Unlocking True Elasticity for the Cloud-Native Era with Dandelion

Elasticity is fundamental to cloud computing. An elastic platform can quickly allocate resources to match the demand of each workload as it arrives, rather than pre-provisioning resources to meet performance objectives. However, even serverless platforms -which boot sandboxes in 10s to 100s of milliseconds -are not sufficiently elastic to avoid preprovisioning expensive resources. Today's FaaS platforms provision many extra, idle sandboxes in memory to reduce the occurrence of slow, cold starts. Initializing securely isolated sandboxes with a POSIX-like computing environment that today's cloud users expect is slow as it requires booting a guest OS and configuring networking.

Our key insight is that the rise of cloud-native application development provides an opportunity to rethink the application interface to the cloud and co-design a much more efficient, elastic computing platform under the hood. We propose Dandelion, an elastic cloud platform with a declarative cloud-native programming model that replaces POSIX-based network interfaces with higher-level (e.g., HTTP-based) interfaces for applications to interact with remote services like cloud storage, databases, and AI inference services. Dandelion executes applications expressed as DAGs of pure compute functions and communication functions.

This enables Dandelion to securely execute compute functions in lightweight sandboxes that cold start in 100s of microseconds, since pure functions do not rely on software environments such as a guest OS. Dandelion makes it practical to boot sandboxes on-demand per request, decreasing performance variability by two to three orders of magnitude