AWS Direct Connect Technical Deep Dive (IX)

AWS Direct Connect Technical Deep Dive (IX)

In the previous posts, we looked at how to use a site‑to‑site VPN to connect your on‑premises network to AWS, and as we saw, it is very easy to set up. So what’s the fuss about Direct Connect (DX), and why would we need one?

To give you a one‑word answer, a VPN connects through the Internet. As you would expect, that comes with some limitations. Latency can be high, and the throughput is capped at around 1.25 Gb/s (per tunnel). So what if we need something more resilient and with much higher throughput?

AWS Site-to-Site VPN
Ideally, we want to securely connect to all of our instances using their private IP addresses, just as if they were in our own data centre. This is where the AWS Site-to-Site VPN comes in.
AWS Direct Connect Technical Deep Dive (IX)

That is where AWS Direct Connect comes in. As the name suggests, it is a Dedicated Direct Connection (DX Connection) to AWS, giving you a dedicated network link with better performance and reliability compared to a traditional VPN over the Internet.

As always, if you find this post helpful, press the ‘clap’ button. It means a lot to me and helps Continue reading

Partnering with OpenAI to bring their new open models onto Cloudflare Workers AI

OpenAI has just announced their latest open-weight models — and we are excited to share that we are working with them as a Day 0 launch partner to make these models available in Cloudflare's Workers AI. Cloudflare developers can now access OpenAI's first open model, leveraging these powerful new capabilities on our platform. The new models are available starting today at @cf/openai/gpt-oss-120b and @cf/openai/gpt-oss-20b.

Workers AI has always been a champion for open models and we’re thrilled to bring OpenAI's new open models to our platform today. Developers who want transparency, customizability, and deployment flexibility can rely on Workers AI as a place to deliver AI services. Enterprises that need the ability to run open models to ensure complete data security and privacy can also deploy with Workers AI. We are excited to join OpenAI in fulfilling their mission of making the benefits of AI broadly accessible to builders of any size.

The technical model specs

The OpenAI models have been released in two sizes: a 120 billion parameter model and a 20 billion parameter model. Both of them are Mixture-of-Experts models – a popular architecture for recent model releases – that allow relevant experts to be called for a Continue reading

How 1&1 Mail & Media Scaled Kubernetes Networking with eBPF and Calico

“We started in 2017 with Calico and never regretted it!”
—Stefan Fudeus, Product Owner/Lead Architect, 1&1 Mail & Media

Challenge

1&1 Mail & Media, part of the IONOS group, powers popular European internet brands including GMX and Web.de, serving more than 50% of Germany’s population with critical identity and email infrastructure. With roughly 45 to 50 million users, network reliability is non-negotiable. Any downtime could affect millions.

By 2022, the company had containerized 80% of its workloads on Kubernetes across three self-managed data centers. While the platform, backed by bare metal nodes and custom network layers, was highly scalable, network throughput bottlenecks began to emerge. Pods were limited to 2.5 Gbps of bandwidth due to IP encapsulation overhead, despite 10 Gbps network interfaces.

The team needed a solution that:

  • Improved pod-to-pod network performance
  • Maintained strong network policy isolation across up to 40 tenants per cluster
  • Scaled to millions of network connections and 1.4 million HTTP requests per second

Solution

1&1 Mail & Media had adopted Calico back in 2017, largely for its unique Kubernetes NetworkPolicy standard support. As their Kubernetes platform evolved, with clusters scaling to 300 bare metal nodes, 16,000 pods, and over 4 million Continue reading

IBM Outlines Steps To Verify Claims Of Quantum Advantage

D-Wave executives stirred up some controversy earlier this year when they claimed a smaller version of its Advantage 2 annealing quantum system, armed with 1,200 qubits, had reached “quantum supremacy,” – or “quantum advantage” – that significant but ill-defined time when a quantum system is able to solve a problem in much less time, at a lower cost, or more efficiently than the most powerful classical supercomputer.

IBM Outlines Steps To Verify Claims Of Quantum Advantage was written by Jeffrey Burt at The Next Platform.

