Shulou(Shulou.com)06/02 Report--

In this issue, the editor will bring you about how to analyze the Linux TCP/IP protocol stack. The article is rich in content and analyzed and described from a professional point of view. I hope you can get something after reading this article.

TCP/IP refers to a suite of protocols that can transfer information between different networks. TCP/IP protocol not only refers to TCP and IP protocols, but also refers to a protocol suite composed of FTP, SMTP, TCP, UDP, IP and other protocols. Only because TCP and IP protocols are the most representative of TCP/IP protocols, they are called TCP/IP protocols. Let's explain the TCP/IP protocol stack in detail.

Characteristics of TCP

We all know very well that the original intention of TCP protocol design is to ensure that the data transmission is fast, orderly and correct. So the characteristics are summarized as follows:

1. Connection-oriented, you can use a quintuple to represent a connection (remote ip, remote port, local ip, local port, transport layer protocol).

2. The data is full-duplex

3. The data is orderly, that is, the accepted data must be in the order in which it was sent.

4. Flow control, the sender can adjust the size of the transmitted data dynamically by sliding the window size of the receiver.

5. Congestion control, the sender calculates the window size comprehensively through the state of ACK and congestion algorithm.

After understanding the characteristic words of TCP, let's really take a look at the process of data transmission.

Data transmission

First of all, let's take a look at a picture: the above figure shows the process of data flow in hardware, and the following figure shows the process of data in the protocol stack:

The whole process is divided into three large areas: user area, kernel area and equipment. The equipment mentioned here is the network card. The process is as follows:

1. The user application calls write system call 2, confirms file descriptor 3, copies data into socket buffer 4, creates tcp fragments, calculates checksum 5, adds IP headers, performs ip routing, calculates checksum 6, adds Ethernet protocol headers, executes ARP 7, tells the network card chip to send data 8, the network card gets data from memory to send, and sends the interrupt to CPU when the transmission is completed.

Data reception

Look directly at the hardware data flow diagram: first, the network card writes the received data packets into its memory. Then it is checked and sent to the main memory of the host. The buffer in the main memory is assigned by the driver, and the driver will give the assigned buffer description to the network card. If there is not enough buffer to accept the data packet from the network card, the network card will discard the packet. Once the packet has been copied to main memory, the Nic will inform the host OS through an interrupt.

The driver then checks to see if it can handle the new package. If it can handle it, the driver wraps the packet in a linux sk_buffer recognized by OS and pushes it to the upper layer. After receiving the frame, the link layer will decode the frame according to the protocol and push it to the IP layer.

After unpacking, the IP layer decides whether to push to the upper layer or forward to other IP based on the IP information contained in the packet. If it is determined that it needs to be pushed to the upper layer, the IP header will be removed and pushed to the TCP layer.

After decoding, TCP will find the corresponding TCB according to its quad, and then process the message through the TCP protocol. After receiving the message, the message is added to the accept message, and then an ACK is sent to the peer according to the status of the TCP.

Of course, the above process will be affected by NAT and other Netfilter, which is not discussed here, nor has it been studied in depth. Of course, for the sake of performance, Daniel has also made a lot of efforts in many aspects, such as RDMA, DPDK and other software and hardware technologies, as small as zero-copy, checksum offload and so on.

What is Linux system Linux is a free-to-use and free-spread UNIX-like operating system, is a POSIX-based multi-user, multi-task, multi-threaded and multi-CPU operating system, using Linux can run major Unix tools, applications and network protocols.

The above is the editor for you to share how to analyze the Linux TCP/IP protocol stack, if you happen to have similar doubts, you might as well refer to the above analysis to understand. If you want to know more about it, you are welcome to follow the industry information channel.

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.