a desired subset of the data. For example, the plot shown in Figure 2-4 was generated from Figure 2-3 by applying a filter to display only the “NICS-KRAKEN” data. It is interesting to note that on Kraken, Geosciences has surpassed Biological Sciences in terms of the total number of jobs run and has a much higher average core count.</XSEDE> <Open> Displayed in the window is a plot that shows the number of jobs (left hand axis) and average core count (right hand axis) for all available resources. As shown in Figure 2-4, the data can be filtered in a variety of ways to display only a desired subset of data. For example, the plot shown in Figure 2-4 was generated from Figure 2-3 by applying a filter to display only the resource: chemistry. </Open> A notable feature is the ability to open a metric that is provided on the Usage tab directly in the Metric Explorer by clicking on the gear icon on the top right of the plot. This allows one to utilize an existing plot as a starting point and easily customize it, configure additional data series for comparison, and save it for use in a report. Taken in its entirety, the Metric Explorer provides a powerful and flexible interface to facilitate analysis of the data.<XSEDE>

Metric Explorer_Overview.png

Figure 2-4: The XDMoD Metric Explorer Tab. Plot shows the number of jobs running for each NSF Directorate vs average core count for June 2014 on all available resources. Number of jobs running is shown on the primary axis (left-hand axis) and average core count (weighted by each job's total SU’s charged) is shown on the secondary axis (right-hand axis).

Metric Explorer_Overview2.png

Figure 2-5: The XDMoD Metric Explorer Tab. A Metric Explorer generated plot showing Number of Jobs Running for each NSF directorate vs Average core count on NICS-Kraken for 2013. Number of Jobs Running is shown on the primary axis (left-hand axis) and the average core count (weighted by each job's total SU’s charged) is shown on the secondary axis (right-hand axis). Plot was generated from Figure 2-3 by applying a filter that limited the analysis to Kraken data.</XSEDE><Open>

Figure 2-6: The XDMoD Metric Explorer Tab. Plot shows the number of jobs running vs Max core count on all available resources. Number of jobs running is shown on the primary axis (left-hand axis) and Max core count is shown on the secondary axis (right-hand axis).

Figure 2-7: The XDMoD Metric Explorer Tab. A Metric Explorer generated plot showing Number of Jobs Running for vs Max core count on. Number of Jobs Running is shown on the primary axis (left-hand axis) and the max core count is shown on the secondary axis (right-hand axis). Plot was generated from Figure 2-3 by applying a filter that limited the analysis to the resource of chemistry.</Open>

The App Kernels tab contains three sub tabs that provide information on the application kernel performance and quality of service for resources. Through this tab, users can view historical performance for all application kernels run on all <XSEDE>ACCESS</XSEDE>resources. For example, Figure 2-8 shows the wallclock time for Enzo benchmark run on Trestles in January 2014. Note that the plot window contains a description pane that provides information on the application kernel. The data generated by the application kernels is substantial, making the exploration of the data challenging. Therefore, in order to facilitate analysis of the application kernel performance data, we developed the App Kernel Explorer subtab. Here the user can easily select a specific application kernel or suite of application kernels, a specific set of resources, and a range of job sizes for which to view performance. It allows users to directly compare application kernel performance across multiple <XSEDE>ACCESS </XSEDE>resources.

Figure 2-8: App Kernels Tab. Plot showing wallclock time for Enzo benchmark on Trestles for June 2014. The description pane in the plot window provides more detailed information on the application kernel and the resource.

The Report Generator tab (Figure 2-9) gives the user access to the Custom Report Builder that allows a user to create and save custom reports. For example, a user may wish to have specific plots and data summarized in a concise report that they can download for offline viewing. The user can also choose to have custom reports generated at a user specified interval (daily, weekly, quarterly, etc) and automatically sent to them via email at the specified time interval, without the need to log into the portal.

Report Generator_Overview.png

Figure 2-9: XDMoD Custom Report Generator tab. A user can create custom reports by selecting plots from the pool of plots (right hand side) that were generated previously using the XDMoD portal.

The Job Viewer Tab shown in figure 2-10, provides the user with the capability to search for and view specific jobs or jobs that meet specified criteria. The Job Viewer displays job accounting and performance data for any job for which this information is available in the XDMoD data warehouse. There are two basic ways to search for and view jobs using the Job Viewer. If the local job id and resource are known, the quick job lookup function can be used to locate the detailed data for the job. If a job or jobs fitting a given set of criteria are desired the Advanced search function can be used to locate all jobs fitting the specified criteria.

Figure 2-10 Job Viewer Tab

<XSEDE>On occasion, NSF program officers and ACCESS management have made requests for reports or comparisons that do not fit into the existing data realms or plotting tools provided by XDMoD. The Custom Query tab, shown in Figure 2-11 and available only to users with the Program Officer role, has been designed as a mechanism for fulfilling these requests without requiring substantial modification of existing XDMoD internals. Servicing these requests often requires custom back-end programming by the XDMoD team, the incorporation of potentially inconsistent data sources, and substantial data sanitization work. While these queries may be incorporated into XDMoD in the future, the Custom Query tab provides a more efficient way to quickly view the requested data while providing familiar user interface elements such as the date selector, plot export tools, and inclusion of plots into custom reports. Examples of custom queries include research funding supported by ACCESS (directly and indirectly) and NSF research funding supported by ACCESS (overall as well as restricted to MPS). In fact, discoveries during the generation of these queries have resulted in requirements to improve the quality of data collected by the ACCESS allocations process.

Custom Queries_Overview.png

Figure 2-11: Custom Query tab showing number of SUs delivered in 2013 by supporting funding agency

A Compliance tab was added to the XDMoD framework to provide service providers, NSF Program Officers and ACCESS leadership with a tool to quickly assess service provider compliance with ACCESS operational reporting requirements and TAS recommendations. The new compliance tab tracks whether or not each service provider is supplying required reporting metrics and data.</XSEDE>

3 Obtaining an Account

<Open>Open XDMoD provides a public view that allows users without an account to view resource utilization summaries. An account is not required to view public data in Open XDMoD, however, an account is required to access many tabs including the Metric Explorer, Custom Report Generator, Job Viewer and Application Kernels.

Contact the administrator of your Open XDMoD instance for specific details about how to obtain an account.

</Open>

<XSEDE>XDMoD provides a public view that allows users without an account to view resource utilization and performance, allocation, and job level performance summaries. An account is not required to view public data in XDMoD, however, an account is required to access many tabs including the Metric Explorer, Custom Report Generator, Job Viewer, Application Kernels, Compliance, Sci Impact and Custom Queries.</XSEDE>

<XSEDE>

3.1 ACCESS Accounts

You must have an ACCESS account to login to XDMoD. If you do not have an ACCESS account then you can create one following the instructions here: https://identity.access-ci.org/new-user.

</XSEDE>

4 Getting Started

4.1 Logging In

<XSEDE>

You can sign in to XDMoD from the public page by clicking the Sign In link in the upper left-hand corner. You will then be redirected to CILogon where you can provide your ACCESS credentials to log in to XDMoD.

Figure 4-1: ACCESS XDMoD Login

You must have an ACCESS account to be able to log in to XDMoD.</XSEDE>

<Open>

Open XDMoD supports two different authentication mechanisms: local login and Single Sign On. The particular mechanism is configured by the Open XDMoD site administrator. To access the login panel click the “Sign In” link on the top right of the Open XDMoD public page. An example of a login panel for an Open XDMoD instance that authenticates with Single Sign On is shown in Figure 4-1. The specific text and graphics will be different for different authentication providers. An example of the login panel for an Open XDMoD instance configured to use local login is shown in Figure 4-2.

Figure 4-1: Example Login dialog for an Open XDMoD instance configured to use Single Sign On. This example shows an Open XDMoD instance configured to use the authentication provider at the University at Buffalo. Clicking the button with the UB logo opens the official UB login page where users can use their university-wide login credentials to authenticate.

Figure 4-2: Example Login dialog for an Open XDMoD instance configured to use local XDMoD accounts.

</Open>

4.2 Top Toolbar and Tabs

XDMoD content is organized into a set of tabs as shown in Figure 4-2 below and described in section 2. Common functions available to all user roles (such as My Profile, Contact, and Help) are available via buttons on a common toolbar at the upper right region of the page (Figure 4-2).<XSEDE>

Figure 4-2: XDMoD Portal tabs and common toolbar. For description see section 2.0

</XSEDE> <Open>

Figure 4-2: XDMoD Portal tabs and common toolbar. For description see section 2.0 </Open>

5 Common User Interface Elements

Here we describe some common XDMoD user interface elements.

