Stateless datacenter load-balancing with Beamer

Stateless datacenter load-balancing with Beamer Olteanu et al., NSDI’18

We’ve spent the last couple of days looking at datacenter network infrastructure, but we didn’t touch on the topic of load balancing. For a single TCP connection, you want all of the packets to end up at the same destination. Logically, a load balancer (a.k.a. ‘mux’) needs to keep some state somewhere to remember the mapping.

Existing load balancer solutions can load balance TCP and UDP traffic at datacenter scale at different price points. However, they all keep per-flow state; after a load balancer decides which server should handle a connection, that decision is “remembered” locally and used to handle future packets of the same connection. Keeping per-flow state should ensure that ongoing connections do not break when servers and muxes come or go…

There are two issues with keeping this state though. Firstly , it can sometimes end up incomplete or out of date (especially under periods of rapid network change, such as during scale out and scale in). Secondly, there’s only a finite amount of resource to back that state, which opens the door to denial of service attacks such as SYN flood attacks.

Beamer is Continue reading

OSPF LSA Types

Link-state advertisements (LSA) are used to communicates the router’s local routing topology to all other local routers in the same OSPF area. There are 11 types of LSAs although only the 6 most commonly used ones are described in this post.

Worth Reading: Automatically detecting peering infrastructure outages

Given the high concentration of interconnections, the uptime of peering infrastructures is crucial for overlay Internet applications. Facilities and IXPs strive to meet Service Level Agreements (SLAs) of ‘five nines’ (five minutes downtime per year), and ‘four nines’ (50 minutes downtime per year). However, outages still occur due to power failures, human errors, attacks, and natural disasters. —Vasileios Giotsas @APNIC

Don’t miss these Ansible Automation sessions at Red Hat Summit

RedHat-Summt-2018-Blog

The countdown is on! It’s just a few short days until Red Hat Summit. I’m Kaete Piccirilli and I do all things Ansible Marketing. While it’s not my first Summit at Red Hat, it’s the first one I’ll be attending, and I cannot be more excited to finally be in the mix of our customers, partners and open source communities.

Ansible Automation Breakout Sessions

Red Hat Summit has an action-packed few days planned, and I have picked a few Ansible Automation sessions that you won’t want to miss.

Managing 15,000 network devices with Ansible

Ansible allows network management across virtually any device platform. Any network device can be managed via SSH or an API. We took this cutting-edge network automation to scale with a customer’s global network infrastructure, giving them the ability to manage nearly all of their network devices at one time.

In this session, we'll discuss the architecture and strategies involved in network automation.

Manage Windows like Linux with Ansible

Few questions induce fear into the heart of a Linux admin more than, "Hey, can you manage these Windows servers?"

In this session, we'll show how Ansible does simple, secure, and agentless Windows management with the exact Continue reading

IDG Contributor Network: IT teams are drowning in data – throw them a lifeline

Today’s businesses thrive on Big Data insights — from sales reports and customer demographics, to business expenses and trend analysis. This explosion of data is multiplied by escalating social media, rich multimedia files and the Internet of Things (IoT). It’s no wonder that the growth of network data traffic continues to defy expectations, and IT support teams are struggling to keep up.But beyond simply being awash in the sheer volume of data traffic, a more complex challenge for enterprise IT is how to make the best use of network performance metadata to streamline workflows, enhance productivity and meet service level expectations, while optimizing the user experience. All too often, IT support teams are drowning in a sea of data, treading water without direction while the end user waits for resolution of their issue.To read this article in full, please click here

New to the INE Course Library: Infrastructure as Code in AWS With Terraform

This course will teach you how to use Terraform to provision your AWS infrastructure. It will guide you through setting up Terraform with your AWS account and take you through creating your first resource with Terraform in AWS.

 

About the Course:

This course is taught by Kevin Holditch and is 4 hours and 28 minutes long.

What You’ll Learn:

  • All of the resource types Terraform can create and how you can use variables to create more advanced infrastructure setups
  • How to group a set of resources into a reusable module allowing you to easily create common setups again and again

OSISoft: old-school process-control company on IoT cutting edge

While the eyes of the tech world are on the usual suspects like Google and IBM, as well as high-profile operational tech firms like GE and Siemens, an almost 40-year-old company called OSISoft has quietly leveraged its expertise in process monitoring and management into an impressive list of prominent clients. These include Aramco, the national oil and gas company of Saudi Arabia, which is arguably the single most valuable and profitable company in the world, Chevron, Pacific Gas and Electric, Heineken, Tyson Foods, and Lawrence Livermore National Labs, among many others.OSISoft has a lot more in common with the GEs of the world than with some of the IT-based powerhouses that are making a lot of noise about IoT these days. It’s a company with a long history of experience in real-time data collection, making the transition into an IoT-enabled world a smooth one.To read this article in full, please click here

1 … 1,622 1,623 1,624 1,625 1,626 … 3,841