WO2014047771A1 - 一种流量控制方法、装置及网络 - Google Patents
一种流量控制方法、装置及网络 Download PDFInfo
- Publication number
- WO2014047771A1 WO2014047771A1 PCT/CN2012/081892 CN2012081892W WO2014047771A1 WO 2014047771 A1 WO2014047771 A1 WO 2014047771A1 CN 2012081892 W CN2012081892 W CN 2012081892W WO 2014047771 A1 WO2014047771 A1 WO 2014047771A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- traffic
- service flow
- flow
- needs
- value
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012544 monitoring process Methods 0.000 claims abstract description 114
- 239000013256 coordination polymer Substances 0.000 claims abstract description 97
- 230000011664 signaling Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 108010001267 Protein Subunits Proteins 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000003139 buffering effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000011410 subtraction method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/12—Avoiding congestion; Recovering from congestion
- H04L47/122—Avoiding congestion; Recovering from congestion by diverting traffic away from congested entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
- H04L43/0894—Packet rate
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/11—Identifying congestion
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/26—Flow control; Congestion control using explicit feedback to the source, e.g. choke packets
- H04L47/263—Rate modification at the source after receiving feedback
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate
Definitions
- TECHNICAL FIELD The present application relates to the field of communications, and in particular, to a flow control method, apparatus, and network. Background technique
- Ethernet technology beats Token Ring, FDDI and ATM technologies with its open standards, high performance, low price, and support from many vendors to become a common interface for LAN technology.
- FDDI Token Ring
- ATM ATM
- High Performance Low Price
- support from many vendors to become a common interface for LAN technology.
- IEEE defines a congestion indication (CN, in the 802.1Qau standard).
- a congestion point (CP, Congestion Point) and a reaction point (RP, Reaction Point) in the Ethernet switch network need to be configured.
- the Ethernet switch is configured as a CP, and other nodes connected to the Ethernet switch are configured as RPs, and one CP corresponds to multiple RPs at the edge of the network.
- a line with two rounded endpoints between two nodes in the figure represents the physical link between the nodes.
- a line with an arrow pointing to each RP point indicates the direction in which the control information is transmitted.
- the CP calculates feedback information (Fb, Feedback Information) according to the outbound port queue length and the queue growth speed of the data stream. If Fb ⁇ 0, it indicates that the outbound port queue congestion probability of the data stream increases, and the CP A certain probability P randomly selects a frame message from the received subsequent message of the data stream, and sends control information to the RP that sends the frame message, where the control information includes Fb, a congestion point ID, and the like; After the control information, the transmission rate of the data stream is reduced according to a certain algorithm, such as a multiplication and subtraction method, and when the new control information is not received within a set fixed period, the transmission of the data stream is re-incremented. Rate until the upper limit of the transmission rate of the data stream is reached. The above process is repeated repeatedly to implement network-level flow control of Ethernet.
- Fb Feedback Information
- the technical problem to be solved by the present application is to provide a flow control method, device and network, which can improve the control performance for network traffic.
- a flow control method including: receiving traffic monitoring information of a first service flow reported by a reaction point RP;
- the RP that needs to adjust the traffic is determined from the specified RP according to the traffic monitoring information of the first service flow reported by the received RP, and according to the traffic monitoring information Calculating a new traffic value of the first service flow in the RP that needs to adjust the traffic; the designated RP has a traffic monitoring function;
- the calculated new traffic value of each of the first service flows is sent to the corresponding RP that needs to be adjusted, so that the RP performs flow control on the first service flow in the RP according to the new traffic value.
- the RP that needs to adjust the traffic from the specified RP according to the traffic monitoring information of the first service flow that is reported by the received RP includes:
- the RP acts as an RP that needs to adjust traffic; or,
- the preset ratio RP of the specified RP is selected according to the priority of the specified RP, and the selected preset RP is used as the RP that needs to adjust the traffic.
- the designated RP is an RP that also configures an information rate CIR value and a peak information rate PIR value.
- the RP that needs to adjust the traffic from the specified RP according to the traffic monitoring information of the first service flow that is reported by the received RP includes:
- the traffic monitoring information includes: a buffering state of the first service flow corresponding to the queue in the RP; determining, according to the traffic monitoring information of the first service flow reported by the received RP, that the traffic monitoring information needs to be adjusted
- the RP of traffic includes:
- the traffic monitoring information includes: a traffic of the first service flow, and the first service of the RP that needs to adjust the traffic is calculated according to the traffic monitoring information.
- the new traffic values for the flow include:
- the traffic monitoring information of the first service flow is transmitted by using an outband signaling or a low delay packet; and/or,
- the new traffic parameter of the first service flow is transmitted by out-of-band signaling or low-latency message.