5.1 Duration Selection Toolbar

Figure 5-1: Duration Selection Toolbar

The duration selection toolbar (Figure 5-1) is used for selecting the range of data displayed in a particular data set or chart. It consists of a drop down list containing commonly accessed time frames, as well as a pair of date choosers for configuring the user defined time frames start and end dates, followed by a refresh button for reloading the data and in turn refreshing the screen.

When you interact with the Start and End date fields, the Refresh button will automatically highlight to indicate that it needs to be pressed to apply the new timeframe. Pressing ENTER in either the Start or End date field will accomplish the same thing.

Time Majiger.png

Figure 5-2: Preset time frames menu

The user can choose from a series of commonly selected time frames including 7, 30, and 90 days from the present or 1, 2, 3, 5, and 10 years from the present or a number of calendar years. Alternatively, a user can select their own custom date range for which to display data.

The Aggregation Unit selector is located at the bottom of the Duration preset menu. The aggregation unit determines the bin granularity for the time series data. XDMoD automatically chooses a default value dependent on the date range selected. However, the user can override this default value using the aggregation unit selector. Note that for very long time date durations, greater than 2 years, the day aggregation level is not supported.

Figure 5-3: Custom time frames - interactive date chooser

The user may choose to click on the button, located to the right of the start and end date choosers, to get the interactive date chooser, shown on the left, for selecting a date value interactively via the mouse, keyboard and touch input. In order for the date from the interactive date chooser to become the effective selected date of the date chooser, the user must click a day in the calendar or click the `Today` button. This will hide the interactive date chooser and replace the value in the corresponding date chooser. If the interactive date chooser goes away due to the user clicking another part of the screen, the value of the date chooser will not change.

5.2 Chart Configuration Toolbar

Figure 5-4: Chart Configuration Toolbar

The chart configuration toolbar (Figure 5-4) provides options for a user to customize the appearance of individual charts (and their datasheet view), export the data in a number of output formats, and make a chart available to the Report Generator.

Figure 5-5: Dataset Filter

When the user clicks on the filter button, the chart configuration toolbar is presented with a multi-selector that provides a list of available data sets to the left and a set of selected data sets to the right, for example, Figure 5-5 which displays the filter by resource multi-selector. The user can then select the desired filter choices by clicking on the check boxes. The search box and the paging mechanisms shown in Figure 5-5 are available to assist the user in sorting through filters having large numbers of choices. Note that for the Usage tab that the user must drill down first before the filter becomes active. The manual sections on the Usage tab and the Metric Explorer give more details on the use of the filters.

Figure 5-6: Display menu.

When the user clicks on the Display button in the Usage tab, they are presented with a menu for customizing the display of the current chart or data. Options include:

Timeseries: When this option is selected, it causes the underlying data to use time as an additional dimension to group the results. Otherwise, the values shown on the chart will be the overall value for the chosen statistic over the entire selected duration.
Legend: A legend will be included in the chart image containing detailed information about each data point. Note: this is only available in Timeseries or Pie chart mode.
Log Scale: When selected, the chart will use log scale for its main data axis.
Datasheet: The view is changed to a spreadsheet showing the underlying data of the chart.
Charts - The various types of charts include:

Bar - Vertical: The chart generated will be displayed as a series of bars with each data point represented by a vertical bar. All bars will be the same color.
Bar - Horizontal: The chart image generated will be a bar chart with each data point represented by a uniquely colored horizontal bar. This option is not available for timeseries data.
Line: Displays each data series as a line.
Area: Displays each data series as a filled area each of which has a unique color.
Pie: Displays the data as a pie chart where each data point has a unique color. This option is not available for timeseries data.

Combine Modes - How multiple data series will be aligned next to each other in the chart (applies only to timeseries charts where multiple data series are represented) .

Side - Position the bars or areas representing different data series next to each other.
Stack - Different data series will be stacked on top of each other.
Percentage - Different data series will be stacked on top of each other and occupy the whole range of the y-axis to indicate the percentage of total that each data series represents.

Reset - Restores the settings for the chart to its default configuration.
Persist - The settings applied through the Display menu will persist across any other charts you view.

Figure 5-7: Export menu.

Allows the user to download a chart image in a number of formats or to export the underlying data. When the user presses the Export button they will be presented with a list of possible export formats, which include:

CSV - Comma Separated Values: Export the raw data in CSV format.
XML - Export the raw data in XML format (Appendix I)
PNG - Portable Network Graphics: Export the chart as a PNG file.
SVG - Scalable Vector Graphics: Export the chart as a lightweight vector file suitable for printing.
PDF - Portable Document Format: Export the chart as a PDF file suitable for embedding in a Word or LaTeX document.

The image export options in the Export menu provide the ability to choose the size of the file, the font size and whether to display the chart title in the exported image. The PNG and SVG options have settings for small, medium, large and poster size images and a ‘Custom’ setting that allows fine grained control over the image size in pixels. The PDF option allows the user to specify the width and height of the PDF in inches and the font size in points.

Figure 5-8: "Available For Report" check box. Selecting the Available for Report check box will cause the chart to be added to the list of available charts for the Report Generator.

Note that the chart will retain the duration and display customizations made prior to checking the box.

5.3 Chart Selection Tree

Jobs and other things.png

Figure 5-9: Chart Selection Tree. The chart selection tree is displayed in the Usage Tab. The tree nodes are grouped by Realm (e.g., Jobs, Allocations, SUPReMM, etc.) and there are three levels of data (nodes).

Dimension: These are the first level of nodes in the tree and are defined based on the inherent grouping of the data, e.g. by Resource, by Provider, etc.. When selected, the chart view will update and display the thumbnails or data sheets for all of the facts available for the selected dimension, e.g. Number of Jobs, Total SU charged, etc..
Fact: Fact nodes are children of the dimension nodes and when selected will load the chart or datasheet associated with the selected fact.
Drilldown: Drilldown nodes are children of fact nodes and are displayed when a user clicks on a chart data series (e.g., bar, line, or pie slice) to drill down to more detailed information about that series.

Selection of a node in the tree can be accomplished by left-clicking the node. A triangular icon to the left of the tree node will point to the right when the node is collapsed and will point to the bottom right and have a black fill when expanded. Double clicking a node will select and expand it. Selected tree nodes are indicated by a light blue background.

Collapse All Button : This will collapse all of the expanded nodes in the tree.

Collapse Selector Tree Button : This will collapse the Usage tab Chart Selection Tree to the left so that it is only visible as a thin vertical bar to the left of the screen providing more screen area for the display of the selected chart or data sheet. Clicking on the button will show the Selector Tree again.

5.4 Chart Viewer

Figure 5-10: Chart Viewer

The chart viewer is shown in Figure 5-10 and provides an area where the user can view and customize metric data as well as export the data or make the chart available for inclusion in a custom report. At the top of the Chart Viewer is a trail of breadcrumbs that shows the origin of the chart. The chart shown in Figure 5-10 is from the <XSEDE>ACCESS</XSEDE>view of the Usage tab. The Jobs by Resource category is expanded, followed by selection of the XD SUs Charged: Per Job metric.

Drilldowns: Most of the charts displayed in XDMoD have a drill-down capability, which will allow users to click on a data series (bar, line, pie slice, etc.) and acquire more detailed information about the relevant selection. This is accomplished by hovering the mouse over a particular data series in a chart and clicking on it, causing a new drilldown node to be displayed in the Chart Selection Tree and the new chart to be displayed. When drilldowns are available, the cursor will change from an arrow to a hand. Whenever a drilldown is not possible the user will be notified via a tooltip.

For example, if the second horizontal bar in Figure 5-10 is clicked on (NICS KRAKEN), followed by the selection of Field of Science from the menu that appears, the chart shown in Figure 5-10a will appear. This new chart will take into account all fields of science which have contributed to charging XD SUs to resource NICS KRAKEN (respective of the timeframe selected). Note that the breadcrumb trail reflects the origin of the chart.

Figure 5-10a: Example of a drilldown chart

5.4.1 Chart Viewer Tools

Figure 5-11: Chart Viewer Tools (Thumbnail Views)

Located on the top right of the Usage tab chart viewer when a dimension is selected, from left to right, this toolbar consists of the following buttons:

Restoring the thumbnails to their original dimensions
Reducing the chart size
Increasing the chart size

6 Summary Tab

<XSEDE>

Figure 6-1: Summary Tab </XSEDE><Open>

Figure 6-1: Summary Tab </Open>

The Summary tab (Figure 6-1) consists of a duration selector toolbar, a summary information bar, followed by a select set of charts representative of the usage. The refresh button can be used to reload the page.

