P99 Conf: 3 Ways to Squash Application Latency

We’ve all been frustrated by latency, either as users of an application,  or as developers building such apps. At ScyllaDB‘s annual Pekka Enberg, founder and CTO of shared his favorite tips for spotting and removing latency from systems. “Latency lurks everywhere,” said Enberg, who also has authored a once estimated that it loses 1% of sales for every 100ms of latency. Screenshot Enberg has thought plenty about ways of reducing latency and has boiled down his solutions into three different approaches: Reduce data movement Continue reading

Microsoft Is First To Get HBM-Juiced AMD CPUs

Intel was the first of the major CPU makers to add HBM stacked DRAM memory to a CPU package, with the “Sapphire Rapids” Max Series Xeon 5 processors, but with the “Granite Rapids” Xeon 6, Intel abandoned the use of HBM memory in favor of what it would hope would be more main stream MCR DDR5 main memory, which has multiplexed ranks to boost bandwidth by nearly 2X over regular DDR5 memory. …

Microsoft Is First To Get HBM-Juiced AMD CPUs was written by Timothy Prickett Morgan at The Next Platform.

TNO009: From Network Monitoring to Observability: Make the Leap for Better NetOps

Traditional network monitoring was built around SNMP and logs. And while there’s still a role for these sources, network observability aims to incorporate more data to help you build a holistic picture of the network and its behavior and performance. These sources can include flows, streaming telemetry, APIs, NETCONF, the CLI, deep packet inspection, synthetic... Read more »

Dynamic BGP Peers

You might have an environment where a route reflector (or a route server) has dozens or hundreds of BGP peers. Configuring them by hand is a nightmare; you should either build a decent automation platform or use dynamic BGP neighbors – a feature you can practice in the next lab exercise.

Click here to start the lab in your browser using GitHub Codespaces (or set up your own lab infrastructure). After starting the lab environment, change the directory to session/9-dynamic and execute netlab up.

SC24 Over 10 Terabits per Second of WAN Traffic

The SC24 WAN Stress Test chart shows 10.3 Terabits bits per second of WAN traffic to the The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC24) conference held this week in Atlanta. The conference network used in the demonstration, SCinet, is described as the most powerful and advanced network on Earth, connecting the SC community to the world.

SC24 Real-time RoCEv2 traffic visibility describes a demonstration of wide area network bulk data transmission using RDMA over Converged Ethernet (RoCEv2) flows typically seen in AI/ML data centers. In the example, 3.2Tbits/second sustained trasmissions from sources geographically distributed around the United States was demonstrated.

SC24 Dropped packet visibility demonstration shows how the sFlow data model integrates three telemetry streams: counters, packet samples, and packet drop notifications. Each type of data is useful on its own, but together they provide the comprehensive network wide observability needed to drive automation. Real-time network visibility is particularly relevant to AI / ML data center networks where congestion and dropped packets can result in serious performance degradation and in this screen capture you can see multiple 400Gbits/s RoCEv2 flows.

SC24 SCinet traffic describes the architecture of the real-time monitoring system used to Continue reading

HPE GreenLake Platform Gets Expanded Storage And Custom KVM Hypervisor

When Fidelma Russo looks at Hewlett Packard Enterprise’s GreenLake, she sees a rapidly expanding platform that like others is trying to keep pace not only with the growing demands of organizations that are continuing to adopt the cloud but also are looking for ways to bring in and deploy emerging AI technologies. …

HPE GreenLake Platform Gets Expanded Storage And Custom KVM Hypervisor was written by Jeffrey Burt at The Next Platform.

