Re:HTTP/3: the past, the present, and the future
by forgot-my-pw on Thursday September 26, 2019 @01:55PM
(#21083489)
When QUIC just came out, early comments said that it makes CPU usage much higher. Is it still the same case today?
[ Parent
| on HN ]
Re:HTTP/3: the past, the present, and the future
by hanakuso on Thursday September 26, 2019 @03:36PM
(#21084645)
Almost certainly, but I cannot confirm without benchmarks.
HTTP1/2 = TCP, which has dedicated hardware to offload major parts of the protocol overhead.
QUIC = UDP, but re-implements some features of TCP in software, leaving the CPU to handle things it didn't have to before.
Re:HTTP/3: the past, the present, and the future
by dragonwriter on Thursday September 26, 2019 @07:13PM
(#21086651)
Over time, especially with HTTP/3 adoption, wouldn't we expect QUIC to get hardware support like TCP, leaving this as a transitional issue?
Re:HTTP/3: the past, the present, and the future
by amluto on Thursday September 26, 2019 @08:14PM
(#21087111)
TCP hardware acceleration is generally pretty minimal. The common features are checksum offload and segmentation offload. Checksum offload should generally work for UDP, and I believe that a good UDP implementation can get much of the benefit of segmentation offloading.
Re:HTTP/3: the past, the present, and the future
by marcosdumay on Thursday September 26, 2019 @03:51PM
(#21084793)
As a rule, discussion of CPU usage of network protocols aren't important for 99% of the people. IO performance is the dominant metric.
Re:HTTP/3: the past, the present, and the future
by mnem on Thursday September 26, 2019 @04:00PM
(#21084881)
I'm not sure that follows. Higher CPU usage isn't undesirable because it slows things down (although it may), it prevents battery powered devices working efficiently. Plucking a figure from the air, if QUIC knocks 10% off the battery life of mobiles, that's a hard sell.
Re:HTTP/3: the past, the present, and the future
by ryacko on Thursday September 26, 2019 @06:10PM
(#21086119)
Large percentage of mobile device power consumption is from radio use. Personal tests of phones in airplane mode and without airplane mode show even network keepalive consumes a fair amount of energy.
I plan on purchasing the book as reviewed by this blog post: https://petewarden.com/2015/10/08/smartphone-energy-consumpt...
Re:HTTP/3: the past, the present, and the future
by krferriter on Thursday September 26, 2019 @10:03PM
(#21087744)
Sure but if HTTP/3 adds significant processor overhead compared to prior versions and the user isn't getting a noticeable benefit from this cost, they're not going to like it and it sort of seems like a pointless waste of effort.
Re:HTTP/3: the past, the present, and the future
by marcosdumay on Thursday September 26, 2019 @05:19PM
(#21085665)
Network usage of CPU is tippically well bellow rounding error on a usual system. That's different if you are talking about a static assets CDN or if you are designing networking equipment, but for usual applications, no, it won't make a difference on the battery life of your mobile, page rendering will, not network.