The Summary tab provides a dashboard that presents summary statistics and selected charts that are useful to the role of the current user. Pertinent information such as the number of jobs run, average CPU time per job, and the average number of processors per job are displayed as well as selected charts that provide an overview of selected available data. <XSEDE>For ACCESS this includes the operation of ACCESS as a whole, a particular Resource Provider, or the state of jobs run by the current user. </XSEDE> <Open>For Open XDMoD users this includes information on the system as a whole, on various sub-clusters and information specific to the current user.</Open>

To access a more detailed and configurable version of each chart in the Summary tab, click on the gear icon to the right of the chart title (see Figure 6-2 below).

Consult the Quick Filters drop-down menu in the upper-left corner to see summary content tailored to specific roles (Figure 6-1).

<XSEDE>Based on the user's role in the XDMoD, the Summary page may show your jobs (for user role), those of your group (for PI role), those of your resource (for center director role) or ACCESS as a whole (for program manager role). </XSEDE>

<Open>Based on the user's role, the Summary page may show your jobs (for user role), those of your group (for PI role) or those of your entire center (for center director role).</Open>

Figure 6-2: Summary Portlet Tools. From left to right, this toolbar provides a button for collapsing the portlet, a button to configure the chart, and a button that when hovered over will present a tooltip to describe the data in the chart.

7 Dashboard Tab

<Open>The dashboard tab is an optional replacement for the summary tab. The dashboard must be enabled by the XDMoD system administrator and is only available for logged in users.</Open><XSEDE>The dashboard tab is the first tab displayed to logged in users.</XSEDE> It displays various information in separate display windows called components. The information displayed in the dashboard varies according to the assigned role of each user account. Table 7-1 lists the default settings for each role.

<Open>

Table 7-1: List of dashboard components by user role. Some of the components are only available if the (optional) XDMoD module is installed.

Role

Components Displayed

XDMoD module

Center Director

Center summary

Saved charts and reports

Center Report Card

Application Kernels

Center Staff

Center summary

Saved charts and reports

Job Efficiency Report

Recent jobs

Center Report Card

SUPReMM

Application Kernels

Principal Investigator

Recent jobs

Job Efficiency Report

Summary Charts

SUPReMM

User

Recent jobs

Job Efficiency Report

Summary Charts

SUPReMM

</Open>

<XSEDE>

Table 7-1: List of dashboard components by user role.

Role	Components Displayed
Program Officer	Center Summary (all Centers) Saved charts and reports Center Report Card (all Centers)
Center Director	Center summary Saved charts and reports Center Report Card
Center Staff / Campus Champion	Center summary Saved charts and reports Job Efficiency Report Recent jobs Center Report Card
Principal Investigator	Recent jobs Job Efficiency Report Summary Charts
User	Recent jobs Job Efficiency Report Summary Charts

</XSEDE>The various dashboard components are described below.

7.1 Dashboard Components Overview

There are two categories of dashboard components: full-width components and half-width components. Full width components are in a fixed location at the top of the dashboard tab and the half-width components are arranged in columns. All half-width components have a title bar such as the example shown in Figure 7-1. The title bar includes the name of the component and, for components that show data limited by time. show the date range of the data. Clicking the question mark icon on the right of the title bar will show a help window that explains how to use the component.

Figure 7-1: Example title bar of a dashboard component. Typically the title includes information about the date range of the data. The question mark button on the top right is used to open a help window. Some components also have additional icons for component-specific features.

The layout of the half-width dashboard components can be customized by dragging the title bar of a component (Figure 7-2). The layout settings are saved automatically and persist between logins. The layout can be reset to default using the “Reset to default” button in the Settings tab of the “My Profile” dialog (Figure 7-3). The My Profile dialog is accessed via the “My Profile” button on the top left of the XDMoD portal. Full-width dashboard components cannot be moved.

Figure 7-2: Example of rearranging the layout of half-width dashboard components. A component can be moved by selecting the title bar and dragging into the new position.

Figure 7-3: The dashboard layout can be reset to the default value using the button available in the Settings tab of the Profile dialog.

7.2 Chart Component

The Chart Component shows charts from the Metric Explorer. An example of the chart component is shown in Figure 7-4. The time range of the chart is shown in the title bar. The wheel icon on the top right of the component will open the chart in the Metric Explorer.

Figure 7-4: Example of a chart component. The time range of the chart is shown in the title bar. The wheel icon on the top right will open the chart in the Metric Explorer.

The default chart configuration settings are controlled by the <Open>Open</Open> XDMoD system administrator. Extra charts can be added to the dashboard via the Metric Explorer. Charts are added via the “Show in Summary tab” checkbox in the Metric Explorer basic chart options (see Section 9.2 for more information).

It is also possible to edit the default charts via the Metric Explorer. Click the wheel icon on the top right of the chart component to open the chart in the Metric Explorer. You can then edit the chart in the Metric Explorer and save the chart without changing the chart name field or deselecting the “Show in Summary tab” checkbox. To reset a system chart to the default just delete it from the list of save charts in the Metric Explorer.

7.3 Saved Charts and Reports Component

Figure 7-5 shows the saved charts and reports component. This component lists a user’s charts that were saved in the Metric Explorer and their reports from the Report Generator. The list can be sorted by the name, type (chart or report), and last modification date. By default, the list is sorted by the last modification date in descending order. The user can filter the list by name by using the search box.

Figure 7-5: Shows the saved charts and reports components.

7.4 Center Summary Component

Figure 7-6 shows the center summary component. This component displays the thumbnails of charts from the center summary report that is tailored based on user role. Clicking on a thumbnail opens a modal containing an interactive version of the chart. The user can open the chart in Metric Explorer to modify it. Note that charts modified in Metric Explorer have to be saved and added to the center summary report in order to be displayed as a thumbnail in the center summary component. The user can control the time period of the charts by using the time range menu. The user can also download the charts as a PDF by clicking the Download Report button.

Figure 7-6: The center summary report shows thumbnails of charts from the center summary report that is tailored based on user role.

7.5 Center Report Card

The center report card component is provided by the optional XDMoD AppKernels module. The component shows a summary of the results of recent application kernel jobs. Figure 7-7 shows an annotated example of the center report card.

Figure 7-7: An annotated example of the Center Report Card component that is available in the optional AppKernels module.

7.6 Jobs Component

The Jobs component displays information about recent HPC jobs. An annotated example is shown in Figure 7-8. The job information is based on the Job Performance (SUPReMM) realm if the Job Performance module is installed. If the Job Performance module is not installed then the data are obtained from the Jobs realm and the component will display ‘N/A’ in the CPU column indicating that the cpu usage is not available. The information displayed in the Jobs component is restricted by XDMoD’s role based access controls. A summary of the data available is shown in Table 7-2 below. The “Filter by Person” widget is not displayed for the user role since it is superfluous.

Figure 7-8: Annotated example of the Jobs component. The User role does not have permission to list other users jobs and does not have the “Filter by Person” widget. The Job overall CPU usage information is only available if the optional Job Performance (SUPReMM) XDMoD module is installed.

<Open>

Table 7-2: Summary of the role based access control restrictions for data shown in the job component.

XDMoD account role	Information available
User	HPC jobs that were run by the user.
Principal Investigator	HPC jobs that were run by the user and HPC jobs that were run on the PIs projects.
Center Staff	All HPC job data.
Center Director	All HPC job data.

</Open>

<XSEDE>

Table 7-2: Summary of the role based access control restrictions for data shown in the job component.

XDMoD account role	Information available
User	ACCESS HPC jobs that were run by the user.
Principal Investigator	ACCESS HPC jobs that were run by the user and HPC jobs that were run on the PIs projects.
Center Staff	All HPC job data for the Center and all ACCESS jobs run by the user.
Center Director	All HPC job data for the Center and all ACCESS jobs run by the user.
Campus Champion	All ACCESS HPC job data for users at the same Institution and all ACCESS HPC jobs run by the user.
Program Officer	All data

</XSEDE>

7.7 Job Efficiency Component

The Job Efficiency component is only available if the Job Performance module is installed. The Job efficiency in XDMoD is defined based on a comparison of the resources (CPU, Memory, etc.) requested to those used by an HPC job. The information in the Job Efficiency component is subject to the same role-based access controls as the Jobs component as listed in Table 7-2. An annotated example of the component view for Center Staff and Center Director roles is shown in Figure 7-9. The Principal Investigator role does not have a toolbar that switches the data grouping between user and PI. The User role example is shown in Figure 7-10.

Figure 7-9: Annotated example of the Job Efficiency component. The total number of jobs and core hours are shown broken down by efficiency categorization. Click on a row in the table to open a window that lists the jobs that were classified as inefficient.

Figure 7-10: Annotated example of the Job Efficiency component for XDMoD accounts with User role. The total number of jobs and core hours are shown broken down by efficiency categorization. Click on the bar chart to show the information about the jobs that are summarized.

