Ultra Ethernet: Address Vector (AV)

 Address Vector (AV)

The Address Vector (AV) is a provider-managed mapping that connects remote fabric addresses to compact integer handles (fi_addr_t) used in communication operations. Unlike a routing table, the AV does not store IP (device mappings). Instead, it converts an opaque Fabric Address (FA)—which may contain IP, port, and transport-specific identifiers—into a simple handle that endpoints can use for sending and receiving messages. The application never needs to reference the raw IP addresses directly.

Phase 1: Application – Request & Definition

The application begins by requesting an Address Vector (AV) through the fi_av_open() call. To do this, it first defines the desired AV properties in a fi_av_attr structure:

int fi_av_open(struct fid_domain *domain, struct fi_av_attr *attr, struct fid_av **av, void *context);

struct fi_av_attr av_attr = {

    .type        = FI_AV_TABLE,   

    .count       = 16,            

    .rx_ctx_bits = 0,          

    .ep_per_node = 1,          

    .name        = "my_av",    

    .map_addr    = NULL,       

    .flags       = 0           

};

Example 4-1: structure Continue reading

TCG059: From Source of Truth to Knowledge Graph – Rethinking Network Data

Network automation has a data problem. Traditional tools may hit limitations when managing complex infrastructure relationships. We explore how OpsMill’s InfraHub uses graph databases and temporal versioning to create what our guest calls “the knowledge graph of infrastructure” – enabling true version control at the database level while maintaining the flexibility to model anything from... Read more »

EVPN Designs: Multi-Pod Fabrics

In the EVPN Designs: Layer-3 Inter-AS Option A, I described the simplest multi-site design in which the WAN edge routers exchange IP routes in individual VRFs, resulting in two isolated layer-2 fabrics connected with a layer-3 link.

Today, let’s explore a design that will excite the True Believers in end-to-end layer-2 networks: two EVPN fabrics connected with an EBGP session to form a unified, larger EVPN fabric. We’ll use the same “physical” topology as the previous example; the only modification is that the WA-WB link is now part of the underlay IP network.

Read more …

Get Your Money For Nothing, Chips Definitely Not For Free

What’s the difference between Meta Platforms and OpenAI? The big one – and perhaps the most important one in the long run – is that when Meta Platforms does a deal with neocloud CoreWeave, it actually has a revenue stream from its advertising on various Web properties that it can pump back into AI investments while OpenAI is still burning money much faster than it is making it. …

Get Your Money For Nothing, Chips Definitely Not For Free was written by Timothy Prickett Morgan at The Next Platform.

Payload on Workers: a full-fledged CMS, running entirely on Cloudflare’s stack

Tucked behind the administrator login screen of countless websites is one of the Internet’s unsung heroes: the Content Management System (CMS). This seemingly basic piece of software is used to draft and publish blog posts, organize media assets, manage user profiles, and perform countless other tasks across a dizzying array of use cases. One standout in this category is a vibrant open-source project called Payload, which has over 35,000 stars on GitHub and has generated so much community excitement that it was recently acquired by Figma.

Today we’re excited to showcase a new template from the Payload team, which makes it possible to deploy a full-fledged CMS to Cloudflare’s platform in a single click: just click the Deploy to Cloudflare button to generate a fully-configured Payload instance, complete with bindings to Cloudflare D1 and R2. Below we’ll dig into the technical work that enables this, some of the opportunities it unlocks, and how we’re using Payload to help power Cloudflare TV. But first, a look at why hosting a CMS on Workers is such a game changer.

Behind the scenes: Cloudflare TV’s Payload instance

Serverless by design

Most CMSs are designed to be hosted on a conventional server that runs Continue reading

Ultra Ethernet: Completion Queue

Completion Queue Creation (fi_cq_open)


Phase 1: Application – Request & Definition


The purpose of this phase is to define the queue where operation completions will be reported. Completion queues are used to report the completion of operations submitted to endpoints, such as data transfers, RMA accesses, or remote write requests. By preparing a struct fi_cq_attr, the application describes exactly what it needs, so the provider can allocate a CQ that meets its requirements.


Example API Call:

struct fi_cq_attr cq_attr = {

    .size = 2048,

    .format = FI_CQ_FORMAT_DATA,

    .wait_obj = FI_WAIT_FD,

    .flags = FI_WRITE | FI_REMOTE_WRITE | FI_RMA,

    .data_size = 64

};


struct fid_cq *cq;

int ret = fi_cq_open(domain, &cq_attr, &cq, NULL);


Explanation of fields:

.size = 2048:  The CQ can hold up to 2048 completions. This determines how many completed operations can be buffered before the application consumes them.

.format = FI_CQ_FORMAT_DATA: This setting determines the level of detail included in each completion entry. With FI_CQ_FORMAT_DATA, the CQ entries contain information about the operation, such as the buffer pointer, the length of data, and optional completion data. If the application uses tagged messaging, choosing FI_CQ_FORMAT_TAGGED expands the entries to Continue reading

Nationwide Internet shutdown in Afghanistan extends localized disruptions

Just after 11:30 UTC (16:00 local time) on Monday, September 29, 2025, subscribers of wired Internet providers in Afghanistan experienced a brief service interruption, lasting until just before 12:00 UTC (16:30 local time). Cloudflare traffic data for AS38472 (Afghan Wireless) and AS131284 (Etisalat) shows that traffic from these mobile providers remained available during that period.