- the RP performs flow control on the first service flow in the RP according to the new traffic value, including:
- the RP decelerates the traffic of the first service flow to the new traffic value.
- the RP performs flow control on the first service flow in the RP according to the new traffic value, including:
- the committed information rate CIR and/or the peak information rate PIR in the RP are configured as the new traffic value.
- a flow control apparatus including: a receiving unit, configured to receive traffic monitoring information of a first service flow reported by a reaction point RP; and a calculating unit, configured to be used in a congestion point CP
- the RP that needs to adjust the traffic is determined from the specified RP according to the traffic monitoring information of the first service flow that is received by the RP, and is calculated according to the traffic monitoring information received by the receiving unit.
- the designated RP has a traffic monitoring function; a sending unit, configured to send, by the computing unit, a new traffic value of each of the first service flows to the corresponding RP that needs to adjust traffic, so that the RP is configured to the first service in the RP according to the new traffic value.
- the flow is flow controlled.
- the computing unit comprises:
- a first selection sub-unit configured to select a preset number of RPs from the specified RP according to the priority, and select the preset number of RPs as the RP that needs to adjust the traffic;
- the second selection sub-unit selects a preset proportion RP of the specified RP from the specified RP according to the priority, and selects the preset proportion RP as the RP that needs to adjust the traffic.
- the designated RP is an RP that also configures an information rate CIR value and a peak information rate PIR value.
- the calculating unit includes:
- the third selection sub-unit determines, for each designated RP, whether the traffic of the first service flow in the RP is greater than the CIR of the RP, and selects the RP of the first service flow that is greater than the CIR as the RP that needs to adjust the traffic.
- the traffic monitoring information includes: a buffering state of the first service flow corresponding queue in the RP; the calculating unit includes:
- the fourth selection sub-unit is configured to select, from the RP that reports the traffic monitoring information of the first service flow, the RP whose buffer status is the overflow RP as the RP that needs to adjust the traffic.
- the traffic monitoring information includes: a traffic of the first service flow; the calculating unit further includes:
- a first calculation subunit configured to calculate a ratio between an entry rate of the first service flow and a maximum egress bandwidth in the CP, and calculate a product between the flow rate reported by the RP that needs to adjust the traffic and the ratio, where The product is used as the new traffic value of the first service flow in the RP that needs to adjust the traffic;
- a second calculating sub-unit configured to calculate a first difference between a maximum egress bandwidth of the first service flow in the CP and a total traffic of the first service flow in the non-designated RP, and calculate an entry rate of the first service flow in the CP Calculating a ratio of the first difference to the second difference, and calculating a ratio of the flow rate of the RP reported by the RP to the second difference of the traffic of the first service flow in the non-designated RP.
- the new traffic value of the first service flow in the RP that needs to adjust the traffic.
- the RP is configured to report traffic monitoring information of the first service flow to the CP, and receive a new traffic value of the first service flow sent by the CP, and perform flow control on the first service flow in the RP according to the new traffic value;
- the CP is configured to receive the traffic monitoring information of the first service flow reported by the RP.
- the traffic monitoring information of the first service flow reported by the received RP is from the designated RP.
- the RP that needs to adjust the traffic is determined, and the new traffic value of the first service flow in the RP that needs to adjust the traffic is calculated according to the traffic monitoring information; the designated RP has a traffic monitoring function;
- the new traffic value of the first service flow is sent to the corresponding RP that needs to adjust the traffic, so that the RP performs flow control on the first service flow in the RP according to the new traffic value.
- the traffic monitoring information of the first service flow reported by the RP is received.
- the traffic monitoring information of the first service flow reported by the received RP is determined from the designated RP.
- the RP, and the new traffic value of the first service flow in the RP that needs to adjust the traffic is calculated according to the traffic monitoring information; the designated RP has a traffic monitoring function; each of the first services to be calculated
- the new traffic value of the flow is sent to the corresponding RP that needs to adjust the traffic, so that the RP performs flow control on the first service flow in the RP according to the new traffic value. Therefore, in the embodiment of the present application, only the RP that needs to adjust the traffic is selected from the designated RP.
- the selected RP that needs to adjust the traffic is more accurate, thereby improving the network traffic control performance.
- calculating, according to the traffic monitoring information, a new traffic value of the first service flow in the RP that needs to adjust the traffic, and the RP performs flow control on the first service flow in the RP according to the new traffic value Compared with the prior art, the selected RP performs traffic deceleration according to a fixed algorithm, and the flow control in the RP is more accurate, which also improves the network traffic control performance.
