sysdesign-latency-targets-techniques

Define P50/P95/P99 latency targets and budget techniques across request path hops.

Updated Apr 23, 2026

Search Tags:#caching #latency #cdn #system-design #nfr #percentile #geo-dns

Ready to run

npx skills add https://github.com/danilods/matilha-sysdesign-pack --skill sysdesign-latency-targets-techniques

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: sysdesign-latency-targets-techniques
Source: https://github.com/danilods/matilha-sysdesign-pack/tree/main/skills/sysdesign-latency-targets-techniques
Command: npx skills add https://github.com/danilods/matilha-sysdesign-pack --skill sysdesign-latency-targets-techniques

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Sets explicit latency targets by percentile (P50, P95, P99) to guide capacity planning and prevent mis-optimizations between latency, throughput, and bandwidth.

Core Features & Use Cases

Percentile-based targets: define P50/P95/P99 targets for latency budgets across services.
Hop-by-hop budgeting: map the request path (DNS, TLS, LB, API, DB, cache) and assign per-hop techniques.
Use cases: capacity planning for consumer apps, internal APIs, and real-time systems; supports NFR decision-making.

Quick Start

Define P50, P95 and P99 latency targets and map the request path to assign per-hop techniques.

Frequently Asked Questions about sysdesign-latency-targets-techniques

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I define latency targets by percentile for system design?▼

Latency targets are defined by setting explicit P50, P95, and P99 thresholds to guide capacity planning and prevent mis-optimizations between latency, throughput, and bandwidth across your architecture.

How do I budget latency across network hops like DNS, TLS, and API requests?▼

Latency budgeting across hops requires mapping the complete request path (DNS, TLS, LB, API, DB, cache) and assigning specific per-hop techniques to stay within your defined percentile latency limits.

What is hop-by-hop latency budgeting for consumer apps and internal services?▼

Hop-by-hop latency budgeting is the process of mapping the request path and assigning techniques per network stop to ensure consumer apps, internal APIs, and real-time systems meet strict percentile targets.

When do I need percentile latency targets for capacity planning?▼

You need percentile latency targets when capacity planning for consumer apps, internal APIs, or real-time systems to support Non-Functional Requirements (NFR) and prevent mis-optimizing latency against throughput.

What techniques justify latency budgets across CDN, geo-dns, and caching layers?▼

Techniques like CDN distribution, geo-dns routing, and caching are justified per hop by mapping them directly to your request path and validating they keep the system within P50, P95, and P99 latency budgets.