<XSEDE>

7.8 Allocations Component

The Allocations Component shows a summary of allocation information. An example of the Allocations Component is shown in Figure 7-11 below. Clicking on the component will load the Allocations Tab

Figure 7-11: Allocations Component

</XSEDE>

8 Usage Tab

Figure 8-1: Usage Tab

The Usage tab (Figure 8-1) provides a convenient way to browse XDMoD’s realms. It consists of a chart selection tree on the left, and a chart viewer to the right of the page. You can interact with the chart selection tree to explore the realms and view individual metric charts.

Figure 8-2: Usage Tab Metric

To view a metric in the Usage tab (Figure 8-2), expand the selection tree and select an item. The CPU Hours Per Job metric from the Jobs realm is shown. You can use the Duration and Chart Configuration controls to customize the chart (Refer to section “Common User Interface Elements”). For example, you can:

Change the data duration
Change the plot’s display

Note that any selection in the Duration control applies to all charts in the Usage tab.

Figure 8-3: Usage Tab Drilldown

You can drill down on a metric in the Usage tab (Figure 8-3) by left-clicking on the plotted data and selecting a dimension. Drilldown of CPU Hours Per Job by Resource is shown. To further customize the plot, you can use the configuration controls, or export the plot to Metric Explorer by clicking the Gear icon at upper right of the plot window.

9 Metric Explorer

The Metric Explorer allows you to create complex plots containing multiple metrics. It has many point-and-click features so you can easily add and filter plotted data and customize plot appearance.

Figure 9-1: Metric Explorer

The Quick Filter drop-down menu in the top toolbar allows you to rapidly focus the information source used by the Metric Explorer. Based on the quick filter selected, the values that are displayed will vary. For example, if you are a PI, selecting the PI quick filter provides access to the information from all of your students’ jobs; however, if you select User, you see only the information from jobs that you submitted yourself.

Other features of the top toolbar include:

Duration Selectors: The duration selection toolbar is provided for selection of the desired time frame. To define a custom timeframe, specify a start and end date in the date fields to the right of the Duration drop-down menu.

Export Menu: Allows you to download the currently visible chart in graphical or datasheet form, and in various formats.

Print: Prepares a version of the chart for printing, and automatically presents you with a print dialog.

Available For Report: when checked, the exact chart will be included in the report generator’s list of available charts.

For more information about the top toolbar, refer to the “Common User Interface Elements” section in this document.

The Chart Options region above your chart gives you ultimate flexibility in the amount and type of statistics you want to view at any time. The Chart Options region comprises five sections: Charts, Data, Global Filters, and Options. Any changes you make in each section will be immediately reflected in the chart.

The Chart Viewer is the area where the chart is generated by using the chart settings. The chart viewer also uses a paged view. When not all of the data series fit on one chart, multiple charts will be generated. Buttons are provided above the chart for navigation through the charts, when needed. The maximum number of data series in the chart, or page size, can be configured in the chart limit input box above the chart.

The sections that follow discuss the Chart Options region in more detail.

9.1 Managing Charts

Figure 9-2: Charts tools

The Charts section (Figure 9-2a) allows you to manage chart presets. Chart presets are mappings between all the components involved in the chart (e.g. data series, filters, etc.) and the textual identifier you assign to each query.

Once you click on to create a new chart, you will be presented with the dialog reference in Figure 9-2b. Here, you have the opportunity to name your chart for easy reference.

Similarly, you can click on to remove a selected chart preset.

In earlier versions of XDMoD, charts were automatically saved. However, the current version gives you more control over your charts. You must manually save your charts by clicking on either the Save or the Save As button, see Figure 9-2a. Charts or changes to charts that you do not explicitly save will be lost when you exit XDMoD. An Undo button allows you to cancel the last change, and a Redo button lets you cancel the effect of the last Undo.

To access your saved charts, simply select the preset from the Load Chart list (Figure 9-2c). If you have lots of charts, you can utilize the Search field located in the top left of the Load Chart area to target specific charts.

9.2 Basic Chart Options

The Basic Chart Options button can be found at the top right of the chart viewer (Figure 9-1). It allows you to customize general chart settings, see Figure 9-3.

The Dataset Type parameter gives you the ability to customize the view of the data on the chart. By selecting Aggregate, the chart will display a collection of data series, each grouped by whichever category you decide (as managed in the Data section). By selecting Timeseries, the chart will show data over time. Additionally, you can set a title for the chart.

You are also able to fine-tune the appearance of the chart. You can adjust the location of the legend. In addition, you are able to set the Font Size for all textual elements of the chart (e.g. axis labels, axis values, legend labels, chart title, etc.)

If you wish to feature your chart on the Summary tab (or Dashboard tab) (for convenience purposes), check the Show in the Summary tab checkbox.

Figure 9-3: Chart Options

In the present version of the Metric Explorer, you can easily change plots by simply clicking on the data series in the chart. A dialog box opens (Figure 9-4) allowing a wide range of changes, including adding another metric, drilling downs, and options that alter the display format.

Figure 9-4: In the Metric Explorer Plots can easily be changed directly by clicking on them.

9.3 Managing Data Series

Figure 9-5: Adding additional data to a chart is made easier through the menu on the left-hand-side. Here we show how to add CPU Hours Per Job to an existing plot of NUs charged Per job and Number of jobs Ended (Selecting CPU Hours Per Job is shown in the upper left corner of the window).

Figure 9-6: Adding data to the plot is as simple as clicking on the chart.

Adding another data series to a chart can be accomplished in several ways. Figure 9-5 shows that clicking on a metric in the chart tree brings up a dialog box. This dialog allows you to choose what data will be displayed and how it will be grouped. In addition, clicking in the chart view area will bring up a chart options box (Figure 9-6) that allows you to choose to add a new metric. Clicking on a particular data series also brings up a dialog box that has an option to select a new metric.

An alternative way to introduce data into a chart is to click on the Add Data button as highlighted in Figure 9-7. Doing so will present you with a collection of categories referred to as realms. Click on a realm to reveal all the respective metrics. In Figure 9-7 the allocations realm has been selected showing 6 possible metrics. Clicking on the XD SU’s Allocated metric brings up the Data Series Definition dialog box. The Data Series Definition dialog box allows you to control how the metric is to be represented and displayed on the chart. In addition, filters can be applied to the data series for even more precision. For example, you may be interested in the number of jobs run by a particular user at an institution for a particular time frame. Using filters allows you to acquire this information.

Figure 9-7: Data Series workflow of Metric Explorer

In addition to adding new metrics to a plot, the Metric Explorer also allows the user to drill down for more detailed information on a particular metric. Figure 9-8 shows the dialog box that opens when you click on a data series within the chart viewer. Selecting “Drilldown” will display the data analyzed by the chosen dimension or grouping, as described by Section 5.3 (the Chart Viewer) previously.

Figure 9-8 Changing how the data for a given data series is displayed can now be achieved simply by clicking on the data series to bring up a dialogue box.

The Data section of the Metric Explorer allows you to include one or many metrics on a single chart. As illustrated in Figure 9-9, you are given many options which allow you to customize the look of each data series. By double-clicking on a data entry in the grid below, you will be presented with a dialog which gives you finer control of how the data can be represented.

Data options.png

Figure 9-9: Data section of Metric Explorer

8.4 Managing Filters

Add Filter.png

As mentioned in the previous section, filters allow you to focus on a subset of the data. To apply filters to your data, you can either consult the Local Filters section of the Data Series Definition dialog (see Figure 8-10), or make use of Global Filters (see Figure 8-11).

Local Filters are solely tailored to a single data series, whereas Global Filters are applied to all the data series you have introduced into the Data section of the Metric Explorer.

To create a filter, click on the Add Filter button (as highlighted in Figure 8-11). Doing so will provide you with a list of dimensions (or parameters) you can filter with. Once you have selected a dimension, you will be presented with a dialog allowing you to navigate, search, and select parameter values. Click on OK to apply any selected filters.

Figure 8-10: Filters section of Metric Explorer

Filters in the Metric Explorer are applied as follows: Dimensions are logically and-ed together, and values associated with the same dimension are logically or-ed together.

An example of filter logic is illustrated in Figure 8-11.

Figure 8-11: Understanding filter logic

10 Job Viewer

The Job Viewer Tab displays information about individual HPC jobs and includes a search interface that allows jobs to be selected based on a wide range of filters. An example of the job viewer tab is shown in Figure 10-1. The main components of the job viewer are the search history pane and the main viewer pane. The search history pane uses a tree menu that shows all saved searches as nodes in the tree. The jobs that were selected in each search are listed under their respective search node. The main viewer pane has a tabbed user interface that shows the information for a selected job with one job per tab. The different types of information within a job are shown in sub-tabs.

