All challenges

Global low-latency at scale

expert

Scenario & brief

A worldwide audience needs p99 ≤ 85 ms at 8,000 rps, 99.95% availability, critical durability — under $1,500/mo. You've inherited only a single-region app fleet and a database: no edge caching, no in-memory cache, single-AZ, on-demand.

You have to build the rest yourself from the component palette — but not everything there belongs. Distant users can only be served fast by going multi-region (set the deployment footprint) and adding a CDN for edge caching; an in-memory cache keeps the database in range. A Global Accelerator looks tempting for latency, but it's costly and redundant once you have a CDN and multi-region — adding it just burns the budget.

8,000 rps peakp99 ≤ 85ms99.95% availdurability: criticalbudget $1,500/mo

Add components

Decide what this architecture actually needs — not every option belongs here.

App Servers

Compute

6instances

System health

Erupting · SLA breach

24

/ 100

Score

SLA not met yet

Monthly cost

$3,736

Budget $1,500/mo · $2,236 over

Metrics

Capacity43
Availability30
Durability25
Cost efficiency0

Requirements

  • Peak capacity 39000 rps compute · 3400 rps db (need ≥ 8000 rps)
  • p99 latency ~134 ms (need ≤ 85 ms)
  • Availability 99.00% (need ≥ 99.95%)
  • Durability at risk (need redundancy + backups)
  • Budget $3736/mo (need ≤ $1500/mo)

Advisor

  • 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

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.