This page archives the workload logs and problem descriptions presented at JSSPP workshops.


Kubernetes Workload from CERIT-SC system

This workload comes from the 2022 paper "Using Kubernetes in Academic Environment: Problems and Approaches" by Viktoria Spišaková, Dalibor Klusáček and Lukáš Hejtmánek.
It contains real life-based descriptions of 292,238 Pods executed in CERIT-SC infrastructure during July 2021 - June 2022 period (CERIT-SC Kubernetes Platform Documentation). Detailed description of the workload can be found in the aforementioned paper.
The workload is stored in SWF-like format with the description available in the workload header.
Workload format used in this log is following (one Pod per line, separated by whitespaces):
Pod_Name 
Pod_UUID 
Created(epoch)      (Note: "-1" denotes missing value)
Deleted(epoch)      (Note: "-1" denotes missing value)
Start(epoch)        (Note: "-1" denotes missing value)
End(epoch)          (Note: "-1" denotes missing value)
CPU_Request         (Note: "," is used as decimal point)
CPU_Limit           (Note: "," is used as decimal point)
CPU_Usage_Avg       (Note: "," is used as decimal point)
CPU_Usage_Min       (Note: "," is used as decimal point)
CPU_Usage_Max       (Note: "," is used as decimal point)
Memory_Request(B)   (Note: Memory in Bytes, "," is used as decimal point)
Memory_Limit(B)     (Note: Memory in Bytes, "," is used as decimal point) 
Memory_Usage_Avg(B) (Note: Memory in Bytes, "," is used as decimal point) 
Memory_Usage_Min(B) (Note: Memory in Bytes, "," is used as decimal point) 
Memory_Usage_Max(B) (Note: Memory in Bytes, "," is used as decimal point) 
GPU_Request 
Namespace    
    

Usage and Acknowledgments

The Kubernetes Workload from CERIT-SC system was graciously provided by the project "e-Infrastruktura CZ" (e-INFRA LM2018140) provided within the program Projects of Large Research, Development and Innovations Infrastructures. If you use this log in your work, please use a similar acknowledgment. To acknowledge authors' work please consider citing the paper that introduced this log:
Viktoria Spišaková, Dalibor Klusáček and Lukáš Hejtmánek, "Using Kubernetes in Academic Environment: Problems and Approaches". In Job Scheduling Strategies for Parallel Processing, June 2022.

JSSPP 2021 - the Workshop on Jobs Scheduling Strategies for Parallel Processing. Contact email: jssppw@gmail.com