AI summaryⓘ
The authors explain that the CAP theorem says a system must choose between consistency and availability when the network is split, but this depends on how the network handles message loss or delays. They introduce Open Atomic Ethernet (OAE), which changes network behavior by ensuring quick and two-way state checks called bisynchrony and using a special mesh design to avoid common network bottlenecks. This setup doesn't remove all network splits but greatly reduces how often and how long these splits affect applications by fixing network problems in nanoseconds. The authors connect their work to earlier theories like CAP, CAL, and PACELC to show how OAE changes the practical understanding of these tradeoffs.
CAP theoremconsistencyavailabilitynetwork partitionOpen Atomic Ethernetbisynchronyspanning treesoft partitionsCAL theoremPACELC
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 Atomic Ethernet (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. 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.