Reducing double spend latency from 40 ms to < 1 ms on privacy proxy

One of Cloudflare’s big focus areas is making the Internet faster for end users. Part of the way we do that is by looking at the "big rocks" or bottlenecks that might be slowing things down — particularly processes on the critical path. When we recently turned our attention to our privacy proxy product, we found a big opportunity for improvement.

What is our privacy proxy product? These proxies let users browse the web without exposing their personal information to the websites they’re visiting. Cloudflare runs infrastructure for privacy proxies like Apple’s Private Relay and Microsoft’s Edge Secure Network.

Like any secure infrastructure, we make sure that users authenticate to these privacy proxies before we open up a connection to the website they’re visiting. In order to do this in a privacy-preserving way (so that Cloudflare collects the least possible information about end-users) we use an open Internet standard – Privacy Pass – to issue tokens that authenticate to our proxy service.

Every time a user visits a website via our Privacy Proxy, we check the validity of the Privacy Pass token which is included in the Proxy-Authorization header in their request. Before we cryptographically validate a user's token, we check Continue reading

Perplexity is using stealth, undeclared crawlers to evade website no-crawl directives

We are observing stealth crawling behavior from Perplexity, an AI-powered answer engine. Although Perplexity initially crawls from their declared user agent, when they are presented with a network block, they appear to obscure their crawling identity in an attempt to circumvent the website’s preferences. We see continued evidence that Perplexity is repeatedly modifying their user agent and changing their source ASNs to hide their crawling activity, as well as ignoring — or sometimes failing to even fetch — robots.txt files.

The Internet as we have known it for the past three decades is rapidly changing, but one thing remains constant: it is built on trust. There are clear preferences that crawlers should be transparent, serve a clear purpose, perform a specific activity, and, most importantly, follow website directives and preferences. Based on Perplexity’s observed behavior, which is incompatible with those preferences, we have de-listed them as a verified bot and added heuristics to our managed rules that block this stealth crawling.

How we tested

We received complaints from customers who had both disallowed Perplexity crawling activity in their robots.txt files and also created WAF rules to specifically block both of Perplexity’s declared crawlers: PerplexityBot and Perplexity-User. Continue reading

Vulnerability disclosure on SSL for SaaS v1 (Managed CNAME)

Earlier this year, a group of external researchers identified and reported a vulnerability in Cloudflare’s SSL for SaaS v1 (Managed CNAME) product offering through Cloudflare’s bug bounty program. We officially deprecated SSL for SaaS v1 in 2021; however, some customers received extensions for extenuating circumstances that prevented them from migrating to SSL for SaaS v2 (Cloudflare for SaaS). We have continually worked with the remaining customers to migrate them onto Cloudflare for SaaS over the past four years and have successfully migrated the vast majority of these customers. For most of our customers, there is no action required; for the very small number of SaaS v1 customers, we will be actively working to help migrate you to SSL for SaaS v2 (Cloudflare for SaaS).

Background on SSL for SaaS v1 at Cloudflare

Back in 2017, Cloudflare announced SSL for SaaS, a product that allows SaaS providers to extend the benefits of Cloudflare security and performance to their end customers. Using a “Managed CNAME” configuration, providers could bring their customer’s domain onto Cloudflare. In the first version of SSL for SaaS (v1), the traffic for Custom Hostnames is proxied to the origin based on the IP addresses assigned to the Continue reading

For Financial Services Firms, AI Inference Is As Challenging As Training

A decade ago, when traditional machine learning techniques were first being commercialized, training was incredibly hard and expensive, but because models were relatively small, inference – running new data through a model to cause an application to act or react – was easy.

For Financial Services Firms, AI Inference Is As Challenging As Training was written by Timothy Prickett Morgan at The Next Platform.

IEPG at IETF 123

he IEPG meeting is held each Sunday at the start of the IETF week. There is no particular theme for these sessions, although subjects of operational relevance are encouraged (www.iepg.org). These are my impressions of the presentations that were made at this IEPG meeting att the start of IETF 123.

Top 5 Kubernetes Network Issues You Can Catch Early with Calico Whisker

Kubernetes networking is deceptively simple on the surface, until it breaks, silently leaks data, or opens the door to a full-cluster compromise. As modern workloads become more distributed and ephemeral, traditional logging and metrics just can’t keep up with the complexity of cloud-native traffic flows.

