Layered diagram contrasting epoll's readiness-based loop with io_uring's submission and completion queues.

Architecting Async I/O with io_uring vs. epoll: A Deep Dive into Linux Performance Models

Compare io_uring and epoll as Linux async I/O architectures, covering kernel internals, syscall costs, and the production patterns where each one wins.

September 1, 2026 · 9 min · 1866 words · martinuke0
Diagram of a TCP flow with bottleneck link and BBR pacing.

Optimizing TCP BBR Congestion Control: A Deep Dive into Production Deployment

How BBR actually estimates bottleneck bandwidth and RTT, why v2/v3 fix v1’s loss-insensitivity, and what to tune at the kernel, application, and NIC layers before you ship it.

September 1, 2026 · 10 min · 2075 words · martinuke0

How Docker Works Internally: A Deep Dive into Its Architecture and Components

Docker has revolutionized software development and deployment by providing lightweight, portable containers that package applications and their dependencies together. But how exactly does Docker work under the hood to achieve this isolation and efficiency? This article takes a comprehensive look at Docker’s internal architecture, explaining the key components and how they interact to create and run containers. Table of Contents Introduction Docker’s Client-Server Architecture Key Docker Components Docker CLI Docker Daemon (dockerd) Container Runtime (containerd and runc) Linux Kernel Features How Docker Creates and Runs a Container Filesystem Management with OverlayFS Networking and Isolation Resource Management via cgroups Conclusion Introduction Docker containers provide isolated environments that behave like virtual machines but share the host OS kernel, making them highly efficient. This is achieved through a combination of Linux kernel features, container runtimes, and Docker’s own architecture. Understanding these layers helps in optimizing container usage and troubleshooting complex issues. ...

December 8, 2025 · 5 min · 987 words · martinuke0
Feedback