Linux Kernel Journey
This article explains the Linux kernel’s perf utility, covering its architecture, key features such as lightweight event sampling, tracing, profiling and debugging, step‑by‑step installation, common commands with real code examples, and how to use perf and flame graphs to locate and optimise performance bottlenecks.
This article walks through the registration of the KVM misc device in the Linux 5.9 kernel for arm64, explains how /dev/kvm is created via misc_register, and demonstrates a user‑space program that opens the device and uses an ioctl to retrieve the KVM API version, with detailed code analysis.
This article explains how the x86‑64 paging mechanism maps virtual addresses to physical memory, detailing the required protection‑mode conditions, page‑table structures, control‑register settings, various paging modes (32‑bit, PAE, 4‑level, 5‑level), and provides concrete kernel code examples and address‑translation demonstrations.
The article provides an in‑depth technical analysis of Linux’s memory reclamation system, covering zones, watermarks, page flags, LRU lists, the shrink_zone workflow, kswapd, direct reclaim, OOM handling, page‑cache structures, and practical tuning tips for optimal performance.
The article explains how memory pools reduce allocation overhead and fragmentation by pre‑allocating large memory blocks, describes their implementation in C++ and the Linux kernel, compares various pool designs, and shows practical scenarios where pools improve performance and stability.
The article explains how Linux’s multicore scheduler distributes tasks across CPU cores, describes the core CFS and real‑time algorithms, details load‑balancing mechanisms such as pull/push and active/passive strategies, and discusses power, thermal, and algorithmic optimizations for servers and embedded devices.
This article explains how Linux memory barriers work, why they are needed on SMP systems, the different barrier types, their kernel implementations, and practical examples showing their impact on multithreaded performance and driver development.
This article analyzes eBPF tracing hook mechanisms—kprobe, tracepoint/raw_tp, and fentry—explaining their implementation, performance trade‑offs, kernel version support, and benchmark results, to guide developers in choosing the most efficient hook for production workloads.
At Netdev 0x19, ByteDance's STE team presented two technical talks: a NUMA‑aware MPTCP flow‑selection strategy that boosts Redis benchmark throughput by up to 30% and cuts tail latency by 6%, and a DPDK‑based user‑space MPTCP stack that halves latency and doubles throughput in data‑center tests.
This article explains what disk I/O is, compares HDD and SSD characteristics, describes the Linux I/O stack, outlines performance metrics such as throughput, IOPS and latency, and reviews factors, tools, caching strategies, and RAID configurations that affect storage performance.