- FIG. 1 is a schematic diagram of a prior art CN technology
- FIG. 2 is a schematic diagram of a first embodiment of a flow control method according to the present application
- 3 is a schematic diagram of a second embodiment of a flow control method according to the present application
- FIG. 4 is a schematic diagram of a flow control device of the present application.
- Figure 5 shows the configuration of the CP and RP in the metropolitan area OTN network. detailed description
- the CP randomly selects one frame of the packet, and sends the control information to the RP that sends the framed message.
- the RP that sends the frame packet is not the RP that causes the data stream to be congested.
- the RP that sends the frame packet reduces the transmission rate of the data stream, which may not solve the problem of congestion of the data stream, and affects the traffic control performance of the Ethernet.
- the embodiment of the present application provides a flow control method, device, and network, which can improve the performance of network flow control.
- the method provided by the embodiment of the present application can be applied to a data exchange network, such as an Ethernet, an IP network, or an OTN network.
- a data exchange network such as an Ethernet, an IP network, or an OTN network.
- data is forwarded and exchanged in the form of a data packet.
- the network includes a congestion point CP and a reaction point RP.
- FIG. 2 is a schematic diagram of a first embodiment of a flow control method of the present application, which can be applied to a CP. As shown in Figure 2, the method includes:
- Step 201 Receive traffic monitoring information of the first service flow reported by the RP.
- Step 202 When the congestion status of the first service flow in the CP meets the congestion condition, determine, according to the received traffic monitoring information of the first service flow, the RP that needs to adjust the traffic from the specified RP, and calculate, according to the traffic monitoring information, a new traffic value of the first service flow in the RP that needs to adjust the traffic; the designated RP has a traffic monitoring function;
- Step 203 Send the calculated new traffic value of each of the first service flows to the corresponding RP that needs to adjust the traffic, so that the RP performs flow control on the first service flow in the RP according to the new traffic value.
- the traffic monitoring information of the first service flow reported by the received response point RP is determined from the designated RP to adjust the traffic.
- RP and calculating, according to the traffic monitoring information, a new traffic value of the first service flow in each RP that needs to adjust traffic; the designated RP has a traffic monitoring function; and each of the first service flows to be calculated
- the new traffic value is sent to the corresponding RP that needs to adjust the traffic, so that the RP performs flow control on the first service flow in the RP according to the new traffic value. Therefore, in the embodiment of the present application, only the RP that needs to adjust the traffic is selected from the designated RP, compared to the prior art.
- FIG. 3 is a schematic diagram of a second embodiment of a flow control method according to the present application. As shown in FIG. 3, the method includes: Step 301: The RP monitors the first service flow, and reports traffic monitoring information of the first service flow to the CP.
- the RP is an RP with traffic monitoring function in the network, and may be all in the network.
- the traffic monitoring information of the RP that reports the first service flow may be preset in a specific implementation, which is not limited herein.
- the first service flow refers to: any one of all service flows or a pre-designated service flow.
- the traffic monitoring information includes: current traffic of the first service flow in the RP, current queue cache status, and the like.
- the current time is the time when the RP reports the first service flow to the CP.
- the current queue cache status includes: overflow, normal, and so on.
- the RP may report the traffic monitoring information of the first service flow to the CP actively or periodically, specifically:
- the traffic threshold value of the first service flow and/or the queue cache state threshold may be set in advance in the RP, so that the The traffic monitoring information of the first service flow reported to the CP may include:
- the RP monitors that the traffic of the first service flow exceeds the traffic threshold, and/or, when the RP monitors that the queue cache state of the first service flow exceeds the queue cache state threshold, the RP reports the first to the CP. Traffic monitoring information for traffic flows.
- the reporting period may be set in the RP, and the traffic monitoring information of the first service flow reported to the CP may include:
- the RP reports the traffic monitoring information of the first service flow to the CP.
- the traffic monitoring information may be carried in the out-of-band signaling or the low-latency packet, and the traffic control information may be transmitted to the CP through the outband signaling or the low-delay packet. .
- Step 302 The CP receives the traffic monitoring information reported by the RP.
- Step 303 When the congestion status of the first service flow in the CP meets the congestion condition, the CP specifies
- the RP determines the RP that needs to adjust the traffic, and calculates a new traffic value of the first service flow in the RP that needs to adjust the traffic according to the traffic monitoring information; the designated RP is an RP that has a traffic monitoring function.
- the congestion condition includes: the buffer queue overflow of the first service flow, or the entry rate of the first service flow is greater than the maximum egress bandwidth, or the buffer queue length of the first service flow is greater than a preset length threshold, or the first service flow.
