A Java library for Apache Mesos frameworks that provides extensible task scheduling with optimization plugins and cluster autoscaling.
Fenzo is a Java library for Apache Mesos frameworks that provides an extensible task scheduler with plugin-based optimization and cluster autoscaling capabilities. It helps frameworks match resources to tasks using various scheduling objectives like bin packing, resource affinity, and task locality. The library allows frameworks to balance scheduling speed with optimal task placement quality.
Developers building Apache Mesos frameworks who need advanced task scheduling, resource optimization, and cluster autoscaling capabilities.
Fenzo offers a flexible, plugin-based architecture that enables custom scheduling optimizations and autoscaling, distinguishing it from basic Mesos schedulers. Its ability to compose multiple constraints and support both hard and soft constraints provides fine-grained control over task placement.
Extensible Scheduler for Mesos Frameworks
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Enables custom constraints and fitness calculators, allowing frameworks to compose multiple plugins for complex objectives like bin packing and task affinity, as outlined in the README.
Facilitates cluster autoscaling based on resource demand with independent scaling per host group and per-job-group limits, helping optimize resource usage dynamically.
Supports both hard and soft constraints, providing fine-grained control over task placement to balance optimization and performance, as specified in the features.
Includes ready-to-use plugins for bin packing, host attributes, unique/balanced placement, and exclusive hosts, reducing development time for common scheduling needs.
Marked as archived on GitHub, meaning it is no longer maintained by Netflix, with no updates, bug fixes, or official support, posing risks for production use.
Designed solely for Apache Mesos frameworks, limiting its relevance in modern ecosystems dominated by Kubernetes and other orchestrators.
Requires Java development and deep integration with Mesos, which can be challenging for teams without distributed systems expertise or those using other languages.