Establishing consumed resource to consumer relationships in computer servers using micro-trend technology

Abstract

A computer-implemented method for diagnosing workload performance problems in computer servers includes measuring resource metrics. The method further includes aggregating resource metrics for each consumed resource, and aggregating resource and non-resource activity metrics for each consumer. The method further includes generating condensed diagnostic data, on a synchronized, regular interval with one or more most significant consumed resource names and corresponding consumed resource metrics. Generating the condensed diagnostic data includes grouping consumers into buckets based on bucket and consumer attributes, aggregating resource and non-resource consumer activity metrics across all consumers in each bucket, and including one or more worst offending consumer names with corresponding resource and non-resource consumer activity metrics in each bucket. The condensed diagnostic data with the most significant consumed resources and bucket contents is recorded. Diagnostic data can be generated in a human consumable form or in a machine consumable form for using machine learning.