Perform a comprehensive test on the performance of a Gigabit Switch Based on nine indicators.

When selecting a vswitch, we are most concerned about its performance and whether it can meet our needs. Here we will teach you how to test the performance of a Gigabit Switch and hope to help you. As the core connection device of an enterprise network, a Gigabit Switch provides the primary performance standard to speed up the enterprise network.

To help readers better understand the overall performance of GE switches, we use the industry-leading IXIA1600 Testing Instrument to test 9 main indicators involving Ge switches. Of course, the test conditions are harsh compared to the actual working environment. We tested the performance mainly based on RFC2544 and RFC2285, and selected 64-byte, 512-byte, and 1518-byte Ethernet frame lengths.

1. throughput is one of the most important indicators for users to select and measure the performance of a gigabit switch. The throughput determines the maximum rate of frames sent and received without frame drop. During the test, we performed the task at full load. This test is configured as one-to-one ing.

2. Frame loss rate this test determines the percentage of frames that the switch should forward under continuous load, but cannot be forwarded due to lack of resources. The frame loss rate can reflect the performance of the vswitch during overload, which is useful for the operation of the vswitch in abnormal conditions such as broadcast storm.

3. Back-to-Back this test considers the number of data frames that can be continuously forwarded by the switch without frame loss. The test of this parameter can reflect the size of the data buffer.

4. delay this indicator determines the time when data packets pass through the vswitch. If the latency is FIFO (FirstinandFirstOut), it refers to the time interval from when the device receives the first frame to the input port to when the first frame reaches the end of the output port. Initially, the sending rate is set to the rate obtained in the throughput test. frames are sent within the specified interval. A specific frame is set to a time mark frame. The time tag of the frame is recorded at the time of sending and receiving, and the difference between the two is the delay time.

5. error frame Filtering this test item determines whether the switch can correctly filter frames of certain error types, such as excessively small frames, ultra-large frames, CRC error frames, Fragment, Alignment errors, and Dribble errors, A small frame is a frame smaller than 64 bytes, including 16, 24, 32, and 63 bytes. A large frame is a frame larger than 1518 bytes, including 1519, 2000, 4000, and 8000 bytes. Fragment indicates a frame with a length less than 64 bytes, and CRC indicates a frame checksum error, dribble frames refer to redundant bytes after the correct CRC Check frame. The switch usually corrects the Dribble frames and forwards them to the correct receiving port, alignment combines a CRC error and a dribble error to indicate an incorrect frame whose frame length is not an integer. This test is configured with One-to-multiple ing.

6. the back pressure determines whether the switch can avoid packet loss when it blocks external data frames from being sent to the congested port. Some vswitches send back-to-source addresses of blocked signals when the sending or receiving buffer overflows. The vswitch uses X traffic control during full dual-work hours for the same purpose. This test sends data to one port through multiple ports to check whether back pressure is supported. If the port is set to half duplex with back pressure, no frame loss or collision is detected. If the port is set to full-duplex and throttling is set, the throttling frame should be detected. If no back pressure is set, the total number of sent frames is not equal to the number of received frames.

7. Line congestion HeadofLineBlocking, HOL) This test determines how congested ports affect the forwarding rate of non-congested ports. During the test, port A and port B are used to send data to port C to form A congested port, while port A also sends data to Port D to form A non-congested port. The result shows the number of received frames, the number of collision frames, and the frame drop rate.

8. Full mesh This test is used to determine the total number of frames that the switch can process when all its ports receive data. Each port of the vswitch sends frames to all other ports in a distributed and cyclic manner while receiving data from other ports at a specific speed. We use the full mesh method to test Gigabit backbone switches for more demanding test environments.

9. Partial mesh this test tests the maximum performance of the Gigabit Switch in a more rigorous environment, and sends frames in a mesh form to multiple receiving ports through multiple sending ports for testing. We use this test method to test the Gigabit access switch. Each m is corresponding to 10 MB ports, and the remaining MB ports are used for full mesh testing.