English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large-scale cloud data centers have gained popularity due to their highavailability, rapid elasticity, scalability, and low cost. However, currentdata centers continue to have high failure rates due to the lack of properresource utilization and early failure detection. To maximize resourceefficiency and reduce failure rates in large-scale cloud data centers, it iscrucial to understand the workload and failure characteristics. In this paper,we perform a deep analysis of the 2019 Google Cluster Trace Dataset, whichcontains 2.4TiB of workload traces from eight different clusters around theworld. We explore the characteristics of failed and killed jobs in Google'sproduction cloud and attempt to correlate them with key attributes such asresource usage, job priority, scheduling class, job duration, and the number oftask resubmissions. Our analysis reveals several important characteristics offailed jobs that contribute to job failure and hence, could be used fordeveloping an early failure prediction system. Also, we present a novel usageanalysis to identify heterogeneity in jobs and tasks submitted by users. We areable to identify specific users who control more than half of all collectionevents on a single cluster. We contend that these characteristics could beuseful in developing an early job failure prediction system that could beutilized for dynamic rescheduling of the job scheduler and thus improvingresource utilization in large-scale cloud data centers while reducing failurerates.

A Deep Dive into the Google Cluster Workload Traces: Analyzing the Application Failure Characteristics and User Behaviors