News for hackers. Stuff that matters.
Re:Why we use the Linux kernel's TCP stack by peterwwillis on Monday July 11, 2016 @02:21PM (#12073096)
I didn't say anything was impossible. I said the Linux Kernel, and operating systems in general, have TCP/IP stacks not designed to facilitate the highest theoretical possible throughput.

And you mention "maxing out" a link. I bet you're talking about maximum throughput. That requires the maximum possible frame size. I, and the article, are talking about maximum frame rate, which requires the minimum possible frame size. The maximum rate results in about 18x more packets per second. (This is for a typical MTU of 1500; let's not get into jumbo frames...)

And you talk about 1Gbps. For a 10Gbps link, which is the most likely use case in the article, it results in 10x more packets per second, which requires a comparable scale in computing resources. But the stack is only designed to scale to the more likely use case of 1Gbps links; after 8 or so cores, performance can drop off precipitously.

So to hit the maximum packets per second of a 10Gbps link, you would need to handle 180x more packets per second than the max throughput of a 1Gbps link. Most stacks are not designed or performance tested with that in mind.

Re:Why we use the Linux kernel's TCP stack by Annatar on Monday July 11, 2016 @05:09PM (#12074654)
Solaris 10 can drive a 10Gb link at 7.3Gbps (limited by PCI-X bandwidth) using 2x2.2Ghz opteron CPUs utilized at less than 50%

https://sunaytripathi.wordpress.com/2010/03/25/solaris-10-ne..., page nine.

Now the PCIe is multiple times faster than the old PCI-X, and in addition to being several times faster then the old Opteron 939 and 940 series, modern intel based systems have 80 CPU's or more.

Re:Why we use the Linux kernel's TCP stack by peterwwillis on Tuesday July 12, 2016 @12:57AM (#12076835)
You are still quoting throughput when i'm quoting frame/packet rate. On top of this the line you have in italics doesn't show up on that page (it shows up in two random websites that provide no detail as to that claim), I have no idea what "page nine" on my resolution monitor is compared to yours, and you're trying to suggest something about the PCI bus being a factor (which it isn't; the limiting factor is cycles per packet). So I don't think you understand what's going on.
Re:Why we use the Linux kernel's TCP stack by Annatar on Tuesday July 12, 2016 @01:38AM (#12076952)
My apologies, wrong link. This is hard to do on a mobile telephone.

http://www.baylisa.org/library/slides/2005/august2005.pdf, page nine, and in more detail further in the document.

Re:Why we use the Linux kernel's TCP stack by wmf on Monday July 11, 2016 @05:28PM (#12074841)
Let's call that 3.3 Gbps/GHz. Linux can now drive 25 Gbps with a single 4 GHz core, so that's over 6 Gbps/GHz. Given the number of years involved, it's hard to tell how much improvement is due to hardware and how much is software. But I'm not blown away.