All the articles with the tag "performance".
ulimit and cgroups v2: set per-process CPU, memory, and file limits, use systemd slice controls, and keep one runaway service from killing your server.
Squeeze every MB/s from WireGuard: MTU sizing, GSO/GRO CPU offloading, AllowedIPs routing, PersistentKeepalive tradeoffs, and iperf3 benchmarks included.
Linux ships with conservative kernel defaults. These sysctl settings tune your server for networking, memory, and file I/O, with explanations, not just paste-and-pray values.
WireGuard is fast out of the box, but default config leaves throughput on the table. Tune MTU, use the kernel module, and benchmark what you actually get.
Your Linux box has hundreds of kernel knobs in /proc/sys that nobody ever touches. Most don't matter, here are the handful that actually improve a Docker host.
A kernel upgrade halved one team's PostgreSQL throughput. The fix was kernel tuning: huge pages, THP, swappiness, I/O scheduler. Here's what matters and why.
Out of RAM and no time to reimage? Add swap via a file on any partition using mkswap, swapon, and fstab, done in under 5 minutes.
Learn multi-stage Docker builds to slash image sizes by 90%. Practical before/after examples for Node.js, Python, and Go with real size comparisons.
Learn systemd socket activation to start services on-demand, save RAM, and cut boot time. Includes .socket unit files, real examples, and testing with systemd-socket-activate.
Your CI job waits 4 minutes for npm install every run. One caching strategy cuts it to 15 seconds. Here's how.
zstd is as fast as gzip with near-xz compression ratios. Here's why you should drop bzip2 forever and how to use zstd in 2026.
Learn which sysctl parameters actually improve Linux server performance. Network tuning, memory management, and a ready-to-use sysctl.conf for Docker hosts.
