All Products
Search

This Product

    Elastic High Performance Computing:View a cluster report

    Document Center

    Elastic High Performance Computing:View a cluster report

    Last Updated:Jan 19, 2024

    A cluster report shows the core hours of a cluster within a specified time range. You can view users, queues, and job list during the core hours. You can use the cluster report to monitor the status of the cluster, and adjust the cluster configurations and jobs at the earliest opportunity.

    Prerequisites

    • The cluster is in the Running state.

    • Jobs in the cluster have been running for more than one hour.

    Limits

    The cluster must use a Portable Batch System (PBS) or Deadline scheduler.

    Procedure

    1. Log on to the Elastic High Performance Computing (E-HPC) console.

    2. In the upper-left corner of the top navigation bar, select a region.

    3. In the left-side navigation pane, choose Job and Performance Management > Report.

    4. Select a cluster from the Cluster drop-down list.

    5. View the report of the cluster.

      报表新

      • View the number of nodes in the cluster.

        The Node Count section shows a line chart that may dynamically change together with the number of nodes in each queue of the cluster.

      • View the resource usage of a cluster in a specified period of time.

        The Cluster Resource Usage section includes tiles such as Users Usage and Queues Usage. The following table describes the tiles in the Cluster Resource Usage section.

        Tile

        Description

        Users Usage

        A pie chart displays the core hours of users in the cluster.

        Queues Usage

        A tree chart displays the core hours of queues in the cluster.

        Instances Usage (core hours)

        A tree chart displays the core hours of instances in the cluster.

        If you select a queue in the Queues Usage section, the core hours of instances in the queue are displayed.

        Instance Type Usage (core hours)

        A tree chart displays the core hours of instance types in the cluster.

        If you select a queue in the Queues Usage section, the core hours of instances in the queue are displayed.

        Note

        • You can move the pointer over each chart to view details.

        • The unit of each statistical chart is core hours. Core hours indicate the number of cores multiplied by the duration of a job in hours.

        • By default, if you want to download a report, click Download to download an .xlsx file. You can also choose Download > CSV Download to download a .csv file.