This guide walks through setting up a Zipkin server, configuring Spring Cloud Sleuth to send trace data via HTTP or RabbitMQ, and using the Zipkin UI to monitor request latency and service dependencies in a Spring Boot microservices environment.
This tutorial explains how Spring Cloud Sleuth creates and propagates Trace‑ID and Span‑ID across microservice calls, shows the required HTTP headers, demonstrates adding the spring‑cloud‑starter‑sleuth dependency, customizing header output, configuring logging levels, and provides runnable code samples with log output for verification.
This article describes the background, design goals, architecture, implementation details, and lessons learned from building a low‑overhead, low‑intrusion distributed tracing system using Kafka, Elasticsearch, and OpenTracing to monitor microservice interactions and support performance analysis and DevOps decision‑making.
To cope with Meituan Hotel’s exploding micro‑service complexity, the infrastructure team built the Satellite System—combining MTrace and a selective, zero‑intrusion Log4j2‑based logging pipeline that streams enriched logs through Kafka, Storm, Redis and Elasticsearch, delivering second‑level trace‑log queries and six‑month retention, dramatically speeding up debugging.
Over seven years, Pinterest’s monitoring team built and refined a three‑pronged observability platform—time‑series metrics, log search, and distributed tracing—scaling from a single‑machine system to handling millions of data points per second across tens of thousands of AWS VMs, while addressing reliability, cost, and usability challenges.
This article chronicles Pinterest's seven‑year evolution from a single‑machine time‑series monitor to a multi‑component system that integrates metrics, log search, and distributed tracing, sharing architectural choices, scaling challenges, and lessons learned for building reliable, high‑performance operations platforms.
QTracer is Qunar’s internal distributed tracing system that generates a global TraceID for each request, records operations across services, and provides features such as execution chain visualization, log correlation, conditional search, service dependency analysis, database statistics, transparent data propagation, and low‑overhead instrumentation for debugging and performance monitoring.
This article provides a comprehensive technical overview of QTracer, Qunar’s internal distributed tracing platform, covering its architecture, core concepts, key features such as execution‑chain queries, log association, conditional searches, data storage, non‑intrusive instrumentation, bytecode injection, and the QTracer Debug tool for online breakpoint debugging.
This article explains how Lianjia designed and implemented LTrace, a zero‑intrusion, high‑performance distributed tracing system that captures full request chains across heterogeneous services, supports multi‑language environments, offers flexible sampling, and enables rapid fault isolation and performance optimization.
Uber’s engineering team chronicles the evolution of its distributed tracing system—from the early Merckx pull‑based solution and TChannel integration to the open‑source Jaeger platform—detailing architectural shifts, sampling strategies, multi‑language client libraries, and the move toward a fully cloud‑native, end‑to‑end observability stack.
This article explains why distributed systems need tracing, outlines design goals, compares major implementations like Zipkin, EagleEye, and Hydra, and details the data collection, storage, and analysis pipelines that enable end‑to‑end visibility and performance optimization in large‑scale services.
This article surveys the design of end‑to‑end tracing systems for large distributed services, explaining core use cases, tracing approaches, metadata propagation, sampling strategies, visualization techniques, and recommended design choices to improve debugging, performance analysis, and resource attribution.
As microservice architectures grow, service calls become increasingly complex, involving dozens of services and teams, making rapid fault localization and comprehensive data analysis critical; distributed tracing systems address these challenges by providing end‑to‑end visibility, low‑overhead instrumentation, and scalable monitoring across large‑scale applications.
The article introduces MTrace, Meituan‑Dianping’s large‑scale distributed session tracing system, explaining its call‑chain concept, architecture, data‑embedding SDK, trace and span identifiers, APIs for transparent data propagation, and how it enables bottleneck detection, performance optimization, and comprehensive monitoring across heterogeneous backend services.
MTrace, Meituan‑Dianping’s internal distributed tracing platform, assigns a global 64‑bit traceId to each request, instruments RPC, HTTP, database and messaging calls, aggregates data via Kafka into HBase and Hive, and visualizes the full call chain to pinpoint network cross‑datacenter traffic, latency bottlenecks, redundant calls, and correlated exceptions, thereby enabling systematic service‑level optimization.
Twitter’s internal monitoring team built a full‑stack observability platform that handles billions of metric writes per minute, supports distributed tracing, log aggregation, visual dashboards, and alerting across data centers and public clouds, and shares the architecture, components, and key lessons learned.
To support over 140 million monthly active users, Sina Weibo evolved from a simple LAMP stack to a sophisticated third‑generation architecture featuring layered interfaces, service and resource tiers, custom RPC and messaging frameworks, SSD caching, and a large‑scale distributed tracing system called WatchMan.
Backend Architecturedistributed tracinglarge-scale web
The article details how Weibo evolved from a LAMP‑based first generation to a third‑generation, orthogonal three‑layer (interface, service, resource) and four‑vertical (business, technology, monitoring, governance) architecture that supports massive high‑availability, high‑concurrency workloads with middleware such as Web V4, MCQ, Motan, object store, SSDCache, and the WatchMan distributed tracing system.
An in‑depth look at Weibo’s evolution to its third‑generation backend system, detailing the orthogonal decomposition model, three‑tier horizontal layering, key middleware such as MCQ, Motan RPC, SSDCache, and the WatchMan tracing platform that together enable high‑availability, massive concurrency, and low‑latency services for billions of users.
In the cloud and mobile era, while many scalability issues can be addressed by cloud platforms, services still face challenges such as remote RPC calls, distributed tracing, configuration management including service discovery and load balancing, and scheduling with lifecycle management, prompting architects to design transparent, pluggable solutions.