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 how Linux creates and allocates PID namespaces, how Docker containers obtain their own PID namespaces using CLONE_NEWPID, the internal kernel structures involved, and how processes view their PID inside a container.
This article explains the concept of CPU turbo boost, why single‑core performance metrics can be misleading, how different CPUs vary in base frequency and cache, and how turbo technology automatically raises clock speeds within safe limits to improve overall processing power.
This article explains step by step how a simple Hello World program is compiled, linked, and executed on Linux, covering the ELF executable format, the role of the file command, the fork‑execve process creation sequence, and the kernel’s binary loader implementation.
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.
