Search arXivSearch

arXiv · 2601.12196

Understanding Partial Reachability in the Internet Core

Abstract

Routing strives to connect all the Internet, but compete: political pressure threatens routing fragmentation; architectural changes such as private clouds, carrier-grade NAT, and firewalls make connectivity conditional; and commercial disputes create partial reachability for days or years. This paper suggests *persistent, partial reachability is fundamental to the Internet* and an underexplored problem. We first *derive a conceptual definition of the Internet core* based on connectivity, not authority. We identify *peninsulas*: persistent, partial connectivity; and *islands*: when computers are partitioned from the Internet core. Second, we develop algorithms to observe each across the Internet, and apply them to two existing measurement systems: Trinocular, where 6 locations observe 5M networks frequently, and RIPE Atlas, where 13k locations scan the DNS roots frequently. Cross-validation shows our findings are stable over *three years of data*, and consistent with as few as 3 geographically-distributed observers. We validate peninsulas and islands against CAIDA Ark, showing good recall (0.94) and bounding precision between 0.42 and 0.82. Finally, our work has broad practical impact: we show that *peninsulas are more common than Internet outages*. Factoring out peninsulas and islands as noise can *improve existing measurement systems*; their ``noise'' is $5\times$ to $9.7\times$ larger than the operational events in RIPE's DNSmon. We show that most peninsula events are routing transients (45\%), but most peninsula-time (90\%) is due to a few (7\%) long-lived events. Our work helps inform Internet policy and governance, with our neutral definition showing no single country or organization can unilaterally control the Internet core.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Guillermo Baltra, Tarang Saluja, Yuri Pradkin, John Heidemann. 2026-01-22. Understanding Partial Reachability in the Internet Core. https://doi.org/10.4230/oasics.nines.2026.4

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

Semord: Learned Semantic-Preserving Placement and Low-Fanout Routing for Distributed Vector Search

Vector databases are increasingly deployed in distributed settings where different users, sites, or domains maintain vector data. Existing vector databases rely on a coordinator to record which shards store which parts of the vector space and to route each query to those shards. In a decentralized setting, peers may join, leave, or move data without a trusted node tracking every change, and outdated routing information can therefore send queries to the wrong peers or require contacting many peers, reducing vector retrieval recall and increasing network latency. We present Semord, a decentralized vector search overlay system that achieves high recall by routing each ANN query to a small set of relevant peers, without relying on a centralized coordinator. Semord addresses this problem by making semantic locality routable: 1) We propose VHash to place semantically related vectors near each other in the overlay key space while avoiding load imbalance, so that each query only needs to contact a small neighborhood of peers for distributed local ANN ranking. 2) We design VecDHT, a communication protocol that maintains decentralized routing, region metadata, churn resilience, and VHash updates under membership and workload changes. Our extensive experiments on a real testbed show that Semord improves recall by more than 15% and reduces contacted peers by over 60% compared with decentralized baselines. Semord also approaches the recall and latency of a centralized oracle baseline while reducing peak peer-local ANN index memory by more than 2X. Controlled large-scale simulations further show that Semord scales across real-world embedding workloads and remains robust under churn for scoped vector retrieval as a decentralized overlay.

cs.NI

Lizard: Bandwidth-Adaptive Real-Time Video Analytics through Content-Aware Packet Discarding at Last-Mile Edge Routers

The timeliness and accuracy of edge-based video analytics can be hindered by drastic reductions in available bandwidth (ABW) at last-mile edge routers, causing prolonged queuing delays. This work proposes Lizard, a system that leverages video-content-aware packet discarding to mitigate the negative effects of drastic ABW degradation that may frequently occur at a last-mile edge router by judiciously discarding packets that contain frame blocks less important to the analytics at the destination. To achieve this, we first devise a frame-block-aware RTP header extension to effectively decouple packet dependencies to encode frame blocks. Second, Lizard uses a priority-based feedback mechanism that dynamically evaluates packet priorities based on relative accuracy impacts. Third, we develop an adaptive phase-transition-based packet discarding strategy at the router to discard packets that represent unimportant blocks. Our evaluation of Lizard shows improvements over existing methods are substantial: 53.2% reduction in latency and 27.1% increase in analysis accuracy.

cs.NI

Flux: Optimal Scheduling of Optical Circuit Switches for LLM Training

Optical Circuit Switching (OCS) offers high bandwidth density and energy efficiency for LLM training, but incurs a non-negligible reconfiguration delay. Prior work typically schedules optical circuit switches independently of compute, using aggregate traffic demand to determine which circuits to provision and when. We argue that this separation creates a fundamental inefficiency: reconfigurations that ignore the compute timeline can stall communication, resulting in low circuit utilization and large buffer requirements. In this paper, we present Flux, a scheduler that optimally schedules optical circuit switches based on the structure of the entire workload. Flux remains effective across a wide range of switching speeds by reusing circuits and amortizing reconfiguration delay behind compute and communication. We show that Flux reduces training iteration time by up to $10\times$ and peak NIC buffer requirements by more than three orders of magnitude compared to traditional periodic schedulers.

cs.NI