Qunar Tech Salon is a learning and exchange platform for Qunar engineers and industry peers. We share cutting-edge technology trends and topics, providing a free platform for mid-to-senior technical professionals to exchange and learn.
This article explains the necessity of vector databases for AI workloads, reviews the PostgreSQL ecosystem, compares vector database options, provides detailed PgVector installation and usage steps, shares operational best‑practices, performance tuning tips, and real‑world deployment cases at Qunar and Tujia.
This article examines various image‑generation approaches, compares web‑frontend, client‑side, and backend methods, introduces a new Node‑backend solution based on Satori to convert HTML to SVG and then to PNG with Resvg (later Sharp), and details performance and memory optimizations that dramatically improve speed, resource usage, and stability for large‑scale image‑service deployments.
At the WOT2024 conference, Qunar Travel’s CTO Zheng Jimin presented a comprehensive overview of AI-generated video production for international hotels, detailing challenges, AI-driven workflow automation, practical implementation steps, multilingual translation enhancements, and performance results, offering valuable insights for scaling high‑quality hotel video content.
This article presents a detailed attribution analysis framework—including background research, a four‑step workflow, Bayesian causal detection, Simpson's paradox handling, and real‑world case studies—demonstrating how data‑driven insights can improve conversion rates and operational efficiency across multiple business lines.
This article details the motivation, design, implementation, testing, and rollout of a refactored Kubernetes DNS solution that replaces the default kube-dns → CoreDNS chain with a node‑local q‑dnsmasq cache and parallel upstream queries to achieve higher availability, faster resolution, and better cache hit rates in large‑scale clusters.
This article details the background, overall architecture, challenges, and step‑by‑step redesign of Qunar Travel's Watcher monitoring platform to achieve second‑level (per‑second) data collection, storage, and alerting, including storage engine selection, client and server optimizations, deployment strategies, and operational outcomes.
This article presents a comprehensive analysis and engineering of Qunar's flight‑ticket intelligent pre‑warning (Radar) system, covering the business need, value analysis, architectural redesign, feature extraction, indicator classification, accuracy quantification, multi‑algorithm anomaly detection, automatic parameter tuning, observed effects, and future plans to incorporate large‑model techniques.
This article analyzes the release‑time bottlenecks of a core travel platform after the post‑COVID traffic surge and presents a shrink‑then‑expand deployment strategy combined with physical‑machine container deployment, evaluating several open‑source solutions and demonstrating significant improvements in release speed, resource cost, and system stability.
This article presents a comprehensive case study of how Qunar Travel identified and resolved Kafka production bottlenecks—through metric monitoring, thread and flush parameter tuning, and Filebeat batch adjustments—resulting in a 2000‑core CPU reduction, higher network idle rates, and lower resource consumption across three clusters.
This article details the investigation of sporadic interface timeouts in the Sirius real‑time pricing service, revealing a weekly pattern linked to RAID controller consistency checks that cause IO spikes, logback queue blockage, and ultimately Dubbo client‑side timeouts, and proposes mitigation steps and general performance‑troubleshooting guidelines.
