-
Notifications
You must be signed in to change notification settings - Fork 33
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.
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
latency seem so high #48
Comments
seems in range 10^2 us , in our scenary is enough fast, what is your scenary? |
Frequent transfer of large amounts of data with low latency, market data server to contribute data to many clients |
Your test case as above isn't our typical scenario. Regarding your scenario, perhaps you can modify the code like this. using more goroutine to send data with concurrently.
|
I can't understand this solution. Does it can improve? |
it panic
|
change it, panic agan
panic
|
result: |
The performance advantages of shmipc stem from two factors: 1. Zero-copy transmission of large data packets. 2. Reduction of system calls through batching when handling intensive requests. If your scenario primarily involves interactions with small data packets, you can increase request density (high concurrency) to achieve the second benefit, which was the change I requested earlier. Additionally, achieving microsecond-level latency is not our primary focus, and latency statistics should include metrics such as average, p50, p90, p99, etc. |
shm server
shm client
result
The text was updated successfully, but these errors were encountered: