According to a recent LinkedIn post from Depot, the company has been experimenting with aggressive performance tuning of its Depot CI microVMs, cutting cold-boot times from roughly seven to nine seconds to under one second in test conditions. The post details a stack of incremental optimizations across kernel configuration, system services, cloud-init behavior, and memory management.
Meet Samuel – Your Personal Investing Prophet
- Start a conversation with TipRanks’ trusted, data-backed investment intelligence
- Ask Samuel about stocks, your portfolio, or the market and get instant, personalized insights in seconds
The company’s LinkedIn post highlights that moving to a direct kernel boot with a trimmed configuration, disabling nonessential systemd services, and tightening cloud-init usage yielded initial gains, bringing boot times to around three seconds. Further improvements were reportedly achieved by replacing cloud-init for configuration delivery via Cloud Hypervisor’s fw_cfg interface and writing a custom init system tailored for ephemeral VMs.
As shared in the post, additional refinements included reducing console logging overhead, adjusting kernel clock and timer parameters for KVM, and backing VM memory with 1 GB hugepages to cut page faults during boot. The post notes current performance around 0.6 seconds at the P50 and 1.2 seconds at the P90, with some variance tied to OCI-backed root disk streaming and on-host caching.
For investors, these technical gains suggest Depot is focused on lowering latency and infrastructure overhead in its CI platform, which could enhance throughput and cost efficiency for customers running frequent or parallelized builds. If translated into commercially robust features, such performance improvements may strengthen Depot’s competitive position in cloud-native CI, potentially supporting customer acquisition and retention in a crowded DevOps tooling market.
The post also indicates ongoing work on VM memory snapshot and restore, hinting at further reductions in startup time and improved elasticity for build workloads. Continued progress in this area could allow Depot to optimize resource utilization and pricing models, although the ultimate financial impact will depend on customer adoption, scalability of these techniques in production, and the company’s ability to differentiate against larger CI and cloud providers.