This action will force synchronization from zieckey/evpp, which will overwrite any changes that you have made since you forked the repository, and can not be recovered!!!
Synchronous operation will process in the background and will refresh the page when finishing processing. Please be patient.
Boost.Asio is a cross-platform C++ library for network and low-level I/O programming that provides developers with a consistent asynchronous model using a modern C++ approach.
We use the test method described at http://think-async.com/Asio/LinuxPerformanceImprovements using ping-pong protocol to do the throughput benchmark.
Simply to explains that the ping pong protocol is the client and the server both implements the echo protocol. When the TCP connection is established, the client sends some data to the server, the server echoes the data, and then the client echoes to the server again and again. The data will be the same as the table tennis in the client and the server back and forth between the transfer until one side disconnects. This is a common way to test throughput.
The test code of evpp is at the source code
benchmark/throughput/evpp, and at here https://github.com/Qihoo360/evpp/tree/master/benchmark/throughput/evpp. We use
tools/benchmark-build.sh to compile it. The test script are single_thread.sh and multiple_thread.sh.
The test code of asio is at https://github.com/huyuguang/asio_benchmark using commits
21fc1357d59644400e72a164627c1be5327fbe3d and the
client2.cpp/server2.cpp test code. The test script is single_thread.sh and multiple_thread.sh.
We have done two benchmarks:
For details, see the chart below, the horizontal axis is the number of concurrent connections. The vertical axis is the throughput, the bigger the better.
For details, see the chart below. The horizontal axis is the number of threads. The vertical axis is the throughput, the bigger the better.
In this ping pong benchmark test, the asio's test code is using a fixed-size buffer to receive and send the data. That can take advantage of asio
Proactor model, he has almost no memory allocation. Each time asio only reads fixed size of data and then sent it out, and then use the same BUFFER to do the next read operation.
In the same time evpp is a network library of
Reactor model, the receiving data is probably not a fixed size, which involves
evpp::Buffer internal memory reallocation problems that lead to excessive memory allocation.
We will do another benchmark test to verify the analysis. Please look forward to it.
The IO Event performance benchmark against Boost.Asio : evpp is higher than asio about 20%~50% in this case
The performance benchmark of
queue with std::mutex against
moodycamel::ConcurrentQueue is the best, the average is higher than
boost::lockfree::queue about 25%~100% and higher than
queue with std::mutex about 100%~500%
The beautiful chart is rendered by gochart. Thanks for your reading this report. Please feel free to discuss with us for the benchmark test.