Fei has over 10 years of development experience at Tencent and Sogou. Through this account, he shares his deep insights on performance.
This article explains the fundamentals of CPU scheduling in Linux, covering real-time scheduling for high-priority tasks and the fair scheduling algorithm for user processes, including code examples.
This article provides a comprehensive analysis of how JDK NIO performs file read and write operations by examining the underlying Linux kernel mechanisms, including the differences between Buffered and Direct IO, the structure and management of the page cache, file readahead algorithms, and the kernel parameters governing dirty page writeback.
This article explains how Nginx evolved into the Kong API gateway through OpenResty, describes Kong’s plugin architecture and micro‑service‑oriented capabilities, and demonstrates setting up and managing Kong with Konga on Tencent Cloud, including monitoring, logging, and high‑availability features.
This article explains how high‑frequency trading firms achieve ultra‑low network latency by combining proximity deployment, dedicated links, microwave transmission, InfiniBand, low‑latency switches, kernel bypass, RDMA, TCP offload engines and FPGA acceleration, and summarizes the impact of each technique on overall request latency.
This article explains how Linux implements processes and threads, showing that both are represented by the same task_struct structure, detailing thread creation via pthread_create and clone, and comparing the kernel‑level steps—including flag handling, copy_process, and resource sharing—that differentiate threads from full processes.
This article summarizes a series of technical Q&A from an OSChina event covering Linux networking fundamentals such as port limits, network namespaces, TCP connection handling, C10K problem, packet loss troubleshooting, TCP memory usage, high CPU causes, useful monitoring tools, kernel parameters, and practical socket examples.
The article explains how to decide between a CPU‑saturated but memory‑free node and a memory‑saturated but CPU‑free node when scheduling a new Kubernetes pod, arguing that the node with ample memory (CPU‑busy) is generally preferable and describing the underlying kube‑scheduler considerations.
This article thoroughly examines Kafka's broker‑side network architecture, tracing its evolution from a simple sequential model to a high‑performance, event‑driven Reactor design using Java NIO, and provides practical tuning guidance for achieving optimal throughput and latency.
This article provides a comprehensive, code‑driven walkthrough of Netty's internal networking architecture, covering NioEventLoopGroup, selectors, channels, pipelines, bootstrap configuration, binding mechanics, and how new connections and user requests are processed in a Java server environment.
This article explores Tencent’s evolution from monolithic LAMP/MVC stacks to a container‑based microservice architecture, detailing the open‑source Polaris Mesh service mesh, Spring Cloud Tencent framework, and their gateway, naming, and configuration components, while highlighting deployment benefits and practical usage examples.
