Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Improvement] tonic throughput problems #1307

Closed
3 tasks done
zuston opened this issue Nov 10, 2023 · 0 comments · Fixed by #1306
Closed
3 tasks done

[Improvement] tonic throughput problems #1307

zuston opened this issue Nov 10, 2023 · 0 comments · Fixed by #1306

Comments

@zuston
Copy link
Member

zuston commented Nov 10, 2023

Code of Conduct

Search before asking

  • I have searched in the issues and found no similar issues.

What would you like to be improved?

I‘m always digging the way to solve the request throughput when the writing concurrency is 400. And then I found the few people talk about this, which makes me confused until I see this hyperium/tonic#1405 (comment) .

From this blog https://medium.com/@fujita.tomonori/scalable-server-design-in-rust-with-tokio-4c81a5f350a3,
I try to do this optimization, and then do some terasort test. I found the peek receive data speed from 1.2G/s -> 2.0G/s, it works ! And the latency becomes low. And the whole processing time reduces from 20min -> 8.5min

How should we improve?

No response

Are you willing to submit PR?

  • Yes I am willing to submit a PR!
@zuston zuston linked a pull request Nov 10, 2023 that will close this issue
[#1307] feat(rust): make each thread listen the socket to improve throughput in tonic #1306
Merged
zuston added a commit that referenced this issue Nov 10, 2023
@zuston
[#1307] feat(rust): make each thread listen the socket to improve thr…
6823916 
…oughput in tonic (#1306)

### What changes were proposed in this pull request?

Make each grpc service thread listens the socket to improve request throughput.

### Why are the changes needed?

I‘m always digging the way to solve the request throughput when the writing concurrency is 400. 
And then I found the few people talk about this, which makes me confused until I see this hyperium/tonic#1405 (comment) .

From this blog https://medium.com/@fujita.tomonori/scalable-server-design-in-rust-with-tokio-4c81a5f350a3,
 I try to do this optimization, and then do some terasort test. I found the peek receive data speed from 1.2G/s -> 2.0G/s, it works ! And the latency becomes low. And the whole processing time reduces from 20min -> 8.5min


### Does this PR introduce _any_ user-facing change?

No.

### How was this patch tested?

No need
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
1 participant
@zuston