- the entry rate is greater than the preset rate threshold.
- the CP determines whether the congestion status of the first service flow satisfies the congestion condition, and the CP may: determine, according to the information acquired by the CP, whether the congestion status of the first service flow meets the congestion condition; or the CP determines the first according to the traffic monitoring information reported by the RP. Whether the congestion status of the service flow satisfies the congestion condition.
- the CP determines whether the congestion status of the first service flow meets the congestion condition according to the information obtained by the CP.
- the CP may determine whether the CP itself has a buffer queue overflow, or the CP determines whether the current cache queue length of the CP itself is greater than a preset length. Threshold. When the CP determines that there is a buffer queue overflow or the current buffer queue length is greater than a preset length threshold, it determines that the congestion status of the first service flow satisfies the congestion condition.
- the CP determines whether the congestion status of the first service flow meets the congestion condition according to the traffic monitoring information reported by the RP.
- the traffic monitoring information reported by the RP may include the current traffic of the first service flow in the RP, the current queue cache state, and the like.
- the CP determines that the RP has a cache queue overflow or the current cache queue length of the RP is greater than a preset length threshold according to the current queue cache status reported by the RP, it determines that the congestion status of the first service flow meets the congestion condition.
- the congestion of the first service flow is determined according to the current traffic information of the first service flow reported by the RP.
- the state satisfies the congestion condition.
- each RP is related to the first data stream Configuration information of CIR (Committed Information Rate) and PIR (Peak Information Rate).
- CIR Committed Information Rate
- PIR Peak Information Rate
- Table 1 the information shown in Table 1 is recorded by means of a table or a data table or the like.
- the CP can obtain the specific values of whether the CIR and PIR of the first data stream in each RP are configured and configured. For example, in Table 1, RP1 and RP4 are configured with both CIR and PIR, while RP2 and RP3 are configured with only CIR and no PIR. Therefore, CIR and PIR are not configured at the same time.
- the RP In practical applications, if the RP is only configured with CIR, it indicates that the traffic of the first data stream in these RPs has a small change and must ensure that the data stream is equal to the bandwidth of the CIR value. For these RPs, it is generally not necessary to adjust the RP.
- the traffic value of the first service flow In practical applications, if the RP is only configured with CIR, it indicates that the traffic of the first data stream in these RPs has a small change and must ensure that the data stream is equal to the bandwidth of the CIR value. For these RPs, it is generally not necessary to adjust the RP.
- the traffic value of the first service flow In practical applications, if the RP is only configured with CIR, it indicates that the traffic of the first data stream in these RPs has a small change and must ensure that the data stream is equal to the bandwidth of the CIR value. For these RPs, it is generally not necessary to adjust the RP. The traffic value of the first service flow.
- the part RP when the part RP is configured to report the traffic monitoring information of the first service flow in step 301, when the part of the RP is selected, the RP of the CIR and the PIR may be selected, that is, the designated RP, or Specifies a partial RP in the RP.
- the RP that determines the traffic to be adjusted from the specified RP may include:
- the preset RP of the specified RP is selected according to the priority of the specified RP, and the selected preset RP is used as the RP that needs to adjust the traffic; or
- the designated RP is an RP that is also configured with a CIR value and a PIR value. That is, the designated RP is configured with a CIR value and a PIR value in addition to the traffic monitoring function.
- determining, from the designated RP, that the RP needs to adjust the traffic may include:
- the RP whose traffic of the first service flow is larger than the CIR is selected as the RP that needs to adjust the traffic.
- the designated RP is an RP with traffic monitoring function.
- the RP with the traffic monitoring function is the RP that can monitor the traffic of the RP and report the traffic monitoring information of the service flow to the CP.
- the RP that selects a preset number of RPs from the specified RP or selects a preset number of RPs according to the priority may include: selecting from the specified RP according to the priority of the RP or according to the service flow from the designated RP. Priority selection.
- the RP is selected according to the preference of the RP.
- the RP has a high priority.
- the RP with a high number of cross-service flows has a high priority.
- a RP with a high number of cross traffic flows This is because RPs with multiple traffic flows tend to cause congestion, so they are prioritized as RPs that need to adjust traffic, which can effectively improve network traffic control performance.
- the RP is selected according to the priority of the service flow in the specified RP.
- the RP with the low priority service flow is preferentially adjusted.
- the priority of each service flow is preset.
- the service flow with high priority often requires higher bandwidth quality and low-latency transmission. Therefore, when determining the RP that needs to adjust traffic, the priority adjustment is low.
- the RP of the priority service flow is selected according to the priority of the service flow in the specified RP.