TL008: How to Hire Top Performers

Hiring is never an easy process. On today’s show, guest Brian Hogan and host Laura Santamaria explore the intricacies of hiring top performers in the tech industry. Brian talks about how to set up a fair and structured interview process, including the use of rubrics to evaluate candidates consistently. He discusses the challenges of assessing... Read more »

N4N004: Essential Topics in Networking: Ethernet, NAT, and More

What are the most essential topics to understand for a new networkers? Ethan Banks and Holly Metlitzky address a listener’s question about foundational topics, covering what a network is, the differences between packet-switched and circuit-switched networks, and the nature of the internet as a “network of networks.” They discuss the importance of Internet Protocol (IP),... Read more »

Bigger and badder: how DDoS attack sizes have evolved over the last decade

Distributed Denial of Service (DDoS) attacks are cyberattacks that aim to overwhelm and disrupt online services, making them inaccessible to users. By leveraging a network of distributed devices, DDoS attacks flood the target system with excessive requests, consuming its bandwidth or exhausting compute resources to the point of failure. These attacks can be highly effective against unprotected sites and relatively inexpensive for attackers to launch. Despite being one of the oldest types of attacks, DDoS attacks remain a constant threat, often targeting well-known or high traffic websites, services, or critical infrastructure. Cloudflare has mitigated over 14.5 million DDoS attacks since the start of 2024 — an average of 2,200 DDoS attacks per hour. (Our DDoS Threat Report for Q3 2024 contains additional related statistics).

If we look at the metrics associated with large attacks mitigated in the last 10 years, does the graph show a steady increase in an exponential curve that keeps getting steeper, especially over the last few years, or is it closer to linear growth? We found that the growth is not linear, but rather is exponential, with the slope dependent on the metric we are looking at.

Why is this question interesting? Simple. The answer Continue reading

Resilient Internet connectivity in Europe mitigates impact from multiple cable cuts

When cable cuts occur, whether submarine or terrestrial, they often result in observable disruptions to Internet connectivity, knocking a network, city, or country offline. This is especially true when there is insufficient resilience or alternative paths — that is, when a cable is effectively a single point of failure. Associated observations of traffic loss resulting from these disruptions are frequently covered by Cloudflare Radar in social media and blog posts. However, two recent cable cuts that occurred in the Baltic Sea resulted in little-to-no observable impact to the affected countries, as we discuss below, in large part because of the significant redundancy and resilience of Internet infrastructure in Europe.

BCS East-West Interlink

Traffic volume indicators

On Sunday, November 17 2024, the BCS East-West Interlink submarine cable connecting Sventoji, Lithuania and Katthammarsvik, Sweden was reportedly damaged around 10:00 local (Lithuania) time (08:00 UTC). A Data Center Dynamics article about the cable cut quotes the CTO of Telia Lietuva, the telecommunications provider that operates the cable, and notes “The Lithuanian cable carried about a third of the nation's Internet capacity, but capacity was carried via other routes.”

As the Cloudflare Radar graphs below show, there was no apparent impact to Continue reading

SC24 Real-time RoCEv2 traffic visibility

The chart shows eight 400Gbits/s RDMA over Converged Ethernet (RoCEv2) flows, typically seen in AI / ML data centers, totaling 3.2 Tbits/s. The unique challenge in this case is that flows are being routed from locations scattered around the United States to Atlanta, the location of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC24) conference.
SC24 Network Research Exhibit: The Resiliant, Performant Networks and Distributed Processing demonstration aims to explore performance limitations and enablers for high volume bulk data tranfers. Maintaining stable 400Gbits/s RoCEv2 connections over a wide area network is challenging since the packets have to traverse multiple links, avoid contention on links, and deal with buffering associated with transmission latency that is orders of magnitude higher than data center environments where RoCEv2 is typically deployed (one way latency across the USA is a minimum of 16 milliseconds due to speed of light, but in practice the latency is quite a bit larger, on the other hand latency across a leaf and spine data center fabric is measured in microseconds).
During setup it was noticed that total throughput with 8 concurrent flows was only 2.7Tbits/s (instead of the 3Tbits/second plus expected). Examining a Continue reading

NAN079: From Network Monitoring to Observability: Make the Leap for Better NetOps

Traditional network monitoring was built around SNMP and logs. And while there’s still a role for these sources, network observability aims to incorporate more data to help you build a holistic picture of the network and its behavior and performance. These sources can include flows, streaming telemetry, APIs, NETCONF, the CLI, deep packet inspection, synthetic... Read more »
1 … 126 127 128 129 130 … 3,877