However, just after 12:30 UTC (17:00 local time), the Internet was completely shut down, with Afghani news outlet TOLOnews initially reporting in a post on X that “Sources have confirmed to TOLOnews that today (Monday), afternoon, fiber-optic Internet will be shut down across the country.” This shutdown is likely an extension of the regional shutdowns of fiber optic connections that took place earlier in September, and it will reportedly remain in force “until further notice”. (The earlier regional shutdowns are discussed in more detail below.)

While Monday’s first shutdown was only partial, with mobile connectivity apparently remaining available, the graphs below show that the second event took the country completely offline, with web and DNS traffic dropping to zero at a national level, as seen in the graphs below.

While the shutdown will impact subscribers to fixed and mobile Internet Continue reading

Ultra Ethernet: Event Queue

Event Queue Creation (fi_eq_open)


Phase 1: Application – Request & Definition


The purpose of this phase is to specify the type, size, and capabilities of the Event Queue (EQ) your application needs. Event queues are used to report events associated with control operations. They can be linked to memory registration, address vectors, connection management, and fabric- or domain-level events. Reported events are either associated with a requested operation or affiliated with a call that registers for specific types of events, such as listening for connection requests. By preparing a struct fi_eq_attr, the application describes exactly what it needs so the provider can allocate the EQ properly.

In addition to basic properties like .size (number of events the queue can hold) and .wait_obj (how the application waits for events), the .flags field can request specific EQ capabilities. Common flags include:


  • FI_WRITE: Requests support for user-inserted events via fi_eq_write(). If this flag is set, the provider must allow the application to invoke fi_eq_write().
  • FI_REMOTE_WRITE: Requests support for remote write completions being reported to this EQ.
  • FI_RMA: Requests support for Remote Memory Access events (e.g., RMA completions) to be delivered to this EQ.

Flags are encoded as a bitmask, so multiple Continue reading

Changing the Layout of netlab Topology Graphs

After I published the updated netlab topology graphs article, Samuel K. Lam quickly made a comment along the lines of now we know how the graph representing the following topology was made, adding a nice ASCII art that illustrated the point I was trying to make much better than my graphs:

ASCII art representing the BGP leak lab

ASCII art representing the BGP leak lab

Let’s see how close we can get to that ideal topology diagram with GraphViz and D2 graphs.

Read more …

Geolocation and Starlink

"Where are you?" is not an easy question to answer on the Internet. The Internet did not adopt a geographic address plan which means that you are going to need a lot of additional information if you want to map an IP address into a location at the level of a country or a city. But what can you do about a satellite service that Provides Internet access for ships at sea aircraft flying international routes?

NB545: CISA Orders Immediate Patch of Cisco Vulnerabilities; Firewall Upgrade Blocks Emergency Calls

There’s an abundance of vulnerabilities in this week’s Network Break. We start with a red alert on a cluster of Cisco vulnerabilities in its firewall and threat defense products. On the news front, the vulnerability spotlight stays on Cisco as the US Cybersecurity and Infrastructure Security Agency (CISA) issues an emergency directive to all federal... Read more »

15 years of helping build a better Internet: a look back at Birthday Week 2025

Cloudflare launched fifteen years ago with a mission to help build a better Internet. Over that time the Internet has changed and so has what it needs from teams like ours.  In this year’s Founder’s Letter, Matthew and Michelle discussed the role we have played in the evolution of the Internet, from helping encryption grow from 10% to 95% of Internet traffic to more recent challenges like how people consume content. 

We spend Birthday Week every year releasing the products and capabilities we believe the Internet needs at this moment and around the corner. Previous Birthday Weeks saw the launch of IPv6 gateway in 2011,  Universal SSL in 2014, Cloudflare Workers and unmetered DDoS protection in 2017, Cloudflare Radar in 2020, R2 Object Storage with zero egress fees in 2021,  post-quantum upgrades for Cloudflare Tunnel in 2022, Workers AI and Encrypted Client Hello in 2023. And those are just a sample of the launches.

This year’s themes focused on helping prepare the Internet for a new model of monetization that encourages great content to be published, fostering more opportunities to build community both inside and outside of Cloudflare, and evergreen missions like making more features available to Continue reading

MythWorx Mashes Up Neuromorphic And GenAI To Take On Model Giants

There is constant chatter surrounding the promise of generative AI, agentic AI, and – eventually – artificial general intelligence, but the need for the massive, expensive, high-density compute and the datacenters to wrap around them and the juice to feed them are incredible, particularly with models OpenAI GPT-4, Alibaba’s Qwen-3, Moonshot AI’s Kimi K2, xAI’s Grok4, and Amazon’s Olympus all cresting the trillion-parameter mark and aiming higher. …

MythWorx Mashes Up Neuromorphic And GenAI To Take On Model Giants was written by Jeffrey Burt at The Next Platform.

1 … 13 14 15 16 17 … 3,831