Remove Energy Remove Network Remove Storage Remove Tuning
article thumbnail

Observability engineering: Getting Prometheus metrics right for Kubernetes with Dynatrace and Kepler

Dynatrace

This challenge has given rise to the discipline of observability engineering, which concentrates on the details of telemetry data to fine-tune observability use cases. But often, we use additional services and solutions within our environment for backups, storage, networking, and more. Labels we don’t need.

Metrics 169
article thumbnail

What Adrian Did Next?—?Part 2?—?Sun Microsystems

Adrian Cockcroft

The early days at Sun Cambridge were special, I absorbed a lot about networking and the technical side of the role from my fellow systems engineer Martin Baines, and we were driving all over the region in cool company cars (I had a Citroen BX 16V) selling a really hot product. Rich Pettit is one of the best programmers I ever met.

Tuning 52
article thumbnail

A case for managed and model-less inference serving

The Morning Paper

Model variants can be created by methods such as model compression, knowledge distillation, tuning of hyperparameter values, varying precision, optimising for different batch sizes, and so on. Different layers offer trade-offs in terms of resource capacity, cost and network latency, management overheads, and energy-efficiency.