Experimenting TCP Congestion Control(WIP)

Introduction

I have always found TCP congestion control algorithms fascinating, and at the same time, I know very little about them. So once in a while, I will spend some time with the hope of gaining some new insights. This blog post will share some of my experiments with various TCP congestion control algorithms. We will start with TCP Reno, then look at Cubic and ends with BBR.I am using Linux network namespaces to emulate topology for experimentation, making it easier to run than setting up a physical test bed.

TCP Reno

For many years, the main algorithm of congestion control was TCP Reno. The goal of congestion control is to determine how much capacity is available in the network, so that source knows how many packets it can safely have in transit (Inflight). Once a source has these packets in transit, it uses the ACK’s arrival as a signal that packets are leaving the network, and therefore it’s safe to send more packets into the network. By using ACKs for pacing the transmission of packets, TCP is self-clocking. The number of packets which TCP can inject into the network is controlled by Congestion Window(cwnd).

Congestion Window:

Congestion Window(cwnd)

Continue reading

FCC urged to test for ‘dangerous’ interference from Wi-Fi 6E

The National Spectrum Management Association this week warned the Federal Communications Commission that Wi-Fi 6E could cause potentially dangerous interference in networks used by first responders, utilities and others if the FCC doesn’t perform“real-world testing on its automated frequency control systems.NSMA argued in an open letter to the commission that testing facilities are already available, specifically at the Idaho National Labs spectrum test bed, and that such studies should be peer-reviewed and transparent. [ Get regularly scheduled insights by signing up for Network World newsletters. ]To read this article in full, please click here

FCC urged to test for ‘dangerous’ interference from Wi-Fi 6E

The National Spectrum Management Association this week warned the Federal Communications Commission that Wi-Fi 6E could cause potentially dangerous interference in networks used by first responders, utilities and others if the FCC doesn’t perform“real-world testing on its automated frequency control systems.NSMA argued in an open letter to the commission that testing facilities are already available, specifically at the Idaho National Labs spectrum test bed, and that such studies should be peer-reviewed and transparent. [ Get regularly scheduled insights by signing up for Network World newsletters. ]To read this article in full, please click here

McLaren Racing relies on edge computing at Formula 1 tracks

“Twenty-two times a year, we build a data center right down at the edge,” said Ed Green, head of commercial technology at McLaren Racing, a British motor racing team based in Surrey, England.For McLaren, the edge is wherever in the world the company’s Formula 1 racing team is competing. An IT setup at each racing site links the entire team, including mechanics, engineers, crew members, and the drivers of McLaren’s two Formula 1 racecars. [Get regularly scheduled insights by signing up for Network World newsletters]To read this article in full, please click here

McLaren Racing relies on edge computing at Formula 1 tracks

“Twenty-two times a year, we build a data center right down at the edge,” said Ed Green, head of commercial technology at McLaren Racing, a British motor racing team based in Surrey, England.For McLaren, the edge is wherever in the world the company’s Formula 1 racing team is competing. An IT setup at each racing site links the entire team, including mechanics, engineers, crew members, and the drivers of McLaren’s two Formula 1 racecars. [Get regularly scheduled insights by signing up for Network World newsletters]To read this article in full, please click here

McLaren Racing relies on edge computing at Formula 1 tracks

“Twenty-two times a year, we build a data center right down at the edge,” said Ed Green, head of commercial technology at McLaren Racing, a British motor racing team based in Surrey, England.For McLaren, the edge is wherever in the world the company’s Formula 1 racing team is competing. An IT setup at each racing site links the entire team, including mechanics, engineers, crew members, and the drivers of McLaren’s two Formula 1 racecars. [Get regularly scheduled insights by signing up for Network World newsletters]To read this article in full, please click here

McLaren Racing relies on edge computing at Formula 1 tracks

“Twenty-two times a year, we build a data center right down at the edge,” said Ed Green, head of commercial technology at McLaren Racing, a British motor racing team based in Surrey, England.For McLaren, the edge is wherever in the world the company’s Formula 1 racing team is competing. An IT setup at each racing site links the entire team, including mechanics, engineers, crew members, and the drivers of McLaren’s two Formula 1 racecars. [Get regularly scheduled insights by signing up for Network World newsletters]To read this article in full, please click here

McLaren Racing relies on edge computing at the racetrack

“Twenty-two times a year, we build a data center right down at the edge,” said Ed Green, head of commercial technology at McLaren Racing, a British motor racing team based in Surrey, England.For McLaren, the edge is wherever in the world the company’s Formula 1 racing team is competing. An IT setup at each racing site links the entire team, including mechanics, engineers, crew members, and the drivers of McLaren’s two Formula 1 racecars. [Get regularly scheduled insights by signing up for Network World newsletters]To read this article in full, please click here

