Pepperdata Decreases Instance Hours 33% for Big Data Workloads
The Pepperdata 2021 HiBench Benchmark Report demonstrates the effect Pepperdata Capacity Optimizer has when implemented on top of an AWS Custom Auto Scaling Policy. The benchmarking work in this report uses HiBench, an industry-standard big data benchmarking workload, and measures instance hours, CPU utilization, memory utilization, and price/performance.
- Instance hours
- CPU utilization
- Memory utilization
- Price/performance, as defined by the cost to run the workload divided by the time it took to run
Key Findings
This report highlights three areas, demonstrating how Capacity Optimizer can:
Reduce instance duration
Optimize resource utilization
Lower the cost of workloads
Big Data Benchmarking in the Cloud
Benchmarking is the process of running a set of standard tests against some object to produce an assessment of that object’s relative performance. Pepperdata had heard anecdotal reports from customers about the effectiveness of Capacity Optimizer, including comments that their servers would fail without Pepperdata.
From the results of our internal testing, we concluded that using Capacity Optimizer resulted in slightly faster runtimes and significantly lower resource utilization. By conducting this HiBench big data benchmarking test, we established an objective measure of the benefits Capacity Optimizer provides.
Resource Utilization Results
On average, Capacity Optimizer decreased both overall duration by 12% and instance hours by 33%, while increasing both CPU utilization by 27% and memory utilization by 7% when compared to AWS Custom Auto Scaling for the HiBench workload:
