31–40 of 117 posts
[flagged]
For example, look at these benchmarks from 2003[1]. Makes you wonder where the myth comes from.
The newest benchmark I could find[2] points in the same direction.
Does anyone have more recent data?
[1] http://bulk.fefe.de/scalability/ [2] https://matteocroce.medium.com/linux-and-freebsd-networking-...
Earlier quoted context omitted.
This is "appeal to authority" fallacy incarnate. Google/Amazon "etc;" are likely happy to pay the cost because it really is "good enough" and the benefits of Linux over FreeBSD are otherwise quite considerable. Google in particular seems blissfully happy to literally throw hardware at problems; since hardware is (for them especially) fundamentally extremely cheap. Even multiple percentage gains in throughput are not…
Do you know for a fact that Google primarily uses userland networking, or does that just seem accurate to you?
However there is some public information on some components that has been shared in this thread which allows you to draw your own conclusion.
Earlier quoted context omitted.
Do you know for a fact that Google primarily uses userland networking, or does that just seem accurate to you?
I can't honestly answer that with the NDA I signed. However there is some public information on some components that has been shared in this thread which allows you to draw your own conclusion.
Earlier quoted context omitted.
I can't honestly answer that with the NDA I signed. However there is some public information on some components that has been shared in this thread which allows you to draw your own conclusion.
Yes, the one link shared says essentially the opposite thing.
Earlier quoted context omitted.
History has shown that tons of Linux networking scalability and performance contributions have been rejected by the gatekeepers/maintainers. The upstream kernel remains unsuitable for datacenter use, and all the major operators bypass or patch it.
Do you have links on this? I’ve not heard anything about it
Earlier quoted context omitted.
You may have read it wrong.
Did I? How?
And making that assumption when there are many public examples of Google doing this in other areas such as gVisor and Netstack?
Earlier quoted context omitted.
Did I? How?
For one by assuming the work that is done primarily for microkernels/appliances is the absolute limit of userspace networking at Google and that similar work would not go into a hypervisor (hypervisors which are universally treated as a vSwitch in almost all virtual environments the world over). And making that assumption when there are many public examples of Google doing this in other areas such as gVisor and Netst…
Earlier quoted context omitted.
The big guys don't have the patience to wait for Linux kernel networking to be fast and scalable. They bypass the kernel and take over the hardware. https://blog.acolyer.org/2019/11/11/snap-networking/
Over the course of several years, the architecture underpinning Snap has been used in production for multiple networking applications, including network virtualization for cloud VMs [19], packet-processing for Internet peering [62], scalable load balancing [22], and Pony Express, a reliable transport and communications stack that is our focus for the remainder of this paper. This paper suggests, as I would have expec…
Does performance tuning for Wi-Fi adapters matter? On desktops, other than disabling features, can anything fix the problems with i210 and i225 ethernet? Those seem to be the two most common NICs nowadays. I don't really understand why common networking hardware and drivers are so flawed. There is a lot of attention paid to RISC-V. How about start with a fully open and correct NIC? They'll shove it in there if it's c…
i225 is just broken but I get excellent performance from i210. 1gb is hardly challenging on a contemporaneous CPU, and the i210 offers 4 queues. What's your beef with i210?