The article summarizes the 58 Group technical salon where experts from Momo and 58 shared practical experiences on monitoring platform architectures, coverage, alarm configurations, convergence techniques, custom dimensions, multi‑view dashboards, and future directions for intelligent and automated monitoring across the company.
The article discusses common challenges with missing logs in production, proposes practical solutions such as adding machine identifiers via Nginx headers and embedding user information with Log4j's MDC, and outlines concise logging guidelines to improve traceability and performance analysis for Java backend systems.
Amid the rise of serverless Kubernetes, growing pod volumes, and real-time log demands, this article examines emerging log-handling challenges, evaluates traditional collection methods, and presents a comprehensive “Logtail + Log Service + Ecosystem” architecture that delivers high-throughput, reliable, and scalable logging for cloud-native environments.
Alibaba’s monitoring evolution—from fragmented early tools to the standardized Sunfire platform and now AI‑powered full‑link observability—addresses scaling challenges, introduces business‑centric metrics, automated traceability, and intelligent anomaly detection, illustrating how massive, multi‑tenant infrastructures achieve unified, proactive operations at scale.
The article explains why operating massive Kubernetes clusters is as challenging as building large systems, outlines three critical stability questions, shares real‑world data collection, visualization, and tooling practices, and provides concrete recommendations for high‑availability, monitoring, and performance optimization.
This article shares practical experience and best‑practice guidelines for operating large‑scale Kubernetes clusters, covering stability checks, component failure impact, recovery strategies, alerting mechanisms, data collection, visualization, and the suite of operational tools that help ensure reliable, high‑performance cloud‑native infrastructure.
This article explains how microservice architectures require a comprehensive monitoring system, covering data, resource, and code dimensions, and describes eight atomic monitoring scenarios such as URL, host, product, component, custom, resource, APM, and event monitoring to help engineers design effective observability solutions.
The article explains the concept, functions, design goals, data models, log collection, and deployment considerations of distributed tracing systems, and compares several open‑source and proprietary solutions such as Dapper, Zipkin, Pinpoint, Alibaba Eagle Eye, and JD Hydra to guide the selection of an appropriate tracing platform.
This article explains why microservice architectures need reliable communication, load balancing, fault tolerance, monitoring, tracing and circuit breaking, and shows how Istio—a cloud‑native service mesh built on Envoy—provides these capabilities, enabling blue‑green and canary deployments, traffic routing, retries, and observability within Kubernetes.
An in‑depth look at Bilibili’s multi‑layer monitoring overhaul, detailing the shift from a monolithic Zabbix setup to micro‑service‑based ELK, Dapper, Misaka, Traceon and Lancer systems, and how layered observability improves fault detection across business, application, and infrastructure levels.
This article explains Zipkin’s data model, how Spring Cloud Sleuth generates and sends Span and Annotation information, the message‑channel listener that converts Sleuth spans to Zipkin spans, debugging techniques to observe the collected data, and why the number of spans shown in Zipkin’s UI can differ from the raw count.
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.
Pandora.js, the Alibaba Midway team's first open-source project, consolidates years of production-grade Node.js operations by offering three core capabilities—manageable application and process control, comprehensive metrics, and Open-Tracing-based request tracing—exposed via RESTful APIs and logs for easy integration.
Metrics act as health checks for applications, enabling developers to monitor performance, track changes, and assess stability; this article explains Pandora.js’s metric naming conventions, types like Gauge, Counter, Histogram, and Meter, and provides practical Node.js code examples for implementing these measurements.
This article describes how WiFi 万能钥匙 designed and implemented the Roma monitoring platform to handle billions of daily requests, covering background challenges, architectural principles, component design, data collection, transmission, storage, alerting, and future directions for large‑scale observability.
The article introduces the ELKB stack—a combination of Elasticsearch, Logstash, Kibana, and Beats—explaining its background, user needs, architecture, component functions, typical scenarios, and the team’s practical implementations for real‑time log and time‑series data processing.
Pinpoint is a full‑stack, non‑intrusive tracing platform that visualizes service topology, active threads, request latency, and application health, and this article explains its architecture, data model, and step‑by‑step process for creating custom plugins—including ServiceLoader configuration, TraceMetadataProvider, and ProfilerPlugin implementations with code examples.
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 examines how Meipai, a popular live‑streaming and short‑video platform with over 150 million monthly active users, engineered a comprehensive, three‑dimensional monitoring architecture that spans client to server, integrates unified dashboards, and leverages both private and public cloud resources to ensure reliable, scalable operations.
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.
Metrics‑Driven Development (MDD) extends test‑driven principles by embedding real‑time monitoring into design, enabling rapid, precise, and granular software iterations, improving early problem detection, decision support, and aligning development with DevOps culture.
Effective Node.js monitoring boosts competitiveness, user experience, and cost efficiency, and this guide outlines eleven key recommendations—from tracking downtime and response thresholds to linking performance with business metrics and leveraging third‑party APM tools—ensuring robust, noise‑free alerts and secure, scalable applications.
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.
This article explains how focusing on non‑functional quality during external acceptance testing can drive DevOps teams to improve system monitorability, reduce technical debt, and establish concrete change‑control, acceptance, and performance verification processes for both operational and business‑level observability.
This article introduces CAT, a Java‑based open‑source distributed real‑time monitoring system, covering its origins, design goals, architecture, message processing pipeline, instrumentation model, and how it achieves high availability, scalability, and low‑latency analytics for large‑scale internet services.
