Explanation and calculation of several main technical parameters of vswitches

Generally, the calculation method is as follows:

1) wire speed backboard bandwidth

Measure the test taker's knowledge about the total bandwidth provided by all ports on the vswitch. The formula is as follows: number of ports * corresponding port rate * 2 (full duplex mode). If the total bandwidth is less than or equal to the nominal backboard bandwidth, the bandwidth is linear.

2) Layer 2 packet forwarding speed

Layer 2 packet forwarding rate = number of Gigabit ports x 1. 488 Mpps + 0.1488 MB port count * Mpps + number of other types of ports * Calculation Method. If this rate can be less than or equal to the forwarding rate of a nominal L2 packet, the switch can achieve the line speed when performing Layer 2 switching.

3) Layer 3 packet forwarding speed

Layer 3 packet forwarding rate = number of Gigabit ports x 1. 488 Mpps + 0.1488 MB port count * Mpps + number of other types of ports * Calculation Method. If this rate can be less than or equal to the forwarding rate of a nominal three-tier packet, the switch can achieve line speed when performing layer-3 switching.

So how does 1.488Mpps get it?

The packet forwarding speed is measured by the number of 64 bytes of data packets (minimum packet) sent per unit time. For Gigabit Ethernet, the calculation method is as follows: 1,000,000,000 bps/8bit/(64 + 8 + 12) byte = 1,488,095 pps Description: When the Ethernet frame is 64 byte, the fixed overhead of the frame gap between 8-byte frames and 12-byte frames must be considered. Therefore, the packet forwarding rate of a Gigabit Ethernet port with a line speed is 1.488 Mpps when a 64 byte packet is forwarded. The 10-in-10 Gigabit Ethernet packet forwarding rate is 148.8 kpps.

* For 10-Gigabit Ethernet, the packet forwarding rate of a wire speed port is 14.88 Mpps.

* For Gigabit Ethernet, the packet forwarding rate of a wire speed port is 1.488 Mpps.

* For fast Ethernet, the packet forwarding rate of a wire speed port is 0.1488 Mpps.

* For the POS port of the OC-12, the packet forwarding rate of a wire speed port is 1.17 Mpps.

* For the POS port of the OC-48, the packet forwarding rate of a wire speed port is 4.68 MppS.

Therefore, if the above three conditions can be met, we will say that this switch is truly linear and non-blocking.

The utilization rate of the backboard Bandwidth Resources is closely related to the internal structure of the vswitch. Currently, the internal structure of a vswitch mainly includes the following types: first, the shared memory structure, which relies on the central switching engine to provide high-performance connections across all ports, the core engine checks each input packet to determine the route. This method requires a lot of memory bandwidth and high management costs. Especially with the increase of switch ports, the price of the central memory will be very high. Therefore, the kernel of the switch machine becomes the bottleneck of performance implementation; the second is the cross-bus structure. It can establish direct point-to-point connections between ports, which is good for single-point transmission performance, but not suitable for multi-point transmission. The third is the hybrid cross-bus structure, this is a hybrid cross-bus implementation method. Its design idea is to divide an integrated cross-Bus Matrix into small cross matrices and connect them through a high-performance bus in the middle. The advantage is that the number of Cross buses is reduced, the cost is reduced, and the bus contention is reduced. However, the bus connected to the cross matrix becomes a new performance bottleneck.

How to check whether the vswitch backboard bandwidth is sufficient

The backboard bandwidth is the maximum amount of data that can be transferred between the vswitch interface processor or interface card and the data bus. The higher the bandwidth of the backboard of A vswitch, the stronger the ability to process data, but the design cost will also rise.

However, how can we check whether the bandwidth of A vswitch is sufficient? Obviously, the estimation method is useless. I think we should consider the following two aspects:

1. The sum of the total port capacity X ports should be 2 times smaller than the backboard bandwidth, enabling full-duplex non-blocking switching, proving that the switch has the conditions to maximize the data exchange performance.