McLaren Racing relies on edge computing at the racetrack’s edge

“Twenty-two times a year, we build a data center right down at the edge,” said Ed Green, head of commercial technology at McLaren Racing, a British motor racing team based in Surrey, England.For McLaren, the edge is wherever in the world the company’s Formula 1 racing team is competing. An IT setup at each racing site links the entire team, including mechanics, engineers, crew members, and the drivers of McLaren’s two Formula 1 racecars. [ Get regularly scheduled insights by signing up for Network World newsletters. ]To read this article in full, please click here

McLaren Racing relies on edge computing at the racetrack’s edge

“Twenty-two times a year, we build a data center right down at the edge,” said Ed Green, head of commercial technology at McLaren Racing, a British motor racing team based in Surrey, England.For McLaren, the edge is wherever in the world the company’s Formula 1 racing team is competing. An IT setup at each racing site links the entire team, including mechanics, engineers, crew members, and the drivers of McLaren’s two Formula 1 racecars. [ Get regularly scheduled insights by signing up for Network World newsletters. ]To read this article in full, please click here

Hedge 145: Roundtable on Professional Liability

The software world is known for overdue projects, costs overrun, lots of defects, and lots of failure all the way around. Many other engineering fields have stricter requirements to take on projects and liability insurance driving correct practice and care. The networking world, and the larger IT world, however, has neither of these things. Does this make IT folks less likely to “do the right thing,” or is the self-regulation we have today enough? Join Tom Ammon, Eyvonne Sharp, and Russ White as they discuss the possibilities of professional liability in information technology.

download

Kubernetes Unpacked 008: Go – The Language Of Kubernetes

In this episode, Michael catches up with Josh Duffney, Cloud Developer Advocate at Microsoft to talk about Go (golang). Kubernetes, Docker, and Terraform are all written in Go. Josh and Michael talk about their journey into Kubernetes and Go, some fun projects to play with, how to learn Go, and why understanding certain programming languages is crucial for breaking into Kubernetes.

Kubernetes Unpacked 008: Go – The Language Of Kubernetes

In this episode, Michael catches up with Josh Duffney, Cloud Developer Advocate at Microsoft to talk about Go (golang). Kubernetes, Docker, and Terraform are all written in Go. Josh and Michael talk about their journey into Kubernetes and Go, some fun projects to play with, how to learn Go, and why understanding certain programming languages is crucial for breaking into Kubernetes.

The post Kubernetes Unpacked 008: Go – The Language Of Kubernetes appeared first on Packet Pushers.

US blocks sale of some Nvidia and AMD AI chips to China

The US government has banned AMD and Nvidia from exporting chips used to support artificial intelligence work to China.The ban affects Nvidia’s A100 chips, often deployed in data centers to speed up the training of machine learning models, and its forthcoming H100 chip, while AMD has also received new license requirements that will stop its MI250 advanced AI chip from being exported to China.In a filing with the SEC, Nvidia said: “The US government has imposed a new license requirement, effective immediately, for any future export to China (including Hong Kong) and Russia of the Company’s A100 and forthcoming H100 integrated circuit.”To read this article in full, please click here

US blocks sale of some Nvidia and AMD AI chips to China

The US government has banned AMD and Nvidia from exporting chips used to support artificial intelligence work to China.The ban affects Nvidia’s A100 chips, often deployed in data centers to speed up the training of machine learning models, and its forthcoming H100 chip, while AMD has also received new license requirements that will stop its MI250 advanced AI chip from being exported to China.In a filing with the SEC, Nvidia said: “The US government has imposed a new license requirement, effective immediately, for any future export to China (including Hong Kong) and Russia of the Company’s A100 and forthcoming H100 integrated circuit.”To read this article in full, please click here

US blocks sale of some Nvidia and AMD AI chips to China

The US government has banned AMD and Nvidia from exporting chips used to support artificial intelligence work to China.The ban affects Nvidia’s A100 chips, often deployed in data centers to speed up the training of machine learning models, and its forthcoming H100 chip, while AMD has also received new license requirements that will stop its MI250 advanced AI chip from being exported to China.In a filing with the SEC, Nvidia said: “The US government has imposed a new license requirement, effective immediately, for any future export to China (including Hong Kong) and Russia of the Company’s A100 and forthcoming H100 integrated circuit.”To read this article in full, please click here

1 … 445 446 447 448 449 … 3,841