Skip to content

Resources & Cost

How it works

What scheduling is

Scheduler architecture

Workload management

What scheduling forbids

Playbooks

Share a cluster or split it

Labs

FIFO vs SRPT Head-of-line blocking Stranded resources and DRF Power of two choices Throughput vs goodput Multiplexing dividend A late autoscaler

Interview

Interview questions Scenarios

Reference

Summary and key takeaways Glossary

The Data EngineeringBeta

Main content

Mechanisms
Scheduling & Workload Management
Playbooks

Scheduling & Workload Management

Playbooks

What do I do, and what does each option cost?

1
Share a cluster or split it
Several teams need compute: one shared pool, a shared pool with guaranteed floors, or separate clusters? Three questions about correlation, guarantees and how fast capacity comes back, and the price of each answer.
Choose

Playbooks across every mechanism →

The Data Engineering

Learn

Mechanisms
Symptoms
Routes

Practice

Labs
Playbooks
Interview

Reference

Trade-offs
Relationships
Glossary

The project

About
Privacy

Text CC BY-NC 4.0 · Lab code MIT

Written by Aayush Sharma