This repository has been archived by the owner on Jul 16, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 167
Netty Performance
linux_china edited this page Mar 22, 2021
·
3 revisions
Netty performance with io_uring
- io_uring在网络编程方面的优化更适合长连接场景,在长连接场景下最高有20%多的提升,我们都知道RSocket是长连接的,这样更有优势。
请确保netty-incubator-transport-native-io_uring使用的Netty版本和应用引用的Netty版本一致。
<dependencies>
<!-- <dependency>
<groupId>io.netty</groupId>
<artifactId>netty-all</artifactId>
<version>4.1.59.Final</version>
</dependency>-->
<dependency>
<groupId>io.netty.incubator</groupId>
<artifactId>netty-incubator-transport-native-io_uring</artifactId>
<version>0.0.4.Final</version>
<classifier>linux-x86_64</classifier>
</dependency>
</dependencies>
- Efficient IO with io_uring: https://kernel.dk/io_uring.pdf
- What is io_uring? https://unixism.net/loti/what_is_io_uring.html
- Linux异步IO新时代:io_uring https://kernel.taobao.org/2019/06/io_uring-a-new-linux-asynchronous-io-API/
- Binary: byte stream
- Async message
- Multi transports
- Reactive Semantics
- request/response
- request/stream
- fire-and-forget
- channel
- TCP+TLS
- WebSocket+TLS
- UDP(Aeron)
- RDMA