A Workers optimization that reduces your bill

A Workers optimization
that reduces your bill
A Workers optimization
that reduces your bill

Recently, we made an optimization to the Cloudflare Workers runtime which reduces the amount of time Workers need to spend in memory. We're passing the savings on to you for all your Unbound Workers.

Background

Workers are often used to implement HTTP proxies, where JavaScript is used to rewrite an HTTP request before sending it on to an origin server, and then to rewrite the response before sending it back to the client. You can implement any kind of rewrite in a Worker, including both rewriting headers and bodies.

Many Workers, though, do not actually modify the response body, but instead simply allow the bytes to pass through from the origin to the client. In this case, the Worker's application code has finished executing as soon as the response headers are sent, before the body bytes have passed through. Historically, the Worker was nevertheless considered to be "in use" until the response body had fully finished streaming.

For billing purposes, under the Workers Unbound pricing model, we charge duration-memory (gigabyte-seconds) for the time in which the Worker is in use.

The change

On December 15-16, we made a change to the way we handle requests that are streaming through the Continue reading

Video: Local Area Network Addressing

In the Local Area Network Addressing video (part of How Networks Really Work webinar) I covered numerous obscure LAN addressing details including:

  • There’s no layer-2 address in Fibre Channel frames (because FC is routing not bridging);
  • Why is the multicast bit the lowest bit (0x01) in the first byte on Ethernet but the highest bit (0x80) on Token Ring or FDDI;
  • How some NIC manufacturers never got the memo on what OUI really means.
You need Free ipSpace.net Subscription to watch the video, and the Standard ipSpace.net Subscription to register for upcoming live sessions.

Video: Local Area Network Addressing

In the Local Area Network Addressing video (part of How Networks Really Work webinar) I covered numerous obscure LAN addressing details including:

  • There’s no layer-2 address in Fibre Channel frames (because FC is routing not bridging);
  • Why is the multicast bit lowest bit (0x01) in first byte on Ethernet but highest bit (0x80) on Token Ring or FDDI;
  • How some NIC manufacturers never got the memo on what OUI really means.
You need Free ipSpace.net Subscription to watch the video, and the Standard ipSpace.net Subscription to register for upcoming live sessions.

The Money Printing Press That Is Chip Maker TSMC

Not every manufacturing node comes out perfectly and not every one comes out on time, but in the past decade and a half, Taiwan Semiconductor Manufacturing Co, the world’s largest and most technologically advanced etcher of chips in the world, has done far better than any of its few remaining peers to push the chip manufacturing envelope while also maintaining consistent and profitable production of older nodes.

The Money Printing Press That Is Chip Maker TSMC was written by Timothy Prickett Morgan at The Next Platform.

Hedge 114: Hardware Hacking 101 with Federico Lucifredi

Hardware hacking isn’t a topic most network engineers are familiar with—but we always used to say that if I can get access to the console of a router, I can eventually get into the box. The same is largely true of all kinds of computing hardware, including laptops, compute nodes connected to a data center fabric, and, again, routers and switches. In this episode of the Hedge, Federico Lucifredi joins Tom Ammon and Russ White to discuss the many options hardware hackers have today.

download

IPv6 Buzz 092: Listener Questions – NAT66, Stable IPv6 Prefix Delegation And More!

In the latest episode of IPv6 Buzz, we tackle the first listener questions of the year (well, really left over from the end of 2021 but still good ones!). Those questions cover topics including Unique Local Addressing (ULA) and SD-WAN, NAT66, IPv6 prefix delegation, and more.

The post IPv6 Buzz 092: Listener Questions – NAT66, Stable IPv6 Prefix Delegation And More! appeared first on Packet Pushers.

Cisco ASR 9000 Series Routers

Cisco already supports industry standard sFlow telemetry across a range of products and the recent IOS-XR Release 7.5.1 extends support to Cisco ASR 9000 Series Routers.

Note: The ASR 9000 series routers also support Cisco Netflow. Rapidly detecting large flows, sFlow vs. NetFlow/IPFIX describes why you should choose sFlow if you are interested in real-time monitoring and control applications.

The following commands configure an ASR 9000 series router to sample packets at 1-in-20,000 and stream telemetry to an sFlow analyzer (192.127.0.1) on UDP port 6343.

flow exporter-map SF-EXP-MAP-1
version sflow v5
!
packet-length 1468
transport udp 6343
source GigabitEthernet0/0/0/1
destination 192.127.0.1
dfbit set
!