That’s where Calico Whisker comes in. Whisker is a lightweight Kubernetes-native observability tool created by Tigera. It offers deep insights into real-time traffic flow patterns, without requiring you to deploy heavyweight service meshes or packet sniffer. And here’s something you won’t get anywhere else: Whisker is data plane-agnostic. Whether you run Calico eBPF data plane, nftables, or iptables, you’ll get the same high-fidelity flow logs with consistent fields, format, and visibility. You don’t have to change your data plane, Whisker fits right in and shows you the truth, everywhere.

Let’s walk through 5 network issues Whisker helps you catch early, before they turn into outages or security incidents.

1. Policy Misconfigurations

Traditional observability tools often show whether a packet was forwarded, accepted or dropped, but not why. They lack visibility into which Kubernetes network policy was responsible or if one was even applied.

With Whisker, each network flow is paired with:

Mythbusting IPv6: Why Adoption Lags and What Will Change It

IPv6 was developed in the late 1990s as a successor to IPv4 to address the internet’s rapid growth and prevent IPv4 address exhaustion. The original vision was that, after a period of dual-stack operation, IPv4 would be phased out. Over 25 years later, full-scale depletion of IPv4 addresses is imminent, yet IPv6 adoption remains slow — currently only about 30% worldwide, with the same proportion of Alexa Top 1,000 websites reachable via IPv6. The timeline for a full transition remains uncertain. Understanding IP Addresses: The Internet’s Postal System Before diving into the complexities of IPv6 adoption, it’s essential to understand what these protocols actually do. Think of IP addresses as the internet’s equivalent of postal addresses — they tell data packets where to go across the vast network of interconnected computers that make up the internet. IPv4 vs. IPv6 address space: A scale comparison The scale difference is staggering.

Cisco’s Outshift Incubator Sends Agentic AI Protocol To The Linux Foundation

AI agents bring with them the promise of being able to autonomously solve complex tasks put before them, from finding and analyzing the necessary data, choosing tools, and making decisions without human intervention to learning from their mistakes and adapting to changes.

Cisco’s Outshift Incubator Sends Agentic AI Protocol To The Linux Foundation was written by Jeffrey Burt at The Next Platform.

Linux packet sampling using eBPF

Linux 6.11+ kernels provide TCX attachment points for eBPF programs to efficiently examine packets as they ingress and egress the host. The latest version of the open source Host sFlow agent includes support for TCX packet sampling to stream industry standard sFlow telemetry to a central collector for network wide visibility, e.g. Deploy real-time network dashboards using Docker compose describes how to quickly set up a Prometheus database and use Grafana to build network dashboards.

static __always_inline void sample_packet(struct __sk_buff *skb, __u8 direction) {
    __u32 key = skb->ifindex;
    __u32 *rate = bpf_map_lookup_elem(&sampling, &key);
    if (!rate || (*rate > 0 && bpf_get_prandom_u32() % *rate != 0))
        return;

    struct packet_event_t pkt = {};
    pkt.timestamp = bpf_ktime_get_ns();
    pkt.ifindex = skb->ifindex;
    pkt.sampling_rate = *rate;
    pkt.ingress_ifindex = skb->ingress_ifindex;
    pkt.routed_ifindex = direction ? 0 : get_route(skb);
    pkt.pkt_len = skb->len;
    pkt.direction = direction;

    __u32 hdr_len = skb->len < MAX_PKT_HDR_LEN ? skb->len : MAX_PKT_HDR_LEN;
    if (hdr_len > 0 && bpf_skb_load_bytes(skb, 0, pkt.hdr, hdr_len) < 0)
        return;
    bpf_perf_event_output(skb, &events, BPF_F_CURRENT_CPU, &pkt, sizeof(pkt));
}

SEC("tcx/ingress")
int tcx_ingress(struct __sk_buff *skb) {
    sample_packet(skb, 0);

    return TCX_NEXT;
}

SEC("tcx/egress")
int tcx_egress(struct __sk_buff *skb) {
    sample_packet(skb, 1);

    return TCX_NEXT;
}

The sample.bpf.c file Continue reading

1 2 3 3,798