- the specific number of the preset number and the preset ratio is not limited herein, and may be set autonomously in an actual application.
- the traffic monitoring information includes: when the RP in the RP is in the cache state of the corresponding queue, the RP that needs to adjust the traffic from the specified RP may include:
- the RP that selects the cache state of the queue is the overflow RP as the RP that needs to adjust the traffic.
- the traffic monitoring information includes: the traffic of the first service flow; the calculating, according to the traffic monitoring information, the new traffic value of the first service flow in the RP that needs to adjust the traffic, including:
- the network includes four RPs listed in Table 1, and the maximum outgoing bandwidth of the first service flow in the CP is 100 Mbps.
- the traffic of the first service flow reported by RP1 is 30M, which is reported by RP4.
- the calculating, according to the traffic monitoring information, the new traffic value of the first service flow in the RP that needs to adjust the traffic may include:
- the weight of each RP may be calculated for the CIR value in the RP that adjusts the traffic according to each requirement, and the product obtained by multiplying the traffic reported by the RP that needs to adjust the traffic with the corresponding weight is used as the required adjustment.
- the new traffic value of the first service flow in the RP of the traffic, etc., is not described here.
- Step 304 The CP sends the calculated new traffic value of each of the first service flows to the corresponding RP that needs to adjust the traffic.
- the control information sent by the CP to the selected RP is generally sent through the data frame, and the data frame carrying the control information is forwarded to the destination RP through the network in the same forwarding manner as the normal data frame.
- the destination RP is prolonged when it receives the data frame carrying the control information. Accordingly, the data transmission rate is shortened according to the control information. Therefore, the destination RP performs flow control. Time lags far behind the moment of congestion, which also affects the flow control performance of Ethernet.
- the new traffic value in order to reduce the transmission delay generated by the CP transmitting the new traffic value to the RP, the new traffic value may also be carried in the outband signaling or the low delay packet.
- the outband signaling or low-latency packet sends the flow control information to the RP, which reduces the transmission delay of the new traffic value between the CP and the RP, and further improves the network traffic control performance.
- Step 305 The RP performs flow control on the first service flow in the RP according to the new traffic value.
- the RP performs flow control on the first service flow in the RP according to the new traffic value.
- the RP reduces the traffic of the first service flow to the new traffic value.
- the RP performs flow control on the first service flow in the RP according to the new traffic value, including:
- the Ethernet traffic control method shown in FIG. 3 compares the flow control information and/or the new traffic value of the first service flow by using out-of-band signaling or low-latency packets compared to the embodiment of the present application shown in FIG. 2 . , thereby reducing the data transmission delay between the CP and the RP, and further improving the network traffic control performance.
- the embodiment of the present application further provides a flow control device. As shown in FIG. 4, the device includes:
- the receiving unit 410 is configured to receive the traffic monitoring information of the first service flow reported by the RP, where the calculating unit 420 is configured to: when the congestion state of the first service flow in the CP meets the congestion condition, according to the first service flow reported by the receiving RP
- the traffic monitoring information is used to determine the RP that needs to adjust the traffic from the specified RP, and the new traffic value of the first service flow in the RP that needs to adjust the traffic is calculated according to the traffic monitoring information received by the receiving unit; Traffic monitoring function;
- the sending unit 430 is configured to send, by the computing unit, a new traffic value of each of the first service flows to the corresponding RP that needs to adjust the traffic, so that the RP is the first one of the RPs according to the new traffic value. Traffic flow is controlled by traffic.
- the computing unit 420 can include:
- a first selection sub-unit configured to select a preset number of RPs from the specified RP according to the priority, and select the preset number of RPs as the RP that needs to adjust the traffic;
- the second selection sub-unit selects a preset proportion RP of the specified RP from the specified RP according to the priority, and selects the preset proportion RP as the RP that needs to adjust the traffic.
- the designated RP is an RP that is also configured with a CIR value and a PIR value, that is, the designated RP is configured with a CIR value and a PIR value in addition to the traffic monitoring function.
- the computing unit 420 can include: The third selection sub-unit determines, for each designated RP, whether the traffic of the first service flow in the RP is greater than the CIR of the RP, and selects the RP whose traffic of the first service flow is greater than the CIR as the RP that needs to adjust the traffic.
- the traffic monitoring information includes: a buffering state of the first service flow corresponding queue in the RP; the calculating unit 420 may include:
- the fourth selection sub-unit is configured to select, from the RP that reports the traffic monitoring information of the first service flow, the RP whose buffer status is the overflow RP as the RP that needs to adjust the traffic.