Note that the information available for a given job depends on the data collection software that is used by the resource provider. <XSEDE>Most of the ACCESS resource providers use tacc_stats software to collect performance information.</XSEDE>

Figure 10-1: Job Viewer Tab

10.1 Searching for jobs

There are two ways to search for jobs. If the job id is known, the quick job lookup function can be used to locate the detailed data for the job. Alternatively, the Advanced search function can be used to find jobs based on one or more search parameters.

To activate the Job Viewer click on the Job Viewer tab, then on the Search button in the upper left corner. This will bring up the Search window (shown in Figure 10-2). The search window has three main components, the Quick Job Lookup form, the Advanced Search form and the Results panel. Use the Quick Job Lookup form to find a known job based on its job id (i.e. the identifier that the job was assigned by the job scheduler). First choose the Resource on which the job ran from the drop-down list. Next enter the desired job number in the Job Number box. Finally click on the Search button in the lower right corner of the form. If there is information for this job in XDMoD then a record will show in the results pane. You may optionally choose a descriptive name for the job search in the Search Name entry box and then click Save Results to add the job to the search history for viewing.

Figure 10-2: Search Window

Alternatively, if you are looking for jobs that satisfy a general set of criteria, you can use the Advanced Search form (see Figure 10-3). You must specify (1) the time frame for the search as well as (2) one or more Filters. The filter field is selected from the drop down list, the value for this field is then selected from the box to its right and then click on the Add button to add the filter to the search. Multiple filters can be added to the search and the same filter field may be added multiple times with different values. You can optionally enter a descriptive name for the search in the Search Name entry box (3).

After the inputs have been completed, click on Search (4). If there are any jobs that fit the given search criteria, a list of jobs will be displayed. You can select specific jobs that you would like to view by checking the box next to the job ID, (5) then click Save Results (6) to add the selected jobs to the search history for viewing.

Figure 10-3: Using the Advanced Search Form in the Search dialog.

10.2 Viewing job data

Job information may only be viewed for jobs that are in the search history. The search history tree on the left hand side of the interface shows the saved searches. An annotated example of a search history tree is shown in Figure 10-4. The tree shows all saved searches, all selected jobs for each search and the list of data available for each job. Selecting a data node for a job will result in the job data loading in the main viewer pane.

Figure 10-4: Job viewer search history tree. The tree shows every saved search (1), all selected jobs for a search (2) and the data available for each job (3)

The different types of data available for a job are listed below:

At-a-glance analytics
Accounting data
Job script
Executable information
Summary metrics
Detailed metrics
Timeseries plots

Note that not all data may be available for all jobs. Availability of data depends on the collection software installed on the HPC resource as well as the hardware capabilities on the compute nodes. The only information that is guaranteed to be present is the Accounting data.

10.2.1 At-a-glance analytics

The at-a-glance analytics are shown at the top of the job tab and are automatically displayed if they are available (there is no data node displayed in the search history for the at-a-glance analytics). There are three plots that show a summary of the values of selected performance metrics of the specific job. The metrics that are displayed here are normalized with values near 1 (displayed in green) indicating a good value and values near 0 (displayed in red) indicating a poor value for the metric. We note that not all jobs should be expected to have good values for all metrics. The default metrics that are displayed are CPU User Balance, Homogeneity, Memory Headroom and CPU User (see Figure 10-5). CPU User Balance indicates how well balanced the usage is between the various cores in the job based on the fraction of time each core spends in CPU user mode. CPU User Balance is defined as

where is the CPU usage for the core with the highest average usage and is the CPU usage for the core with the lowest average usage. A value near 1 is ideal in that all cores are working equally; a value near zero indicates that one or more cores are nearly idle. Homogeneity is a measure of how uniform the L1D cache load rate is over the lifetime of the job. The L1D load rate is a useful metric measuring if the job is accomplishing useful data processing. High values near 1 are good; if the value is low near 0, the job should be investigated to determine if data processing terminated prematurely. CPU User is the ratio of CPU clock ticks spent in the CPU user mode summed over all of the cores divided by the total clock ticks for the job for all of the cores. Values near 1 are ideal indicating that all cores are spending most of their time in CPU user mode. Values near 0 indicate a job where the cores are spending only a small fraction of their time in CPU user mode.

10.2.2 Accounting data

This tab shows the information about the job that was obtained from the resource manager <XSEDE>and the ACCESS allocation service</XSEDE>. This includes timing information such as the start and end time of the job as well as administrative information such as the user that submitted the job and the account that was charged.

10.2.3 Job script

This tab shows the job batch script that was passed to the resource manager when the job was submitted. The script is displayed verbatim.

10.2.4 Executable information

This tab shows information about the processes that were run on the compute nodes during the job. This information includes the names of the various processes and may contain information about the linked libraries, loaded modules and process environment.

10.2.5 Summary metrics

This tab shows a table with the performance metrics collected during the job. These are typically average values over the job. The label for each row has a tooltip that describes the metric. The data are grouped into the following categories:

CPU Statistics: information about the cores on which the job was assigned, such as CPU usage, FLOPs, CPI
File I/O Statistics: information about the data read from and written to block devices and file system mount points.
Memory Statistics: information about the memory usage on the nodes on which the job ran.
Network I/O Statistics: information about the data transmitted and received over the network devices.

10.2.6 Detailed metrics

This tab shows the data generated by the job summarization software. Unlike the summary metrics listed above, this data is not normalized and the format and content is specific to the job summarization software used. Please consult the relevant job summarization software documentation for details about these metrics.

10.2.7 Timeseries plots

The final aspect of the Job Viewer tab is the ability to view timeseries plots of several different metrics. The available plots for a job are listed under the Timeseries tree node in the search history (see Figure 10-6). The metrics that are available depend on the collection software that runs on the compute nodes as well as the hardware on the nodes themselves. A brief description of the metrics follow:

CPU User: The ratio of time spent in user mode to total CPU time for the cores that were assigned to the job.
L1D loads: The ratio of L1D cache loads to reference CPU clock ticks for the cores that were assigned to the job.
Memory bandwidth: The rate of data transferred to DRAM.
Memory Usage: The memory usage reported by the OS for the nodes that were assigned to the job.
Interconnect MPI traffic: The rate of data transferred over the high-speed interconnect
Parallel filesystem traffic: The rate of data read from and written to the parallel filesystem
SIMD instructions: The rate of SIMD instructions (this is correlated to the number of floating point operations).
Process memory: The amount of memory used by the processes that were run by the job
NFS Filesystem traffic: The rate of data read from and written to NFS mounted filesystems.

It is possible to drill down on the timeseries data by clicking on the data series on the chart or by using the search history tree. The degree to which it is possible to drill-down varies according to the metric. For example, the CPU metric shows the compute node-level average values and it is possible to drill down to the per-core values. The memory metric shows the compute node-level average value and it is possible to drill down to the individual NUMA nodes (for supported collection software).

Figure 10-5: Job Viewer Information

Figure 10-6: Chart vs Time

11 App Kernels

Figure 11-1: Application Kernels

The Application Kernels Tab consists of three subsections, each has a specific goal in order to make viewing Application Kernels simple and intuitive. The three sections consist of the Application Kernels Viewer, Application Kernels Explorer and the Reports subsidiary tabs. The section below will describe each of these subsidiary tabs in much greater detail

11.1 App Kernels Viewer

The Application Kernel Viewer selector tree (Figure 11-1) functions similarly to the chart selection tree of the Usage tab. Data is displayed hierarchically where the top level nodes are the names of the available application kernels followed by the resources on which that kernel was run, followed by the metrics that were generated on that resource, followed by the number of processing units used as shown in Figure 11-1. Clicking on the tree nodes will display a set of thumbnails in the chart viewer that reflects the node's location in the hierarchy - the farther down in the hierarchy that a node lies, the more specific the set of data displayed. The available node types are:

App Kernel: Selecting an application kernel name will load all thumbnails associated with that kernel (all metrics for all resources).
Resource: Selecting a resource loads the thumbnails for all the metrics collected for this resource and application kernel.
Metric : Selecting a metric will display the chart with a dataset for each number of processing units.
Processing Unit: Selecting the number of processing units will display data for the specific number of processing units for that metric, resource, and application kernel.

