[−]austin-cheney · 2026-07-02 Thu 02:11 UTC ·
link
Another example is QUIC. What is the benefit of QUIC? On one hand Google boasts it greatly increases page load speed, which is contextually arguable. On the other hand, Google’s design priorities were to introduce UDP to the browser because UDP supports multicast, which lowers CPU utilization in data centers.
IIRC, QUIC was also the precursor to HTTP/3. I don't like Google's motivations for wanting a faster web, but many of the things they've encouraged and/or provided have made things faster and more efficient. I'm not a google apologist, there's so much wrong and so much harm done... just saying it's maybe worth separating the tech from the motives.
HTTP/3 uses QUIC as the transport layer, which in turn relies on UDP. QUIC replaces TCP while allowing a reduction of handshake exchanges in HTTP/3 first requests. Finally, even though UDP supports multicast, I believe QUIC doesn't. GP saying Google has developed it to use multicast thus is nonsense. Furthermore, QUIC takes much more CPU than TCP right now, due to running in userland.
In my opinion, QUIC and HTTP/3 are technical marvels, but are perhaps way too complicated and don't really serve the interest of most internet users.
There will be a point in the development of web browsers and associated technologies where we should just stop a bit to get things stable instead of churning protocol version after protocol version after new API. Will it ever stop?
Eventually, it all becomes so complicated no company can manage it all. Honestly, we might already be past this point, with Chromium at almost 40mi LOC, more than the Linux kernel itself, including all its drivers. When will the madness stop? Do we really need such complicated software to see Instagram posts, comment on a few Hacker News threads and mess around with Google Sheets?
The biggest reason I worry so much about this is that in the web, adding new features, APIs and protocols is easy. Removing and deprecating is basically impossible.
It's not very complicated to import the QUIC library, or to import the HTTP library with HTTP/3 supported. For the library authors, QUIC isn't more complicated to implement than TCP. Doomsaying about the complexity of Google Sheets is completely unrelated to whether QUIC is good tech and superior to TCP, which it is; the only remaining complaint is that it's too new to have been part of the kernel yet, and if that makes technology somehow illegitimate then I guess we're just stuck with the mistakes of the 90s forever, why ever invent anything new at all.
They claimed and showed QUIC slightly-to-moderately reduced latency, particularly for mobile. This benefits Google by loading pages with third-party content, i.e. ads, faster.
But QUIC significantly increases CPU utilization on servers, at least the widely used userland stacks do. Unless/until Google deploys QUIC in the kernel (or puts the whole network stack in userland, a la DPDK), this won't change.
The multicast claim is kinda bizarre. I can see how QUIC could help eliminate UDP client barriers, but those barriers pale in comparison to multicast. Multicast routing just doesn't exist on the Internet; it's only supported within some independent, typically small networks. Most ISPs don't support it. Wherever you could manage to distribute content with multicast, you'd necessarily also be resolving the collateral routing problems which QUIC support resolves, whereas even ubiquitous QUIC doesn't materially improve the multicast situation.
In my opinion, QUIC and HTTP/3 are technical marvels, but are perhaps way too complicated and don't really serve the interest of most internet users.
There will be a point in the development of web browsers and associated technologies where we should just stop a bit to get things stable instead of churning protocol version after protocol version after new API. Will it ever stop?
Eventually, it all becomes so complicated no company can manage it all. Honestly, we might already be past this point, with Chromium at almost 40mi LOC, more than the Linux kernel itself, including all its drivers. When will the madness stop? Do we really need such complicated software to see Instagram posts, comment on a few Hacker News threads and mess around with Google Sheets?
The biggest reason I worry so much about this is that in the web, adding new features, APIs and protocols is easy. Removing and deprecating is basically impossible.
But QUIC significantly increases CPU utilization on servers, at least the widely used userland stacks do. Unless/until Google deploys QUIC in the kernel (or puts the whole network stack in userland, a la DPDK), this won't change.
The multicast claim is kinda bizarre. I can see how QUIC could help eliminate UDP client barriers, but those barriers pale in comparison to multicast. Multicast routing just doesn't exist on the Internet; it's only supported within some independent, typically small networks. Most ISPs don't support it. Wherever you could manage to distribute content with multicast, you'd necessarily also be resolving the collateral routing problems which QUIC support resolves, whereas even ubiquitous QUIC doesn't materially improve the multicast situation.