2. Full configuration throughput (Mbps) = number of fully configured GE ports × 1. 488Mpps the theoretical throughput of One gigabit port when the packet length is 64 bytes is 1.488 Mpps. For example, A vswitch that can provide up to 64 Gigabit ports must have a full configuration throughput of 64 × 1.488 Mpps = 95.2 Mpps to ensure that all ports are working at the same speed, provides non-blocking packet switching. If a vswitch can provide a maximum of 176 Gigabit ports and the declared throughput is less than 261.8 Mpps (176x1.488 Mpps = 261.8 ), the user has reason to think that the switch adopts a blocking structure design.

Generally, the switches that both meet the requirements are qualified switches.

For vswitches with relatively large backboards and low throughput, the software efficiency/dedicated chip circuit design is not a problem, but the backboard is relatively small. A vswitch with a relatively high throughput has a high overall performance. However, the Board bandwidth can be believed by the manufacturer, but the throughput cannot be believed by the manufacturer. because the latter is a design value, the test is very difficult and the significance is not great.

1. Board bandwidth: refers to the total communication bandwidth (relatively virtual) between all business boards and exchange routing engines)

2. Switching capacity: For a chassis switch, it indicates the maximum switching capability that a certain engine can exert on a certain chassis.

Calculation method:

The box type is determined by the engine.

The size of the low-end swap capacity is determined by the BUFFER's Bit Width and its bus frequency. That is, the switching capacity = cache Bit Width * cache bus frequency

3. packet forwarding rate: it refers to the number of data packets that the switch can forward per second. Ethernet is based on the minimum 64-byte packet. Of course, a 20-byte frame is required for calculation.

Calculation method:

When a full-duplex 1000 Mbps interface reaches the line speed requirement: Forwarding capacity = 1.488 Mbps/(64 + 20) * 8bit) = Mpps

When a full-duplex 100 Mbps interface reaches the line speed requirement: Forwarding capacity = 0.149 Mbps/(64 + 20) * 8bit) = Mpps

For example, the packet forwarding rate of A vswitch with an 8*100 M/1*2.68 M port is M.

4. Port capacity: double the switch port capacity under full duplex

Calculation method:

Port capacity = 2 * (n * 100 Mbps + m * 1000 Mbps) (n: indicates that the switch has n m ports, and m: indicates that the switch has m ports)

For example, the port capacity of an 8*100 M/1*3.6 M port is GB.

All core switches should adopt a modular structure. They must have a considerable number of slots and have powerful network expansion capabilities to protect original investment. The modular structure has stronger performance, greater flexibility and scalability. You can select different numbers, different rates, and different interface types based on actual or future needs, to meet ever-changing network needs.

Scalability should include two aspects:

1. Number of slots. The slot is used to install various functional modules and interface modules. Because the number of ports provided by each interface module is certain, the number of slots fundamentally determines the number of ports that the switch can accommodate. In addition, all functional modules (such as the super engine module, IP voice module, extended service module, network monitoring module, and security service module) need to occupy one slot, therefore, the number of slots fundamentally determines the scalability of the switch.

2. module type. Undoubtedly, the more supported module types (such as LAN interface module, WAN interface module, ATM interface module, and extended function module), the more scalable the switch. Taking LAN interface module as an example, it should include RJ-45 module, GBIC module, SFP module, 10 Gbps module, so as to meet the needs of large and medium-sized network complex environment and network application.

Forwarding Rate

Data in the network is composed of data packets, which consume resources to process each data packet. The forwarding rate (also called throughput) refers to the number of packets passed per unit time without packet loss. The throughput is like the traffic flow of an overpass. It is the most important parameter of a layer-3 Switch, marking the specific performance of the switch. If the throughput is too small, it will become a network bottleneck and negatively affect the transmission efficiency of the entire network. The switching machine should be able to achieve line rate exchange, that is, the exchange rate should reach the data transmission speed on the transmission line, so as to eliminate the bottleneck of the exchange to the maximum extent. For a Gigabit Switch, if you want to achieve non-blocking network transmission, you need:

Throughput (Mpps) = 10g port count × 14. 88 Mpps + gigabit port count × 1. 488 Mpps + 1488 MB port count × 0. Mpps

If the nominal throughput of A vswitch is greater than or equal to the computing value, the line rate can be reached during layer-3 switching. Among them, the theoretical throughput of the 10 thousand MB port when the packet length is 64 B is 14.88 Mpps, and the theoretical throughput of the 1 gigabit port when the packet length is 64 B is 1.488 Mpps, the theoretical throughput of A 0.1488 MB port when the packet length is 64 B is Mpps. How do we obtain these values?

