A nightly batch/analytics job runs on 4× m5.4xlarge On-Demand, 24×7, even though the work only runs off-hours and can safely restart if an instance disappears.
Targets (relaxed): p99 ≤ 300 ms, 99.0% availability, standard durability, under $300/mo.
All challenges
Run batch jobs on Spot
intermediateScenario & brief
300 rps peakp99 ≤ 300ms99% availdurability: standardbudget $300/mo
Batch Workers
Compute
4instances
System health
Erupting · SLA breach
28
/ 100
Score
SLA not met yet
Monthly cost
$2,593
Budget $300/mo · $2,293 over
Metrics
Capacity100
Availability100
Durability25
Cost efficiency0
Requirements
- Peak capacity — 26000 rps compute · 3400 rps db (need ≥ 300 rps)
- p99 latency — ~74 ms (need ≤ 300 ms)
- Availability — 99.00% (need ≥ 99.00%)
- Durability — at risk (need backups)
- Budget — $2593/mo (need ≤ $300/mo)
Advisor
- The database has no Multi-AZ standby or replica — a failure risks data loss. Enable Multi-AZ and backups.
Discussion
Sign in to join the discussion.
No comments yet. Be the first to start the discussion.
For learning purposes only. Costs and capacities are illustrative, not live AWS prices. Not affiliated with or endorsed by Amazon Web Services.