Zero-copy in Go: sendfile, splice, and the cost of io.Copy
segflow.github.io
Zero-copy in Go: sendfile, splice, and the cost of io.Copy
1–10 of 24 posts
Re: Zero-copy in Go: sendfile, splice, and the cost of io.Copy
#2A good reminder. It is surprising first time you encounter it.
Same for Rust. As https://doc.rust-lang.org/stable/std/io/fn.copy.html says, std::io::copy can use copy_file_range(2), sendfile(2), or splice(2).
Re: Zero-copy in Go: sendfile, splice, and the cost of io.Copy
#3Zero-Copy in Go: Why magic is an antipattern, and: performance is observable behavior.
Re: Zero-copy in Go: sendfile, splice, and the cost of io.Copy
#4Zero-Copy in Go: Why magic is an antipattern, and: performance is observable behavior.
What would you prefer?
I do think it is criminal this is not documented (https://pkg.go.dev/io#Copy), but I think io.Copy is fine as an API.
Re: Zero-copy in Go: sendfile, splice, and the cost of io.Copy
#5Ugh, AI slop writing.
Re: Zero-copy in Go: sendfile, splice, and the cost of io.Copy
#6Interesting premise for a post, but I had to stop midway due to the AI slop writing adding meaningless information.
Re: Zero-copy in Go: sendfile, splice, and the cost of io.Copy
#7Ugh, AI slop writing.
Definitely written by codex.
Re: Zero-copy in Go: sendfile, splice, and the cost of io.Copy
#8Zero-Copy in Go: Why magic is an antipattern, and: performance is observable behavior.
What would you prefer? I do think it is criminal this is not documented ( https://pkg.go.dev/io#Copy ), but I think io.Copy is fine as an API.
it is documented by saying it calls ReadFrom or WriteTo
Re: Zero-copy in Go: sendfile, splice, and the cost of io.Copy
#9This is almost like the expression problem. Copy is a new operation, and you introduced a new type, thus creating a new grid cell nobody from either side could have reasonably known about - except for the fact Copy is in the standard library so you could have known about it but not done anything.