News for hackers. Stuff that matters.
Re:Efficient IO with io_uring [pdf] by cafxx on Tuesday May 07, 2019 @07:32AM (#19848441)
> 10Gb ethernet is only about 10x slower than main memory

Server-class CPUs have much higher bandwidth nowadays:

> The total memory bandwidth available to a single CPU clocks in at 170 GB/s.

(i.e. ~136x slower than main memory)

https://www.anandtech.com/show/11183/amd-prepares-32-core-na...

Re:Efficient IO with io_uring [pdf] by geocar on Wednesday May 08, 2019 @08:18AM (#19858098)
The per-channel number[1] is much better (imo) for napkin spec'ing because it's what you'll get in a typical networked application that's already done and minimised stalls.

But you're raising a good point: If you can arrange your data set across the physical DIMMS yes you can get much another 10x, and maybe the contortions you need to do to get it can be worth it (if you're actually memory bound).

[1]: better link, since the one you posted is bust: https://developer.amd.com/wp-content/resources/56301_1.0.pdf