- the traffic monitoring information includes: the traffic of the first service flow; the calculating unit 420 may further include:
- a first calculation subunit configured to calculate a ratio between an entry rate of the first service flow and a maximum egress bandwidth in the CP, and calculate a product between the flow rate reported by the RP that needs to adjust the traffic and the ratio, where The product is used as the new traffic value of the first service flow in the RP that needs to adjust the traffic;
- a second calculating sub-unit configured to calculate a first difference between a maximum egress bandwidth of the first service flow in the CP and a total traffic of the first service flow in the non-designated RP, and calculate an entry rate of the first service flow in the CP Calculating a ratio of the first difference to the second difference, and calculating a ratio of the flow rate of the RP reported by the RP to the second difference of the traffic of the first service flow in the non-designated RP.
- the new traffic value of the first service flow in the RP that needs to adjust the traffic.
- the designated RP is an RP configured with a 7N information rate CIR value and a peak information rate PIR value, and has a traffic monitoring function.
- the sending unit sends the new traffic value of each of the first service flows calculated by the computing unit to the corresponding RP that needs to adjust the traffic, so as to receive the new traffic.
- the value RP reconfigures the respective CIR value and PIR value according to the received new traffic value, so as to control the traffic of the first service flow.
- both the CIR value and the PIR value in the PR can be configured as the new traffic value sent by the sending unit received by the RP.
- the foregoing is only one example of configuring the CIR value and the PIR value of each RP according to the new traffic value. It can be understood that there are multiple configurations, which are not limited by the present invention.
- the RP has a traffic monitoring function; the calculated new traffic value of each of the first service flows is sent to the corresponding RP that needs to adjust traffic, so that the RP is in the RP according to the new traffic value.
- the first traffic flow is flow controlled. Therefore, in the embodiment of the present application, only the RP that needs to adjust the traffic is selected from the designated RP.
- the selected RP that needs to adjust the traffic is more accurate, thereby improving the network traffic control performance.
- calculating, according to the traffic monitoring information, a new traffic value of the first service flow in the RP that needs to adjust the traffic, and the RP performs flow control on the first service flow in the RP according to the new traffic value Compared with the prior art, the selected RP performs traffic deceleration according to a fixed algorithm, and the flow control in the RP is more accurate, which also improves the network traffic control performance.
- the application also provides a data exchange network, the network including a reaction point RP and a congestion point
- the reaction point RP is used to report traffic monitoring information of the first service flow to the congestion point CP; and receive a new traffic value of the first service flow sent by the congestion point CP, according to the new traffic value in the reaction point RP
- the first service flow performs flow control
- the congestion point CP is configured to receive the traffic monitoring information of the first service flow reported by the reaction point RP.
- the flow rate monitoring information of the flow determines the reaction point RP of the flow that needs to be adjusted from the specified reaction point RP, and calculates a new flow value of the first service flow in the reaction point RP of each of the need to adjust the flow according to the flow monitoring information;
- the designated reaction point RP has a traffic monitoring function; and the calculated new traffic value of each of the first service flows is sent to the corresponding reaction point RP that needs to adjust the traffic, so that the reaction point RP is based on the new traffic value.
- Flow control is performed on the first service flow in the reaction point RP.
- the designated RP is an RP configured with a 7-noise information rate CIR value and a peak information rate PIR value, and the RP has a traffic monitoring function.
- the CP may be integrated with the flow control device described in the foregoing embodiments.
- a method of configuring a CP and an RP in the data exchange network is described.
- a metropolitan area network access point such as a Layer 3 switch, Layer 3 Switch, L3SW
- a service processing point such as a service router, Service) Router, SR.
- Each node in the metro OTN network integrates OTN functions and Ethernet switching functions.
- the service aggregation node in the network can be selected as the CP.
- the node connected to the service processing point can be selected as the CP. After the CP is confirmed, you need to configure the corresponding RP.
- One CP can configure multiple RPs.
- the RP can be automatically selected or manually selected by the network management system according to the network topology and service configuration information. Specifically, the RP is generally selected according to the service traffic of the node and the number of service connections, for example, a node whose service traffic is greater than 50% of the line rate, or a node whose service connection number is greater than the average number of nodes.
- a node through which a service connection passes can be used as an RP to perform flow control specifically for this flow.
