Meta just open-sourced the placement engine behind its fleet. rebalancer, in production for nine…
meta just open-sourced the placement engine behind its fleet. rebalancer, in production for nine years, solves about 40 million assignment problems a day and is now pip-installable under apache 2.0.
the boring scheduler turned out to be the real moat.
Context
Engineering at Meta's post of September 21, 2026 says Meta is open-sourcing Rebalancer, the assignment-problem solver it has used for over nine years to solve resource allocation problems. It lists uses including assigning shards to servers (Shard Manager), servers to services (RAS) and routing traffic from edge datacenters. The post says Rebalancer is released under Apache 2.0, and the GitHub README says it installs with pip install rebalancer.
The post says Rebalancer separates how a problem is specified, stored, solved and debugged, and describes a local search solver that works on an expression graph. Meta's OSDI 2024 paper on resource allocation in hyperscale datacenters is the related academic description.
The nine years in production, the Apache 2.0 license and the pip install match the sources. The note's 'placement engine behind its fleet' is a loose summary of several uses, which the post lists as a range of infrastructure optimization problems.
The note says Rebalancer solves about 40 million assignment problems a day. That figure was not found in the post or the README read here, so it is unsupported here, not refuted.
'The boring scheduler turned out to be the real moat' is the author's opinion. The post presents the release as open source and invites contributions, so the project's value to Meta as a moat is not addressed by the sources.
Related work
- Open-Sourcing Rebalancer: A Generic, High-Performance Library for Solving Assignment Problems (Engineering at Meta, September 21, 2026) ↗Primary source for the nine years, the uses, the design and the Apache 2.0 license.
- facebook/rebalancer (GitHub) ↗Source for the license and the pip install command.
- Optimizing Resource Allocation in Hyperscale Datacenters (USENIX OSDI 2024) ↗Meta's paper on resource allocation; surfaced in search and not read in full here.
Watch next
- Find the source of the daily problem count. Compare Rebalancer with open solvers such as HiGHS on a shard assignment problem.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 9 October 2026 at 01:47 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →