I don’t see how that necessarily follows, but I’ll believe you
-
-
It’s mostly all about malloc perf. Async/await avoids allocations (alliteration!) BTW, the syscall cost of spawning a thread on Linux is a lot less than the cost of allocating the stack.
3 replies 0 retweets 9 likes -
This Tweet is unavailable.
-
I don’t have up-to-date numbers but I know it was a pretty big difference on really high C10K-style workloads. Alex, Carl, etc. probably can cite you some benchmarks.
0 replies 0 retweets 1 like -
This Tweet is unavailable.
-
Go’s concurrency model is fundamentally broken: https://songlh.github.io/paper/go-study.pdf …
3 replies 0 retweets 1 like -
Replying to @bascule @valarauca1 and
As someone who’s used both Go and Erlang extensively, they are leaky, hig-cost abstractions with all sorts of sharp edges. I think Erlang had better defaults with shared nothing asynchrony, but they used unbounded mailboxes which need load shedding or they OOM
0 replies 0 retweets 0 likes -
This Tweet is unavailable.
-
Here’s a presentation from Paul Turner of Google (at the time) about threads from 2013: https://blog.linuxplumbersconf.org/2013/ocw/system/presentations/1653/original/LPC%20-%20User%20Threading.pdf … Sadly he seems to have disappeared and the work never materialized…I’d really like to see work in this direction.
2 replies 0 retweets 0 likes -
Replying to @pcwalton @valarauca1 and
He’s still at Google, doing good work we have all benefited from
1 reply 0 retweets 0 likes
Hrm, my emails bounced.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.