Configure the sFlow analyzer address in an exporter-map.

flow monitor-map SF-MON-MAP
record sflow
sflow options
extended-router
extended-gateway
if-counters polling-interval 300
input ifindex physical
output ifindex physical
!
exporter SF-EXP-MAP-1
!

Configure sFlow options in a monitor-map.

sampler-map SF-SAMP-MAP
random 1 out-of 20000
!

Define the sampling rate in a sampler-map.

interface GigabitEthernet0/0/0/3
flow datalinkframesection monitor-map SF-MON-MAP sampler SF-SAMP-MAP ingress

Enable sFlow on each interface for complete visibilty into network traffic.

The diagram shows the general architecture of an sFlow monitoring deployment. All the switches stream sFlow telemetry to a central sFlow analyzer for network Continue reading

Explicit Null in Segment Routing

MPLS is such a user-friendly technology it needs a special label that does nothing.

Why explicit null

Normally, the penultimate router in the LSP removes (pops) the top transport label, so that the egress LSR will deal either with the …

Worst Topics To Discuss At A Dinner Party

The holiday season is near. This means you will have to attend dinner parties. And, of course, conversations are the best way to have fun at most events.

When you interact with people at a dinner party, you can talk about various things. For example, you may want to discuss your hobbies, interests, and much more. 

However, there are some topics that you should avoid. Here are the worst topics to discuss at a dinner party.

  1. Controversial Jokes

During dinner parties, you are not banned from making jokes. However, you should avoid controversial topics at all costs. Humor is harmless and good only if it’s not very sarcastic.

Besides that, you may decide to joke about another person that is not at the event. Well, we suggest you do not. That is because the individual you’re talking to may know that person. Additionally, it is not good etiquette to talk behind someone’s back.

  1. Encouraging Someone To Eat Or Drink

Yes, we understand that at a dinner party eating is mainly the point. But of course, you should never tell someone to eat more. This is, of course, unless you’re the host. 

A person may have eaten less as Continue reading

How the Internet Really Works Part 2

I’m a little late in posting this, but I thought I’d put it out here anyway. Tomorrow I’m teaching through a three-hour webinar, How the Internet Really Works part 2. From the session description—

This training will provide short reviews of many of these systems and a deeper look at the many tools network engineers can use to discover the information they need to navigate through the DNS and routing systems on the global Internet. This training will be arranged as a set of case studies posing a problem, and then working through tools available to gather the information needed to understand the problem.

You can register here.

Nvidia acquires Bright Computing

Remember when Nvidia was a gaming-card vendor? That doesn’t seem all that long ago but now it’s a full-blown enterprise high-performance computing and AI company that happens to sell videogame cards - if you can actually find them.Its latest move is the acquisition of Bright Computing, a maker of Bright Cluster Manager software that controls the configuration of clustered HPC systems, including Nvidia’s own DGX servers and HGX systems made by OEMs and ODMs, plus clusters from other manufacturers. The clusters of servers are linked by high-speed networks into a single unit.[Get regularly scheduled insights by signing up for Network World newsletters.] If the deal goes through, Bright Cluster Manager will become a part of Nvidia’s Enterprise Products Group. Nvidia has no intention of keeping Bright Cluster Manager for itself, and by being a part of the Nvidia channel, it gives Bright an opportunity to expand and grow its market.To read this article in full, please click here

Nvidia acquires Bright Computing

Remember when Nvidia was a gaming-card vendor? That doesn’t seem all that long ago but now it’s a full-blown enterprise high-performance computing and AI company that happens to sell videogame cards - if you can actually find them.Its latest move is the acquisition of Bright Computing, a maker of Bright Cluster Manager software that controls the configuration of clustered HPC systems, including Nvidia’s own DGX servers and HGX systems made by OEMs and ODMs, plus clusters from other manufacturers. The clusters of servers are linked by high-speed networks into a single unit.[Get regularly scheduled insights by signing up for Network World newsletters.] If the deal goes through, Bright Cluster Manager will become a part of Nvidia’s Enterprise Products Group. Nvidia has no intention of keeping Bright Cluster Manager for itself, and by being a part of the Nvidia channel, it gives Bright an opportunity to expand and grow its market.To read this article in full, please click here