When navigating the App Kernels Viewer subtab, targeting solely a specific number of node configuration will yield a comprehensive plot:

Figure 11-2: Application Kernel Viewer Plot

The following table helps to analyze the plot more effectively:

Change Indicators	An exclamation point icon is shown if and whenever a change occurs to the execution environment of the app kernel (library version, compiler version, etc).
Running Average	Shown as a dashed line on the chart. The running average is the linear average of the last five values.
Control Band	A green band is shown, representing the values of the running average considered "In Control" at any given time. A control region is picked to be the first few points in a data set and updated whenever an execution environment change is detected by the app kernel system. The control band then is calculated by clustering the control region into two sets based on the median and then finding the average of each set. The two averages define the control band.
Control Zones	A red interval is shown on the plot when the control value falls below -0.5, indicating an out of control (worse than expected) running average, and a yellow interval when the control value is greater than 0, indicating a better than control (better than expected) running average. Other running average values are considered "In Control".
Control Plot	Represented as a dotted line. The control is calculated as the distance of the running average to the nearest boundary of the control band, normalized over the range of the control band.
Discrete Controls	Convert the control values from real numbers to discrete values of -1, 0, 1. Values less than zero become -1 and values greater than zero become 1.

11.2 App Kernel Explorer

App kernel explorer_no Color.png

Figure 11-3: App Kernel Explorer

The App Kernel Explorer (Figure 11-3) allows you to conveniently compare performance between two or more resources, provided the selection of processing units and metrics. Any changes in selections made on the left-hand section of the Data Explorer will immediately be reflected in the right-hand section (Data Comparator).

It is important to note that changes made in the Metrics Section affect the availability of options in the Resource Selector.

Selections made in the Processing Units section are considered global in the sense that they are applied to every single metric selected. Any selections (and de-selections) made in Processing Units override those made for any metric. Processing units can be selected by clicking the check boxes.

Alternatively, all possible values for either Metrics, Resources or Processing Units can be toggled on or off using the global selection boxes as shown in Figure 11-3a.

Figure 11-3a: Reset buttons for App Kernel Explorer sections

11.3 Reports tab

The Reports tab (Figure 11-4) is used for sending reports based on a specific Resource and App Kernel. The first section of the Reports tab is for sending reports periodically. The options include daily report, weekly report and monthly report. Each of these time frames contains a pull down menu which gives a set of options indicating under what circumstances a report will be sent. The options include always, on any error, on any major error, on pattern errors or on major pattern errors.

The weekly report and monthly report also have another drop down menu which gives options for day of the week for weekly report (e.g. Monday, Tuesday, etc.) and which day of the month for monthly report (e.g 1st, 2nd, 3rd, etc.). Once all settings have been selected, you can click save settings in order to start sending reports.

There is also an option to send reports covering specific and customizable date ranges via email; this can be found directly below the first section.

Figure 11-4 Reports Subtab

12 Data Export

To manage data export requests, click on the Data Export tab (Figure 12-1).

The Data Export functionality allows you to request batch exports of non-aggregate records from the data warehouse. These requests are limited to a one year duration, but there is no limit to the number of requests. The exported data can be formatted as either CSV or JSON. Submitted requests are typically fulfilled within 24 hours and an email is sent to notify you that your data is ready for download.

The Data Export tab appears as shown below with a form used to create requests (Figure 12-2) on the left and a list of existing requests (Figure 12-3) on the right.

Figure 12-1 Data Export Tab

12.1 Create Data Export Request

To create a new request fill out the form and the left and click the button. When a realm is selected the list of fields that will be exported are displayed below the form. A start date, end date and format must be selected. The maximum duration is one year. The export formats are CSV and JSON. The JSON export is structured as an array of arrays.

Figure 12-2 Data Export Create Request Panel

12.2 Manage Existing Export Requests

After submitting a request it will be added to the list in the "Submitted" state. The request may be deleted before it is fulfilled.

Figure 12-3 Data Export Status Panel

Requests are fulfilled on a set schedule and emails are sent to notify you that your data is ready for download. The email will include a link that can be used to download the file and the file will also be available to download through the web portal. The file is retained for a set amount of time, typically 30 days. The expiration date will be displayed in both the email and the web portal. After this date the file will no longer be available for download, but the request may be resubmitted.

13 Report Generator

To manage reports, click on the Report Generator tab.

The default view of the Report Generator UI is shown below. The left region provides a listing of any reports you have created. The right region displays any charts you have chosen to make available for building a report (see Available for Report check box section).

report Generator.png

Figure 13-1: Reports Overview window

Each report entry present under the Report Generator tab displays the title of the chart, whether it was generated manually or from a template, the delivery schedule, the delivery format and the number of charts. In the Available charts section each chart has its title, the timeframe of interest, and a thumbnail view. The time frame defaults to the one chosen prior to making the chart available for reporting.

If you create a chart by a process that includes at least one filtering step and choose to make that chart available for reporting, information on the filtering and drilldown processes can be viewed in by moving your mouse over the information icon to the left the chart title in the chart entry as shown in Figure 13-2.

Figure 13-2: Viewing additional details for a chart entry

The top toolbar serves as the starting point for managing a report.

Figure 13-3: Report Generator toolbar

New: Creates a new report. A default (and unique) name will be chosen, and no charts will be included.

New Based On: Creates a new report which contains all the charts and settings of an existing report. A default (and unique) name will be chosen and assigned to this report.

Edit: Opens an existing report for editing.

NOTE: Another way to open a report for editing is to double-click on one of the entries in My Reports:

Figure 13-4: Editing a report

Preview: Previews the (selected) report prior to sending it.
Send Now: Builds and sends the (selected) report to the email address associated with the user.
Download: Builds the (selected) report and presents it to the user as a downloadable file.

13.1 Selection Model

All the lists / grids under the Report Generator tab have been designed such that multiple selections can be made for more efficient workflows.

Clicking on one entry, followed by holding shift while clicking another entry results in the selection of both entries along with all the entries that fall in between them:

Figure 13-5: Selecting charts for addition in a report

Clicking on one entry, followed by holding the control key (or command key on a Mac) while clicking another entry results in individual selections being added (appended) to what is currently selected.

Figure 13-6: Another method to select charts for addition in a report

Note: Deselections can be made by clicking on selected items in the grids while holding down the control key (or command key on a Mac).

Whether you choose to create a new report or edit an existing report, you will be directed to the Report Editor:

Figure 13-7: Selecting reports and charts via the Select menus

An alternative way to select reports and charts in the Report Generator is to make use of the Select menus (as highlighted in Figures 13-7a and 13-7b). Using these select menus is especially helpful if you are dealing with a substantial number of reports or charts. The select menus also gives you the ability to invert selections made in the report and chart grids. In other words, when you click on Invert Selection, any items previously selected will become deselected, and vice-versa (see Figure 13-7c).

Figure 13-8: Report editor

General Information for this report is displayed on the left side of the Report Editor. The only required field is the report File Name, which must be unique. When creating a new report (including a new report based on another report), a default unique file name will be generated and assigned to the File Name field.

The Chart Layout section allows you to control how many charts are to appear on a single page.

The Scheduling section allows you to customize the frequency in which reports are to be sent to your email address (associated with your account). Schedule options include Daily, Weekly, Monthly, Quarterly, Semi-annually, and Annually. To disable automatic delivery of reports, set the Schedule option to Once.

Currently available formats for reports are PDF and Word Document.

Figure 13-9: Information to be entered to customize a report

To add charts to a report, simply drag an entry from the list of Available Charts (on the right-hand side) into the Included Charts list. See the section entitled Selection Model for adding multiple charts at once.

The order in which the charts appear in the Included Charts section of the Report Editor dictates the order in which they will appear in the report. Re-ordering of charts in the report can be accomplished by simply dragging the charts into the desired order:

Figure 13-10: Reordering charts in a report

13.2 Changing Chart Timeframes

Should you decide (during the report building process) that you want to change the timeframe of a given chart, you can easily accomplish this task by either clicking on the timeframe or the edit icon to the left of the time frame in the respective chart entry. As a result, you will be presented with a dialog for conveniently updating the timeframe to your liking.

Figure 13-11: Changing the timeframe of a chart entry in the report editor

Note: If you want to edit timeframes for multiple charts in a report, select two or more charts, then click on the Edit Timeframe of Selected Charts button in the top menu. Doing so will bring up the same Edit Chart Timeframe dialog as mentioned above. When you click on Update, each of the charts you had previously selected will update to reflect the new timeframe you specified.

13.3 Previewing a Report

At any time during the report editing process, you may preview the current state of the report by first saving and then pressing the Preview button (previewing reports is also possible from the My Reports view):

Figure 13-12: Previewing a report

13.4 Building, Exporting Reports

To build the report (as a PDF or MS Word document), you can make use of the Send Now and Download options available from any of the following sections: My Reports, Report Editor, and Report Preview. The Download feature will allow you to immediately access or download the resulting document, whereas the Send Now feature will email the constructed report to the address associated with your profile (see the My Profile section).

