Circumventing the CAP Theorem with Open Æthernet

Abstract

The CAP theorem is routinely treated as a systems law: under network partition, a replicated service must sacrifice either consistency or availability. The theorem is correct within its standard asynchronous network model, but operational practice depends on where partition-like phenomena become observable and on how lower layers discard or preserve semantic information about message fate. This paper argues that Open Æthernet (OAE) shifts the engineering regime in which CAP tradeoffs become application-visible by (i) replacing fire-and-forget link semantics with bounded-time bilateral reconciliation of endpoint state -- the property we call bisynchrony -- and (ii) avoiding Clos funnel points via an octavalent mesh in which each node can act as the root of a locally repaired spanning tree. The result is not the elimination of hard graph cuts, but a drastic reduction in the frequency and duration of application-visible "soft partitions" by detecting and healing dominant fabric faults within hundreds of nanoseconds, under the link-fault model and repair rule stated in the paper. We connect this view to Brewer's original CAP framing, the formalization by Gilbert and Lynch, the CAL theorem of Lee et al., which replaces binary partition tolerance with a quantitative measure of apparent latency, and Abadi's PACELC extension.

arXiv comment24 pages, 14 figures. v2: corrects graph-theoretic claims (Whitney inequality, disjoint spanning trees, 3x3 grid and 10x20 mesh bounds, chain-vs-grid ratio), restates the resilience theorem via edge-connectivity, adds a loop-free local-repair rule, states protocol assumptions; title now uses Open Æthernet