Page History

...

• White-box: all the network devices along the data propagation path are in the same responsibility zone. In this case, the QoS configuration on the devices can be synchronized, according to the requirements specified in the section above.
• Black-box: some network devices in the data propagation path are part of an external responsibility zone. The classification rules for incoming data and the algorithm for emptying the queues are configured individually on each device. The architecture of the packet queues's implementation depends on the manufacturer of the equipment, therefore there is no guarantee of a correct QoS configuration on the devices in the external responsibility zone, and as a result, there is no guarantee of the high-quality performance indicators.

...

Keep in mind that usually, the equipment located in an external responsibility zone does not support data prioritization in accordance with the priority values in the service headers. Traffic priority coordination should be performed at the border of the responsibility zones and , at the administrative level, by implementing additional network configuration settings.

...

The Ethernet frame header includes the "User Priority" service field, which is used to prioritize the data frames. The field has a size of 3 bits size, which allows to select 8 traffic classes: 0 - the lowest priority class, 7 - the highest priority class. Keep in mind that the "User Priority" field is present only in 802.1q frames, i.e. frames using VLAN tagging.

...

1. When the protocol was first approved, there was an 8-bit ToS (Type of Service) field in the IP packet header (see RFC 791). ToS included the following fields (Figure 12a):
   1. Precedence: priority value (3 bits).
   2. Delay: delay minimization bit.
   3. Throughput: throughput minimization bit.
   4. Reliability: reliability maximization bit.
   5. 2 bits equal to 0.
2. In the second stage, 8 bits were still used for packets packet prioritization, however, ToS included the following fields (see RFC 1349):
   1. Delay.
   2. Throughput.
   3. Reliability.
   4. Cost: bit to minimize the cost metric (1 bit is used, whose value was previously zero).
3. Last, the IP header structure has been changed (see RFC 2474).The 8 bits previously used for prioritization were distributed in the following way (Figure 12b):
   1. DSCP (Differentiated Services Code Point): packet priority (6 bits).
   2. 2 bits are reserved.

Thus, ToS allows to distinguish 8 traffic classes: 0 - the lowest priority, 7 - the highest priority, and DSCP - 64 classes: 0 - the lowest priority, 63 - the highest priority.

...

Let's look at the example of a data transmission from Node-1 to Node-2 through a DS-domain and through a third-party telecom operator's network (Figures 13a-c). The DS domain includes three devices, two of them are located at the borderline and one is an intermediate device. Lets  Let's look at the steps of taken for data processing in a network using an Ethernet frame transmission (the basic principles discussed in the example below are applicable for an IP packet or other protocol that supports data prioritization):

• Step 1: Node-1 generates an Ethernet frame for Node-2. There is no field present for frame priority tagging in the header (Figure 13a).
• Step 2: Border Network Device-1 changes the Ethernet header, setting the priority to 1. Border devices should have rules configured in order to filter the traffic of Node-1 from the general stream and assigna  to assign a  priority for it (usually the traffic of several devices is aggregated using a switch before reaching Border network device-1, but this is a simplified example). In networks with a large traffic flow number, the list of rules on border devices can be volumetric. Border network device-1 processes the frame according to the set priority, placing it in the corresponding queue. The frame is transmitted towards the outgoing interface and sent to Intermediate network device-2 (Figure 13a).
• Step 3: Intermediate network device-2 receives the Ethernet frame having priority 1, and places it in the corresponding priority queue. The device does not handle the priority in terms of changing or removing it inside the frame header. The frame is next transmitted towards the Border network device-3 (Figure 13a).
• Step 4: Border network device-3 processes the incoming frame similarly to the Intermediate device-2 (see Step 3) and forwards it towards the service network provider(Figure 13a).
  • Step 4a: in case of agreeing that the traffic will be transmitted through the provider's network with a priority other than 1, then Border Device-3 must perform a change the priority change. In this example, the device changes the priority value from 1 to 6 (Figure 13b).
• Step 5: during the transmission of the frame through the provider's network, the devices will take into account the priority value in the Ethernet header (Figure 13a).
  • Step 5a: similarly to Step 4a (Figure 13b).
  • Step 5b: if there is no agreement about the frame prioritization according to the priority value specified in the Ethernet header, a third-party service provider can apply its own QoS policy and set a priority that may not satisfy the QoS policy of the DS domain (Figure 13c).
• Step 6: the border device in the provider's network removes the priority field from the Ethernet header and forwards it to Node-2 (Figure 13a-c).

...

• The devices automatically recognize priorities according to different protocols. For example, the InfiLINK XG family of devices supports 802.1p prioritization, but does not recognize DSCP priority values.
• The devices at the borderline of the DS domain allow to use a different set of criteria to classify the traffic. For example, the InfiMAN 2x2 devices allow to set priorities by selecting all the TCP traffic directed to port 23, while the Quanta 5 family devices does not support this type of prioritization.
• The number of the queues implemented inside the devices differs and depends on the manufacturer. A correspondence table is used to set a relation between the priority in the service header and the device's internal queue.

...

Please note the architectural queuing feature of the Infinet devices: all queues share a single memory buffer. In case that all the traffic falls into a single queue, its the size of the queue will be equal to the size of the buffer, but if there will be several queues in use, the size of the memory buffer will be evenly divided between them.

...