Theory of Intelligence
BACKEND ENGINEERING•Scalability And Reliability•Scalability•1.2 Latency & Throughput

1.2.1 Latency

Subtopics: Latency, P99 Latency, Tail Latency, Throughput and Network Bottleneck.

timer1 min read•format_list_bulletedConcept 1 of 5•forumLesson Discussion

1.2.1 Latency

Breakdown: DNS + TCP + TLS + TTFB + download. On the server: queue time vs handler time.

Why it matters

Users and SLOs care about time, not your CPU graph.

How it is used

Measure at the edge. Separate waiting vs running. Fix the largest slice first (usually the database or a missing timeout).

Discuss theoretical concepts, mathematical formulas, and architectural foundations.

Supports inline code with `backticks`
No comments yet. Be the first to start the discussion!
arrow_backPrevious Lesson
1.1 Scaling Up & Out
Next Lessonarrow_forward
1.3 Backpressure & Partitions