Figure 13-13: Sending a report with Send Now or Download

<XSEDE>

13.5 Report Templates

Report templates allow you to easily construct a set of reports, complete with charts. This is particularly useful for System Providers, for example, who want to acquire comprehensive information regarding their resources without having to go through the time-consuming task of navigating XDMoD and hand-selecting a series of charts.

At this moment, report template functionality is only available to center-based roles (e.g. Center Directors and Center Staff members).

If no reports have been selected, clicking on New Based On will simply present a menu of the available templates for you to use. If a report has been selected prior to this action, then that report will appear at the top of the list followed by available templates. This gives you the option of either cloning an existing report or deriving a new report from a template. Figure 13-4a illustrates this logic.

If your account is associated with multiple centers, you will be able to select the center from which to derive reports. The template you select will direct you to a sub-menu consisting of the centers associated with your XDMoD account. At this point, simply select the center you want to generate reports for. Figure 13-4b illustrates this.

Figure 13-14: Creating reports from templates

If you were to select Template: SP Quarterly Report, for example, XDMoD will automatically acquire the most informative charts per resource belonging to the center of interest, and create a report for each resource discovered. The Reports Overview window will automatically refresh itself and present you with the reports derived from the template.

Each generated report would be configured for quarterly delivery, and each of the included charts would be based on the previous quarter.

14 Efficiency

The Efficiency Tab displays information about the efficiency of jobs running on the resources at your center. The initial display (Figure 14 -1) shows analytic cards that each have a small description of the analytic and a thumbnail view of a scatter plot showing efficiency regarding that specific analytic. The scatter plots are intended to give you a quick view of which analytics need to be investigated more for poor efficiency.

Figure 14-1: Efficiency Tab. The efficiency tab shows analytic cards when you first navigate to the tab which give efficiency information about users’ jobs at your center.

A larger, interactive view of the scatter plot can be seen by clicking on the analytic that you want to learn more about (Figure 14-2). The scatter plots are described in more detail in section 14.1 - Scatter Plot View.

Figure 14-2: When you click on one of the analytic cards, you will be redirected to the scatter plot view.

Analytics are categorized into two bins - analytics associated with usage and analytics associated with design. Usage analytics compare resources allocated for a job to measured usage for the job. Design analytics determine if jobs are using resources in an efficient manner consistent with their design. Table 14-1 below lists the available analytics for the XDMoD 10.0 release and the associated description for that analytic.

Table 14-1: Analytics available for display in the Efficiency Tab for XDMoD 10.0 Release.

Analytic	Description	Category
CPU Usage	Measures the percentage of time that the CPU cores were idle.	Usage
GPU Usage	Measures the percentage of time that the GPUs were busy.	Usage
Memory Usage	Measures the overall highest memory usage for jobs.	Usage
Homogeneity	Measures how uniform the work rate of the job is.	Usage
Wall Time Accuracy	Measures how well used wall time matches requested wall time.	Design
Short Jobs	Measures the number of jobs that ran for 30 seconds or less.	Design

14.1 Scatter Plot View

This view shows a larger, interactive scatter plot for the analytic selected by clicking on its corresponding analytic card. For example, Figure 14-3 shows the CPU Usage Scatter Plot View.

All scatter plots are initially the same as the thumbnail plot in the previous view, but you have the ability to apply filters, zoom in, and drill down in this view. Each point on each of the scatter plots represents data for the jobs of a particular user with the efficiency statistic plotted on the x-axis and the overall usage plotted on the y-axis. Table 14-2 shows the analytics and their associated efficiency and usage statistics that are plotted in the scatter plots.

Figure 14-3: Scatter Plot View. This view displays a larger scatter plot that allows drill downs and filters to be applied. The view also includes help text to give more context about the analytic and ideas for improving efficiency in regard to this analytic.

Table 14-2: Statistics that are plotted for each of the analytics in the scatter plots.

Analytic	Scatter Plot Statistics
	Efficiency Statistic	Usage Statistic
CPU Usage	Average CPU % Idle: Weighted by Core Hour	CPU Hours: Total
GPU Usage	Average GPU % Active: Weighted by GPU Hour	GPU Hours: Total
Memory Usage	Avg: Max % Memory: Weighted by Core Hour	CPU Hours: Total
Homogeneity	Avg: Homogeneity: Weighted by Node-Hour	CPU Hours: Total
Wall Time Accuracy	Wall Time Accuracy	Wall Time Allocated
Short Jobs	Number of Short Jobs (<30s)	Total Number of Jobs Ended

Points higher on the y-axis represent more usage and points on the left hand side of the plot correspond to a high measured usage. The upper right hand quadrant of each scatter plot represents users with jobs that have a lot of usage on the system and are running inefficiently in regard to that analytic. A tooltip appears (Figure 14-4) when you mouse over a point to show the user name (if you have access), the efficiency statistic value, and the usage statistic value.

Figure 14-4: A tooltip giving information

about the user, their efficiency, and

usage of their jobs appears when you

mouse over a point in the scatter plot.

You can use these to compare efficiency of your jobs against other users’ jobs at the same center. If you have access to the user, you are able to click on their point on the scatter plot to drill down and view more information about that user’s jobs’ efficiency (Figure 14-5). When you drill down, you will be presented with a histogram chart (Figure 14-7) which is described in section 14.2 - Histogram View.

Figure 14-5: Clicking on a point in the scatter plot that you are allowed access to will take you to the histogram view for that user which shows more information about that user’s jobs.

There are slight variations to the scatter plot view you will see depending on the user access that you have. These are described below in sections 14.1.a and 14.1.b. The main differences between the views are the markers used on the scatter plot and the ability to drill down and learn more about a user’s jobs. The markers are shown in Figure 14-6.

Figure 14-6: Different markers used to indicate users

on the scatter plot.

14.1.a Center Staff View

Center staff can view all users at the center that have data to be displayed on the scatter plot. Each user is marked with either a red or blue marker on the scatter plot. A red marker indicates a user that has been flagged as running jobs inefficiently in regard to the analytic that is being shown. A blue marker indicates a normal user. As center staff, you have access to all users and therefore have the ability to view all names in the tooltips and drill down on any user in the scatter plot to learn more about the jobs that they are running.

14.1.b PI or Normal User View

PIs have access to their own point as well as points that represent their users. This is indicated by a black circle around the points that you have access to. Normal users only have access to their own data and therefore can only drill down on their own point.

The data that appears in the scatter plot can be altered by changing duration and applying filters. Applying filters to the scatter plot is described in Section 14.4 and changing duration is described in Section 14.5.

14.2 Histogram View

If you have access to view information about a specific user, you can drill down to the histogram view from the scatter plot view. The histogram view for each analytic gives a more detailed analysis of a specific user’s jobs in relation to the analytic that is being investigated. For example, Figure 14-7 shows the histogram view for the CPU Usage analytic.

Figure 14-7: Histogram view. This view gives a more detailed view of a specific user’s jobs.

If you were to drilldown from the CPU Usage scatter plot on a specific user, you would see their jobs binned by the CPU User value compared to the overall CPU Usage for jobs in that bin. The bins are color coded according to efficiency and the color coding is unique to the analytic that is being displayed. However, in each histogram view red is associated with jobs that were running more inefficiently while green is associated with jobs that were running more efficiently.

The histogram chart can be modified to learn more information about the user’s jobs. You can change the duration of the data included in the histogram by using the duration selector toolbar as described in Section 14.5 and filters can be applied to the chart as described in Section 14.4.

To learn more information about the user’s jobs that were included in each of the bins, you can click on any of the bars in the plot that have data in them. Clicking on them will bring up a window that lists all jobs that were grouped in the category that you are viewing (Figure 14-8).

Figure 14-8: Clicking on a bin in the histogram plot will bring up a list of all jobs that were binned in this category.

14.3 Job List

As shown in Figure 14-8, a job list window will appear when you click on one of the bars from the histogram plot (as described in Section 14.3 - Histogram View). The job list window for each analytic varies slightly concerning the data that is shown in the window.

You can click on a row in the job list table to view that job in the Job Viewer (Figure 14.9). When you click on a job, you will be redirected to the Job Viewer tab with that job showing. This will provide you with more details about the job.

Figure 14-9: Clicking on a row in the job list table will take you to the Job Viewer for that job.

14.4 Filtering Charts

Figure 14-10: Filter Menu. Select filters you want to apply to the chart from this menu and apply these using the “Apply Filters to Chart” button.

In addition to drilling down on the charts to get more information, you can also filter the results that you see on the scatter plot and drill down charts. In both cases, you use the filter menu on the left hand side of the chart to apply filters. There is filtering available for four categories - queue, application, resource, and PI. You can choose filters by either checking the box that corresponds with the filter that you want to apply or by searching the filter in the search box of the category you are interested in and clicking on the filter that you want to apply from the dropdown box.

