- Blog /
- How DreamHost Slashed Memory Usage by 80% and Scaled to 76 Million Time Series

For any growing business, there comes a point where the tools that once worked perfectly begin to show their limits. This is especially true for monitoring infrastructure. As your user base, services, and data volumes expand, the pressure on your monitoring stack intensifies. For web hosting leader DreamHost, with over 1.5 million websites to manage, their existing open-source solutions simply couldn’t keep up.

They found their monitoring stack would “fall apart” under the load of high-cardinality data, consuming immense resources just to stay operational. The challenge was clear: find a solution that could handle massive scale without the operational overhead.
After evaluating the usual suspects, DreamHost chose VictoriaMetrics, and the results speak for themselves. The switch wasn’t just an incremental improvement; it was a transformative one.
Here are some of the key gains they experienced:
The ultimate goal of monitoring isn’t just to collect data; it’s to gain visibility that drives business value. For DreamHost, the stability and efficiency of VictoriaMetrics led to a “massive improvement in visibility” into what is happening with their customers’ websites. This allows them to be more proactive, improve service quality, and build a better customer experience.
DreamHost’s success is a powerful example of what happens when a great product meets a challenging problem. If their story resonates with you, here’s how you can learn more:
Reduce observability costs with hybrid strategies: prioritize revenue-driving signals in SaaS, self-host high-volume telemetry. Cut bills 3-12x without losing visibility.
Q1 2026 brought incremental but important updates to VictoriaMetrics Anomaly Detection: UI improvements, AI assistance inside the UI, a public traces playground, new false-positive reduction controls, and continued resource optimizations.
VictoriaMetrics participated in KubeCon + CloudNativeCon Europe 2026 in Amsterdam. The team delivered multiple talks covering platform design, Kubernetes observability, and distributed tracing optimization. A real-world case study from Miro showcased a cost-efficient, AZ-aware observability architecture built with VictoriaMetrics. With a 15-person team on site, the booth saw strong interest from users tackling scaling, cost, and performance challenges. The company also hosted its first community after-party, “After Deploy,” co-organized with Varnish and Shipfox, extending discussions beyond the conference.
Q1 2026 brought VictoriaLogs GA, a hosted MCP Server, a brand new cost calculator, a major expansion of alerting rule presets with a new editor, infrastructure improvements, notifications via generic webhooks and a few things we are cooking.