Scale the read platform to 12k rps

advanced

Scenario & brief

A content platform now peaks at 12,000 rps, most of it reads. The current single-AZ origin fleet and lone database are saturated and slow.

Targets: p99 ≤ 130 ms, 99.95% availability, critical durability, under $1,700/mo.

Shed load before it hits the origin: a CDN for static/edge-cacheable content, an ElastiCache tier for hot reads, then a right-sized autoscaling origin across two AZs and a Multi-AZ database. The challenge is doing all of that without blowing the budget — Graviton plus a Savings Plan is your friend.

12,000 rps peakp99 ≤ 130ms99.95% availdurability: criticalbudget $1,700/mo

CloudFront

Networking

Enable CDN

System health

Erupting · SLA breach

/ 100

Score

SLA not met yet

Monthly cost

$1,241

Budget $1,700/mo · within budget

Metrics

Capacity28

Availability30

Durability25

Cost efficiency71

Requirements

Peak capacity — 10800 rps compute · 3400 rps db (need ≥ 12000 rps)
p99 latency — ~187 ms (need ≤ 130 ms)
Availability — 99.00% (need ≥ 99.95%)
Durability — at risk (need redundancy + backups)
Budget — $1241/mo (need ≤ $1700/mo)

Advisor

Compute tops out at ~10800 rps but peak demand is 12000 rps — requests will queue.
The database is saturated at peak — add a cache to shed read load, or scale it up.
Compute runs in a single AZ — spread across ≥2 AZs (with ≥2 instances) to meet the availability target.
The database has no Multi-AZ standby or replica — a failure risks data loss. Enable Multi-AZ and backups.

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.