In fact, the packet forwarding speed is measured by the number of data packets (minimum packet) that are sent 64 B per unit time. The following example uses a Gigabit Ethernet port as an example:

1,000,000,000 bps/8 bit/(64 + 8 + 12) B = 1,488,095 pps

When the Ethernet frame is 64 B, the fixed overhead of the frame header of 8 B and the frame gap of 12 B must be considered. It can be seen that the packet forwarding rate of the Gigabit Ethernet port is 1.488 Mpps. 10 Gbit/s Ethernet line-rate port forwarding rate, which is 10 times that of 10 Gbit/s Ethernet, that is, 14.88 Mpps; while 10 Gbit/s Ethernet line-rate port forwarding rate is 10 Gbit/s Ethernet, that is, 0.1488 Mpps.

For example, for a vswitch with 24 Gigabit ports, its full-configuration throughput should reach 8x1.488 Mpps = 35.71 Mpps to ensure that all ports are working at the same speed, implement non-blocking packet switching. Similarly, if A vswitch can provide a maximum of 176 Gigabit ports, the throughput should be at least 261.8 Mpps (176 × 1.488 Mpps = 261.8 Mpps), which is the real non-blocking structure design.

Board bandwidth

Bandwidth is the maximum amount of data that can be transferred between the vswitch interface processor, interface card, and data bus. It is like the sum of the lanes owned by the overpass. Because the communication between all ports needs to be completed through the backplane, the bandwidth provided by the backplane becomes the bottleneck for concurrent communication between ports. The larger the bandwidth, the greater the available bandwidth provided to each port, the greater the data exchange speed; the smaller the bandwidth, the smaller the available bandwidth provided to each port, the slower the data exchange speed. That is to say, the bandwidth of the backboard determines the data processing capability of the switch. The higher the bandwidth of the backboard, the stronger the data processing capability. Therefore, the larger the bandwidth of the backboard, the better, especially for those aggregation layer switches and center switches. To achieve full-duplex and non-blocking network transmission, the minimum bandwidth must be met. The formula is as follows:

Backboard bandwidth = number of ports x port rate X 2

Tip: For a layer-3 Switch, only the forwarding rate and the backboard bandwidth meet the minimum requirements is a qualified switch. Both are indispensable.

Layer-4 Switching

Layer-4 switching is used for fast access to network services. In layer-4 switching, the transmission is determined based not only on the MAC address (layer-2 Bridge) or the source/target address (layer-3 route), but also on TCP/UDP (layer-4) application port number, designed for high-speed Intranet applications. In addition to the Server Load balancer function, layer-4 Switching also supports transmission Flow Control Based on Application Types and user IDs. In addition, the layer-4 switch is directly placed on the front end of the server. It understands the application session content and user permissions, and thus makes it an ideal platform to prevent unauthorized access to the server.

Module Redundancy

Redundancy is the guarantee for safe network operation. No manufacturer can guarantee that its products will not fail during operation. The ability to quickly switch when a fault occurs depends on the redundancy capability of the device. For core switches, all important components should have redundancy capabilities, such as Management Module Redundancy and power supply redundancy, so as to ensure stable network operation to the maximum extent possible.

Routing Redundancy

HSRP and VRRP protocols are used to ensure load sharing and hot backup of core devices. When a switch in the core switch and Shuanghui cluster switch fails, the layer-3 routing device and the virtual gateway can be quickly switched, dual-line redundant backup to ensure the stability of the entire network.