Netdev 0x16 - Keynote: It's Time to Replace TCP in the Datacenter
Why Hacker News recommends it
Recommended as the thorough case for replacing TCP in datacenters and for Ousterhout's Homa protocol.
What it is
John Ousterhout's Netdev 0x16 keynote arguing that nearly every aspect of TCP is wrong for the datacenter, from connections and streams to reliable delivery and congestion control. He presents the case for a replacement protocol.
Recommended by 2 HN commenters across 2 different months, 2023 to 2023.
What Hacker News said
Strong rec hardwaresofton · 2023-02 · on “It's TCP vs. RPC All over Again”
If you'd like to watch Ousterhoust explain Homa and his vision of replacing TCP: [this video] Spoiler: Ousterhout is right, and the data shows he is right. Maybe not everyone knows it yet, or it's the kind of "right" that not everyone will ever get to (and we'll settle for "good enough" for much longer), but he is almost certainly right. Not to disparage the poster of this article of course -- I always love a good hot take or contrarian piece.
Strong rec eklitzke · 2023-03 · on “RPC vs. TCP (Redux)”
You can obviously build an RPC protocol on top of TCP, people have been doing it for decades. However there are things that are difficult to efficiently implement on top of TCP (multiplexing different logical streams over the same connection, message priorities) in the TCP model, and some things that are impossible to implement over TCP (for example, you don't really have any ability to influence what happens during congestion control scenarios). There are also a bunch of things about TCP that are fundamentally inefficient on modern hardware. Do these things matter if you're running some RPC service over the internet with a Python backend? Almost certainly not. But if you read John Ousterhou
Recommends hardwaresofton · 2023-02 · on “Is It Time to Replace TCP in Data Centers?”
If you want to watch Outsterhout in talk form: Netdev 0x16 - Keynote: It's time to replace TCP in the datacenter: [this video] Netdev is an amazing conference btw, it is insane that we get access to the trailblazing being shown off at conferences for free on places like YT.
Cites HippoBaro · 2023-10 · on “Is POSIX really outdated?”
I think there are a few misunderstandings there (the video is funny, btw). The kind of async IO I'm referring to exists one layer below whatever Apache and node are using. Both are event-driven, actually. They both use some flavor of epoll (see [LINK] ). Historically, buffered IO was sufficient to circumvent slow threads. Simply because buffered IO operations usually don't block (you merely memcpy, and the kernel flushes asynchronously in the background). That can only take you so far, however, and it's apparent today that hardware can go much further and that the gap is widening. It's a valid point, though, to question whether that additional performance is even needed. John Ousterhout ( [V