The hidden latency inside your database: PlanetScale on network-attached storage costs
DanielLockyer · x · 2026-11-04
PlanetScale's engineering blog highlights an overlooked performance drag: network latency inside your database cluster. Most cloud-hosted databases use network-attached storage — a disk on a separate server — adding measurable latency to every read/write, while locally attached storage keeps the disk on the same machine as the CPU. The post traces how the industry got here (SPARC servers with in-chassis disks, RAID in the late 1980s, then compute-storage separation for durability and throughput). Performance 101: move your app closer to your database, then move database storage closer to database compute. DanielLockyer says this is the most common source of excess latency he sees.
More from Infra
- OpenAI's 3.4-month compute doubling trend used ~15 data points; Epoch AI corrected it to ~6 — ohlennart · 2026-11-04
- Big tech has contracted over 10 GW of nuclear power, but contracts aren't generation — ingliguori · 2026-11-04
- Fully Local AI Short Film Rendered on a Mac, Workflow Open-Sourced as Phosphene — Opening-Ad5541 · 2026-11-04
- Anthropic's 15-person chip team uses Claude to design its own AI chips — kimmonismus · 2026-11-04
- Anthropic's 15-person chip team uses Claude to design its own AI chips ahead of $1.5T IPO — kimmonismus · 2026-11-04
- AAOI signs $194M InP wafer supply deal with Yunnan Germanium at ~$1,077 per wafer — zephyr_z9 · 2026-11-04