Shulou(Shulou.com)05/31 Report--

This article mainly explains "how to understand Redis pipeline". The content of the explanation is simple and clear, and it is easy to learn and understand. Please follow the editor's train of thought to study and learn "how to understand Redis pipeline".

1. Request response protocol and RTT:

Redis is a typical TCP server based on the C-hand S model. In the process of communication between the client and the server, the client usually takes the lead in initiating the request, the server executes the corresponding task after receiving the request, and finally sends the obtained data or processing results to the client in the way of reply. During this process, the client waits for the result returned by the server in a blocking manner. See the following command sequence:

Client: INCR X

Server: 1

Client: INCR X

Server: 2

Client: INCR X

Server: 3

Client: INCR X

Server: 4

In the process of each pair of requests and responses, we have to bear the extra overhead of network transmission. We often refer to this overhead as RTT (Round Trip Time). Now let's assume that the RTT for each request and reply is 250ms, and our server can process 100k of data in one second, but the result is that our server can process at most four requests per second. To solve this performance problem, how can we optimize it?

2. Pipeline (pipelining):

Redis has provided support for command pipelines in early versions. Before giving a specific explanation, let's transform the above example of synchronous response into an asynchronous response based on command pipeline, which can give you a better perceptual understanding.

Client: INCR X

Client: INCR X

Client: INCR X

Client: INCR X

Server: 1

Server: 2

Server: 3

Server: 4

As you can see from the above example, after sending a command, the client does not have to wait for a reply from the server immediately, but can continue to send subsequent commands. After the command is sent, the responses of all previous commands are read at once. This saves the cost of RTT in synchronization mode.

Finally, if the Redis server finds that the client's request is pipeline-based, the server will queue the reply data for each command after receiving the request and processing it, and then send it to the client.

3. Benchmark:

Here are the test cases and results from the Redis website. It is important to note that the test is based on loopback (127.0.0.1), so RTT takes relatively little time, and the performance improvement brought about by the pipeline mechanism is even more significant if it is based on the actual network interface.

1 million rubygems'

2. Resume redisis'

three

4 def bench (descr)

5 start = Time.now

6 yield

7 puts "# {descr} # {Time.now-start} seconds"

8 end

nine

10 def without_pipelining

11 r = Redis.new

1210000.times {

13 r.ping

14}

15 end

sixteen

17 def with_pipelining

18 r = Redis.new

19 r.pipelined {

2010000.times {

21 r.ping

22}

23}

24 end

twenty-five

26 bench ("without pipelining") {

27 without_pipelining

28}

29 bench ("with pipelining") {

30 with_pipelining

31}

32 / / without pipelining 1.185238 seconds

33 / / with pipelining 0.250783 seconds

Thank you for your reading, the above is the content of "how to understand the Redis pipeline". After the study of this article, I believe you have a deeper understanding of how to understand the Redis pipeline, and the specific use needs to be verified in practice. Here is, the editor will push for you more related knowledge points of the article, welcome to follow!

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.