5.1万- Resources
- Engineering
ClickHouse engineering resources
SLOs, SLIs, and SLAs: definitions, differences, and worked examples
An SLI measures a service, an SLO sets the internal target for that measurement, and an SLA is the external contract with penalties. How the three layers fit together, with error-budget math and worked examples.
Last updated: 2026年7月29日
RUM vs synthetic monitoring: which do you need?
RUM measures what real users experienced; synthetic monitoring measures what scripted probes experienced. How the two differ on alerting, coverage, and cost, and when to run both.
Last updated: 2026年7月29日
What is root cause analysis? Methods, process, and limits
Root cause analysis traces an incident from symptom to underlying cause. The methods, a worked example, a report template, and where the single-root-cause model breaks down.
Last updated: 2026年7月29日
RED method vs USE method: which should you use?
RED (Rate, Errors, Duration) monitors request-driven services; USE (Utilization, Saturation, Errors) monitors resources. How they differ, a worked outage through both lenses, and why most teams run both.
Last updated: 2026年7月29日
Percentiles vs averages: why your latency dashboard lies
Latency distributions are right-skewed, so the mean hides the slow tail users actually feel. What p50, p95, and p99 mean, why you cannot average percentiles, and how to compute them at scale.
Last updated: 2026年7月29日
OpenTelemetry's profiles signal enters public alpha
OpenTelemetry profiles, the fourth telemetry signal, entered public alpha in March 2026, with OTLP support, collector pipelines from v0.148.0, and a whole-system eBPF profiler.
Last updated: 2026年7月29日
OpenTelemetry semantic conventions explained
OpenTelemetry semantic conventions standardize telemetry attribute names like http.request.method and db.system.name, so data from any service is portable and queryable across tools.
Last updated: 2026年7月29日
OpenTelemetry histograms explained: buckets, exponential histograms, and percentiles
How OpenTelemetry histograms summarize distributions: explicit-bucket vs base-2 exponential encodings, how percentiles are computed from buckets and their error bounds, and how histogram data is stored and queried.
Last updated: 2026年7月29日
Observability vs visibility: the terms teams conflate
Visibility means seeing predefined surfaces; observability means interrogating internal state for unknowns. Why network teams say one and software teams say the other.
Last updated: 2026年7月29日
Observability vs monitoring: what''s actually different
Monitoring watches known indicators for known failures; observability lets you ask new questions of a live system. How they differ in data, cardinality, and cost.
Last updated: 2026年7月29日
Observability architecture: how the pieces fit together
The six layers of an observability architecture, from OpenTelemetry SDKs to alerting, and the four design decisions that determine what debugging costs at scale.
Last updated: 2026年7月29日
What is MTTR? MTTD, MTBF, and the incident metrics that matter
MTTR is the average time from incident start to service restoration. Learn the formulas behind MTTR, MTTD, MTTA, and MTBF, what a good target looks like, and how observability shrinks each one.
Last updated: 2026年7月29日
LLM inference latency: TTFT, tokens per second, and what to measure
LLM inference latency breaks down into TTFT, time per output token, throughput, and end-to-end latency. What each metric means, what moves it, and how to measure it with OpenTelemetry.
Last updated: 2026年7月29日
LLM guardrails: what they are and how to run them in production
LLM guardrails are programmatic controls that validate model inputs and outputs to block prompt injection, PII leaks, and off-topic responses, and every verdict they emit is an event worth monitoring.
Last updated: 2026年7月29日
The incident response process: from alert to postmortem
The incident response process is the structured sequence teams follow when production breaks: detect, declare, mobilize, mitigate, resolve, and learn, with severity levels, defined roles, and blameless postmortems.
Last updated: 2026年7月29日