- the storage medium may be, for example, a ROM/RAM, a magnetic disk, an optical disk, or the like.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
一种流量控制方法及装置,方法包括:接收反应点RP上报的第一业务流的流量监控信息;当拥塞点CP中第一业务流的拥塞状态满足拥塞条件时,根据接收的流量监控信息从指定反应点RP中确定需要调整流量的反应点RP,并且,根据所述流量监控信息计算出各个所述需要调整流量的反应点RP中第一业务流的新流量值;所述指定反应点RP具备流量监控功能;将计算出的各个所述第一业务流的新流量值发送给对应的所述需要调整流量的反应点RP,以便所述反应点RP根据新流量值对该反应点RP中的第一业务流进行流量控制。本申请能够提高对于网络流量的控制性能。
Description
一种流量控制方法、 装置及网络
技术领域 本申请涉及通信领域, 尤其涉及一种流量控制方法、 装置及网络。 背景技术
以太网技术以其开放标准、 高性能、 低廉价格、 众多厂商支持等因素击败 令牌环、 FDDI和 ATM等技术, 成为 LAN技术的通用接口。 随着使用以太网 技术的新业务和新应用不断涌现,如何保证网络应用的端到端 QoS , 已经成为 以太网技术面临的最大挑战。
为了解决该问题, IEEE在 802.1Qau标准中定义了一种拥塞指示 ( CN,
Congestion Notification )方法, 以实现以太网端到端流量控制, 增强以太网的 端到端 QoS能力。
在所述 CN 方法中, 首先需要配置以太网交换机网络中的拥塞点 (CP, Congestion Point )和反应点 ( RP, Reaction Point ), 如图 1所示, 可以将以太 网交换机网络中的某个以太网交换机配置为 CP, 与以太网交换机连接的其他 节点配置为 RP, —个 CP对应网络边缘的多个 RP。 如图 1所示, 图中两个节 点之间 (例如 RP点与 RP点之间、 CP点与 RP之间)具有两个圓形端点的连 线表示节点之间的物理链路。 在图 1中, 从 CP点出发, 指向各 RP点带有箭 头的线表示控制信息的传递方向。
对于每一数据流, CP根据该数据流的出端口队列长度和队列增长速度计 算反馈信息(Fb, Feedback Information ), 如果 Fb<0, 表示该数据流的出端口 队列拥塞概率加大, CP以一定的概率 P从接收到的该数据流的后续报文中随 机选择一帧报文, 向发送该帧报文的 RP发送控制信息, 控制信息中包含 Fb、 拥塞点 ID等信息; RP接收到所述控制信息后, 按照一定的算法, 例如乘法倍 减方法等降低所述数据流的发送速率,并且在设定的固定周期内没有接收到新 的控制信息时, 重新增加该数据流的发送速率, 直到达到该数据流的发送速率 上限。 上述过程不断重复, 实现以太网的网络级流量控制。
申请人发现: 现有的以太网流量控制方法对以太网流量的控制性能差。
发明内容
有鉴于此, 本申请要解决的技术问题是, 提供一种流量控制方法、 装置及 网络, 能够提高对于网络流量的控制性能。
为此, 本申请实施例采用如下技术方案:
根据本申请实施例的第一方面, 公开了一种流量控制方法, 包括: 接收反应点 RP上报的第一业务流的流量监控信息;
当拥塞点 CP中第一业务流的拥塞状态满足拥塞条件时, 根据接收的 RP 上报的第一业务流的流量监控信息从指定 RP中确定需要调整流量的 RP, 并 且, 根据所述流量监控信息计算出各个所述需要调整流量的 RP中第一业务流 的新流量值; 所述指定 RP具备流量监控功能;
将计算出的各个所述第一业务流的新流量值发送给对应的所述需要调整 流量的 RP,以便所述 RP根据新流量值对该 RP中的第一业务流进行流量控制。
在第一方面的可能的第一种实现方式中, 根据接收的 RP上报的第一业务 流的流量监控信息从指定 RP中确定需要调整流量的 RP包括:
从指定 RP中按照优先级选择预设数量个 RP, 将选择的所述预设数量个
RP作为需要调整流量的 RP; 或者,
从指定 RP中按照优先级选择指定 RP总数的预设比例个 RP,将选择的所 述预设比例个 RP作为需要调整流量的 RP。
在第一方面的可能的第二种实现方式中, 所述指定 RP为还同时配置了承 诺信息速率 CIR值和峰值信息速率 PIR值的 RP。
在第一方面的可能的第三种实现方式中, 根据接收的 RP上报的第一业务 流的流量监控信息从指定 RP中确定需要调整流量的 RP包括:
