88bd6e7a93
Motivation: While benchmarking the native transport with gathering writes I noticed that it is quite slow. This is due the fact that we need to do a lot of array copies to get the buffers into the iov array. Modification: Introduce a new class calles IovArray which allows to fill buffers directly in a iov array that can be passed over to JNI without any array copies. This gives a nice optimization in terms of speed when doing gathering writes. Result: Big performance improvement when doing gathering writes. See the included benchmark... Before: [nmaurer@xxx]~% wrk/wrk -H 'Host: localhost' -H 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8' -H 'Connection: keep-alive' -d 120 -c 256 -t 16 --pipeline 256 http://xxx:8080/plaintext Running 2m test @ http://xxx:8080/plaintext 16 threads and 256 connections Thread Stats Avg Stdev Max +/- Stdev Latency 23.44ms 16.37ms 259.57ms 91.77% Req/Sec 181.99k 31.69k 304.60k 78.12% 346544071 requests in 2.00m, 46.48GB read Requests/sec: 2887885.09 Transfer/sec: 396.59MB With this change: [nmaurer@xxx]~% wrk/wrk -H 'Host: localhost' -H 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8' -H 'Connection: keep-alive' -d 120 -c 256 -t 16 --pipeline 256 http://xxx:8080/plaintext Running 2m test @ http://xxx:8080/plaintext 16 threads and 256 connections Thread Stats Avg Stdev Max +/- Stdev Latency 21.93ms 16.33ms 305.73ms 92.34% Req/Sec 194.56k 33.75k 309.33k 77.04% 369617503 requests in 2.00m, 49.57GB read Requests/sec: 3080169.65 Transfer/sec: 423.00MB |
||
|---|---|---|
| all | ||
| buffer | ||
| codec | ||
| codec-dns | ||
| codec-haproxy | ||
| codec-http | ||
| codec-memcache | ||
| codec-mqtt | ||
| codec-socks | ||
| codec-stomp | ||
| common | ||
| example | ||
| handler | ||
| license | ||
| microbench | ||
| tarball | ||
| testsuite | ||
| transport | ||
| transport-native-epoll | ||
| transport-rxtx | ||
| transport-sctp | ||
| transport-udt | ||
| .fbprefs | ||
| .gitignore | ||
| .travis.yml | ||
| CONTRIBUTING.md | ||
| LICENSE.txt | ||
| NOTICE.txt | ||
| pom.xml | ||
| README.md | ||
| run-example.sh | ||
Netty Project
Netty is an asynchronous event-driven network application framework for rapid development of maintainable high performance protocol servers & clients.
Links
How to build
For the detailed information about building and developing Netty, please visit the developer guide. This page only gives very basic information.
You require the following to build Netty:
- Latest stable Oracle JDK 7
- Latest stable Apache Maven
- If you are on Linux, you need additional development packages installed on your system, because you'll build the native transport.
Note that this is build-time requirement. JDK 5 (for 3.x) or 6 (for 4.0+) is enough to run your Netty-based application.
Branches to look
The 'master' branch is where the development of the latest major version lives on. The development of all other versions takes place in each branch whose name is identical to <majorVersion>.<minorVersion>. For example, the development of 3.9 and 4.0 resides in the branch '3.9' and the branch '4.0' respectively.