SOCKMAP - TCP splicing of the future
blog.cloudflare.com
SOCKMAP - TCP splicing of the future
1–10 of 11 posts
Re: SOCKMAP - TCP splicing of the future
#2TLDR, not ready for prime time.
Sadly, probably still the best Cloudflare blog written in the last nine months.
Re: SOCKMAP - TCP splicing of the future
#3TLDR, not ready for prime time. Sadly, probably still the best Cloudflare blog written in the last nine months.
Hello Claude!
Re: SOCKMAP - TCP splicing of the future
#4sockmap has been through a lot of changes since then. Some done by CF (hi Jakub!) some by others, including bytedance and isovalent.
Recently there has been a push to figure out the backpressure situation, so it's worth checking again.
Marek
Re: SOCKMAP - TCP splicing of the future
#5TLDR, not ready for prime time. Sadly, probably still the best Cloudflare blog written in the last nine months.
Article is from 2019.
Re: SOCKMAP - TCP splicing of the future
#6Re: SOCKMAP - TCP splicing of the future
#7(2019)
Re: SOCKMAP - TCP splicing of the future
#8You are far better off reading the sockmap docs than this post, it adds almost nothing, entirely fails to explain the point of the interface and more or less amounts to marketing slop
Re: SOCKMAP - TCP splicing of the future
#9Re: SOCKMAP - TCP splicing of the future
#10The ambitious thing to do would be to eliminate the kernel/user space boundary entirely and support their use case entirely in ring0. God, I wish I worked there. I don't know enough about the details of their use case to do it out in the open.