Laravel Cloud Achieves Sub-500ms Scale-to-Zero Using Checkpoint/Restore Technology
By
Laravel Team
Master baker tier. Every paragraph earns its place on the tray.
Summary
Laravel Cloud introduced a new "Flex" scale-to-zero feature that reduces wake time from 10 seconds to under 500 milliseconds using checkpoint/restore technology. Instead of performing a cold boot on every request, the runtime saves the full in-memory state to disk and restores it instantly. The original implementation had a 10-second wake time that was noticeable to users, and adding database/cache startup would have made it worse, so most apps kept those running continuously. The new approach also includes spending limits that enforce a hard monthly ceiling for apps.
Key quotes
· 4 pulledThe original implementation of scale to zero on Cloud had a 10-second wake time, long enough for users to notice.
The new scale-to-zero Flex compute uses checkpoint/restore.
Instead of a cold boot on every request, the runtime saves the full in-memory state to disk and restores it instantly.
Wake time drops to under 500 milliseconds.
You might also wanna read
Modal introduces GPU memory snapshots for sub-second container startup times
Modal announces GPU memory snapshots, a new feature that extends their checkpoint/restore technology to GPU-accelerated workloads, enabling
Zeroboot: Sub-millisecond VM Sandboxes for AI Agents Using Copy-on-Write Forking
Zeroboot is an open-source project that enables sub-millisecond VM sandboxes for AI agents using copy-on-write forking. It achieves signific
How Modal reduced inference cold starts by 40x using LP, FUSE, C/R, and cuda-checkpoint
Modal presents a deep technical analysis of how they reduced inference cold starts by 40x using a combination of techniques including LP (li
How Digital Society Reduced Cloud Costs by 76% While Tripling Capacity with Hetzner Migration
Digital Society, a not-for-profit cooperative, successfully migrated their cloud infrastructure from AWS and DigitalOcean to Hetzner, achiev
digitalsociety.coop·8mo agoHow LLMs and AI agents are breaking the 20-year-old stateless compute architecture
The article argues that the foundational assumption of modern cloud-native architecture—that state lives in the database while compute is st
Cloudback adds Linear workspace backup support to its Git backup platform
Cloudback is a backup and restore service for Git platforms (GitHub, GitLab, Azure DevOps) and Linear. It now supports Linear workspace back
