Example Workload Data Import Format

WorkloadWisdom does not require the imported Workload Data (.csv) from storage arrays, or other devices that contain storage workload information, to be in any specific format. The engine is designed to be completely generic.WorkloadWisdom requires a specific set of metrics to perform its analysis, and provides Workload Analysis Policies to map the imported data to the metrics required by WorkloadWisdom to perform analysis. Therefore, WorkloadWisdom requires the imported .csv to contain data, identified by the column label, required by an Analysis Policy.

An Analysis Policy is essentially a “conversion” template that converts the imported data into the specific set of metrics that WorkloadWisdom requires to perform analysis. The metrics required to perform analysis include, but not limited to, read/write percentages, read/write IO sizes, and IOPS.

2019-11-15_16-13-05.png

Analysis Policies are designed to be extensible and customizable. Therefore, you can either edit an Analysis Policy so that it can interpret the Input Data from the .csv, or you can edit the import .csv column labels to so that it can be interpreted by an available Analysis Policy.

As different storage arrays keep track of workload data differently, and produce .csv in different structures, the Analysis Policy also provides mechanisms to perform calculations on the data in the imported .csv to derive the metrics WorkloadWisdom requires to perform analysis on the .csv. For example, if a storage array provides data on Throughput and IOPS, but does not provide data on average Block Size, then the Analysis Policy can derive the average Block Size by dividing Throughput by IOPS.

As an example, here is a truncated example of an imported .csv from a storage array:

2019-11-15_16-15-22.png

And here is a truncated example of an Analysis Policy that is defined to interpret the imported .csv:

2019-11-15_16-16-16.png

For some of the metrics that are not directly available from the imported .csv such as Average Write IO Size, the following Calculation Rules can be applied to derive the Average Write IO Size:

2019-11-15_16-18-02.png

In this example, the Calculated Metric “Average Write IO Size” is derived by the formula (Write Throughput/Write IOPs) * 1024, where “Write Throughput” is interpreted from the data from the column labeled “Write Xfer /sec” in the imported .csv, and “Write IOPS” is interpreted from the data from the column labeled “Write I/O /sec”.

The Workload Data Importer is extremely flexible, and the fidelity of the analyzed workload depends on the Analysis Policy you define, and most importantly, the amount of data that is available in the imported .csv file.