Once all filters that you want to apply are checked, click on the Apply Filters button in the top of the filter menu to apply those filters to the chart that you are looking at. The chart will reload and filters that have applied will be listed in the subtitle (Figure 14-11).

Figure 14-11: Filters that have applied to the chart will be listed in the subtitle of the chart.

To remove all filters, click on the Remove Filters button at the top of the filter menu and the chart will be reloaded with no filters applied. If you only want to remove a select number of filters from a chart that has filters previously applied, you will need to uncheck the filters in the filter menu and click the Apply Filters button again.

Note: If you change the duration of the plot that you are viewing, filters will remain applied as reflected by the filters listed in the subtitle. To remove filters, use the Remove Filters from Chart button at the top of the filter menu.

14.5 Selecting Duration of Charts

By default all charts show data from the previous 30 days. You can change this duration for any of the views at any time to view data from a different time frame. In each view, there is a duration selection toolbar present in the upper toolbar (Figure 14-12). You can choose a pre-defined timeframe from the duration drop-down menu, or specify a start and end date in the date fields to the right of the drop-down menu to select a custom timeframe.

Figure 14-12: Duration Selection Toolbar. Use this toolbar

to select a timeframe for the chart that you are viewing.

14.6 Navigation in Efficiency Tab

To move forward in the efficiency tab, you click on elements within the current view you are on. For the analytic card view, you click on an analytic card to navigate to the scatter plot view. For the scatter plot view, you click on a point on the chart to move to the drilldown view (this is only true for users that you have access to view their jobs).

Figure 14-13: Navigation Toolbar. Use the navigation toolbar to navigate between views in the efficiency tab. Clicking on any of the enabled buttons will take you back to that view.

To move back to previously viewed plots, you use the navigation buttons in the top toolbar next to the duration toolbar (Figure 14.13). A new navigation button will be enabled as you move through the different chart views and you can click on the corresponding button to go back to a chart view that you were previously on.

14 Compliance Tab

Note: The Compliance tab is currently available to program officers, and will eventually be made available to center directors.

The Compliance tab allows one to quickly determine which service providers are providing information with integrity. The Compliance tab can be thought of as a “report card”, reflecting the level of consistency in which each service provider is contributing information relevant to ACCESS from a “job level” as well as “resource level”.

Compliance tab.png

Figure 14-1: Compliance tab

Under the Compliance tab, requirements are displayed in the left-most column.

Job-Level requirements (Figure 14-2a) represent the attributes which are to be supplied or associated with each job record that gets submitted to the ACCESS allocation service.

Resource-Level requirements (Figure 14-2b) are attributes which comprise the technical specification of the resource.

Requirements in black text are supported by ACCESS. Requirements in gray text are proposed by the TAS team. Due to this fact, any proposed requirements will not currently be provided on behalf of any resource (hence n/p will be present in respective cells of the grid).

If more information is associated with a given requirement it can be found by hovering over the icon to the right of its name.

Figure 14-2: Requirements Listing in the Compliance tab

To determine compliance at a job-level, raw job records from the ACCESS allocation service are analyzed on a daily basis. The first row immediately under the Job Level header reflects this raw job record count.

Job Record count as determined from the XDcDB

For a given resource, raw (un-sanitized) job records pertaining to that resource were collected via the ACCESS allocations service. Of those collected records, it was determined that only a fraction (or subset) of those records consisted of a meaningful value that represented the number of cores charged, SUs charged, etc. This fraction is represented as a percentage in the table cell where the requirement row and the resource column intersect.

Note: It is important to note that a “job record” does not correspond to a single job. Each resource’s definition of a “job” varies.

To determine compliance at a resource-level, the Resource Description Repository (RDR) is analyzed on a daily basis. If values pertaining to requirements are present in the RDR for a given day, then the resource is considered to be in compliance for that day. The percentage for resource-level compliance takes into account the number of days (within the given timeframe) the RDR was consulted, and of those consultations, how many times values existed which represented resource specifications such as operating system, node count, processor type, etc.

To view more details about a particular compliance value, simply click on the cell of interest. As a result, the Description section at the bottom will provide more information.

Figure 14-3: Description associated with a cell in the Compliance grid

Note that the nature of the description changes, depending on whether you click on a cell in the job-level or resource-level category.

14.1 Scheduled Compliance Reports

Provided that you have the necessary privileges to view the Compliance tab, you will also be able to set up periodic delivery of resource compliance status through the Report Generator. In the My Reports section of the Report Generator, click on the New Based On button, then click on the template named Monthly Compliance Report. As a result, a new report will be made available to you, already configured for monthly delivery to the email address associated with your XDMoD account.

Figure 14-4: Creating a compliance report to be delivered on a monthly basis

</XSEDE>

15 My Profile, About, Roadmap, Contact and Help

On the upper right side of the XDMoD page, there are a series of five buttons that allow the user to set his profile, get more information about XDMoD, view the XDMoD Roadmap, contact the XDMoD developers and seek help.

Figure 15-1: My Profile, About, Roadmap, Contact and Help functional buttons

15.1 My Profile Button

My profile allows you to view and update general settings pertaining to your account. To access your profile, click on the My Profile button located in the upper right section of the portal.

Your current role will be displayed in the title bar of the My Profile window. In the figure above, for example, it shows the user is a Program Officer.

The first section in the My Profile window contains User Information such as: First Name, Last Name, and Email Address. All of the aforementioned fields must be specified in order to update your profile.

The last section in My Profile allows you to optionally update your account password. In order to update your password, click the Update radio button and specify the new password twice into the fields that follow.

Figure 15-2: Password change window

<Open>

Also in the My Profile window is the option to choose your Role Delegation by clicking the tab at the top of the window (Figure 15-2a). This tab allows you to choose a specific staff member connected to your account to delegate special privileges.

Figure 15-2a: Role Delegation Menu </Open>

15.2 About Button

Clicking the about button will display a page of information about XDMoD.

15.3 Contact Button

Selecting the contact button will bring up a window that allows the user to send a message to the XDMoD team. The user must fill in his name, email address and his message.

Figure 15-3: Contact window

15.4 Help Menu

Figure 15-4: Help menu

Clicking on the Help menu will provide you with the following options: User Manual, FAQ and YouTube Channel (Figure 15-4). Clicking on User Manual will direct the user to the XDMoD User Manual (the document you are viewing at this very moment). If help is available for the section of XDMoD you are currently visiting, the User Manual will automatically navigate to the respective section when it loads. Clicking on FAQ will take you to a page containing Frequently Asked Questions. Clicking on YouTube Channel takes you to the XDMoD YouTube Channel.

15.5 Roadmap

Clicking on the RoadMap button brings up a screen which displays an information page giving details on how to navigate to the XDMoD development roadmap (Figure 15-5). Click on any feature in this page and you will be taken off of the XDMoD site to the Trello.com site where you will be able to view and interact with the XDMoD roadmap (Figure 15-6). To return to XDMoD, simply close the browser tab/window. If you simply want to view the Roadmap you can select the various Trello cards shown in Figure 15-6 for further details about each roadmap task. You can also “vote” for a feature in the roadmap that you would particularly like to use. To do this Sign Up or Log In to Trello (upper right corner Figure 15-6). Then clicking on any roadmap feature such as X-Y plot capacity, will give you access to the Vote box, as shown in Figure 15-7.

Figure 15-5: Roadmap information page

Figure 15-6: XDMD Roadmap on Trello.com

Figure 15-7: Voting for a feature in the XDMD Roadmap on Trello.com

16 Design Philosophy

The XDMoD portal provides end users with a rich web-based user interface as shown in Figure 2-1. Developed using the Model-View-Controller design pattern, the view is provided via a thin client written entirely in JavaScript and built on the ExtJS user interface toolkit while the Controllers and access to the Model are provided by a set of web-based RESTful services. Information in the portal is organized using a set of tabs that allows related information to be grouped together while providing the user an easy way to navigate the interface and make the most of the available screen real estate. The RESTful services provide access to data stored in the warehouse while maintaining a clear separation between the user interface and the application logic. This also allows 3rd party tools to access the services directly and ingest or present the information as they see fit.

17 Appendix I-XML Document Type Definition

<!DOCTYPE xdmod-xml-dataset [

<!ELEMENT header (title, parameters?, start, end, columns)>

<!ELEMENT rows (row?)>

<!ELEMENT parameters (parameter)>

<!ELEMENT parameter (name, value)>

<!ELEMENT row (cell)>

<!ELEMENT cell (column, value)>

<!ELEMENT title (#PCDATA)>

<!ELEMENT name (#PCDATA)>

<!ELEMENT value (#PCDATA)>

<!ELEMENT column (#PCDATA)>

XDMoD User Manual v10.0 CCR @ UB