对于每个指定 RP, 确定 RP中第一业务流的流量是否大于该 RP的 CIR, 选择第一业务流的流量大于 CIR的 RP作为需要调整流量的 RP。
在第一方面的可能的第四种实现方式中, 所述流量监控信息包括: RP中 第一业务流对应队列的緩存状态; 根据接收的 RP上报的第一业务流的流量监 控信息确定需要调整流量的 RP包括:
从上报第一业务流的流量监控信息的 RP中, 选择队列的緩存状态为溢出 的 RP作为需要调整流量的 RP。
在第一方面的可能的第五种实现方式中, 所述流量监控信息包括: 第一业 务流的流量; 所述根据所述流量监控信息计算出各个所述需要调整流量的 RP 中第一业务流的新流量值包括:
计算 CP中第一业务流的进入速率与最大出口带宽之间的比值, 计算所述 需要调整流量的 RP上报的流量与所述比值之间的乘积, 将所述乘积作为该需 要调整流量的 RP中第一业务流的新流量值; 或者,
计算 CP中第一业务流的最大出口带宽与所有非指定 RP中第一业务流的 流量总和的第一差值, 并且, 计算 CP中第一业务流的进入速率与所有非指定 RP中第一业务流的流量总和的第二差值, 计算第一差值与第二差值的比值, 将需要调整流量的 RP上报的流量与所述比值相乘得到的乘积作为该需要调整 流量的 RP中第一业务流的新流量值。
在第一方面的可能的第六种实现方式中,所述第一业务流的流量监控信息 通过带外信令或者低延时报文传输; 和 /或,
所述第一业务流的新流量参数通过带外信令或者低延时报文传输。
在第一方面的可能的第七种实现方式中, 所述 RP根据新流量值对该 RP 中的第一业务流进行流量控制包括:
所述 RP将第一业务流的流量降速为所述新流量值。
在第一方面的可能的第八种实现方式中, 所述 RP根据新流量值对该 RP 中的第一业务流进行流量控制包括:
将 RP中的承诺信息速率 CIR和 /或峰值信息速率 PIR配置为所述新流量 值。
根据本申请实施例的第二方面, 公开了一种流量控制装置, 包括: 接收单元, 用于接收反应点 RP上报的第一业务流的流量监控信息; 计算单元, 用于当拥塞点 CP中第一业务流的拥塞状态满足拥塞条件时, 根据接收的 RP上报的第一业务流的流量监控信息从指定 RP中确定需要调整 流量的 RP, 并且, 根据接收单元接收到的流量监控信息计算出各个所述需要 调整流量的 RP中第一业务流的新流量值; 所述指定 RP具备流量监控功能;
发送单元,用于将计算单元计算出的各个所述第一业务流的新流量值发送 给对应的所述需要调整流量的 RP,以便所述 RP根据新流量值对该 RP中的第 一业务流进行流量控制。
在第二方面的可能的第一种实现方式中, 计算单元包括:
第一选择子单元, 用于从指定 RP中按照优先级选择预设数量个 RP, 将 选择的所述预设数量个 RP作为需要调整流量的 RP; 或者,
第二选择子单元, 从指定 RP中按照优先级选择指定 RP总数的预设比例 个 RP, 将选择的所述预设比例个 RP作为需要调整流量的 RP。
在第二方面的可能的第二种实现方式中, 所述指定 RP为还同时配置了承 诺信息速率 CIR值和峰值信息速率 PIR值的 RP。
在第二方面的可能的第三种实现方式中, 计算单元包括:
第三选择子单元, 对于每个指定 RP, 确定 RP中第一业务流的流量是否 大于该 RP的 CIR, 选择第一业务流的流量大于 CIR的 RP作为需要调整流量 的 RP。
在第二方面的可能的第四种实现方式中, 所述流量监控信息包括: RP中 第一业务流对应队列的緩存状态; 计算单元包括:
第四选择子单元, 用于从上报第一业务流的流量监控信息的 RP中, 选择 队列的緩存状态为溢出的 RP作为需要调整流量的 RP。
在第二方面的可能的第五种实现方式中, 所述流量监控信息包括: 第一业 务流的流量; 计算单元还包括:
第一计算子单元, 用于计算 CP中第一业务流的进入速率与最大出口带宽 之间的比值,计算所述需要调整流量的 RP上报的流量与所述比值之间的乘积, 将所述乘积作为该需要调整流量的 RP中第一业务流的新流量值; 或者,
第二计算子单元, 用于计算 CP中第一业务流的最大出口带宽与所有非指 定 RP中第一业务流的流量总和的第一差值, 并且, 计算 CP中第一业务流的 进入速率与所有非指定 RP中第一业务流的流量总和的第二差值, 计算第一差 值与第二差值的比值, 将需要调整流量的 RP上报的流量与所述比值相乘得到 的乘积作为该需要调整流量的 RP中第一业务流的新流量值。
根据本申请实施例的第三方面,公开了一种数据交换网络, 所述网络包括 RP和 CP, 其中,
所述 RP用于向 CP上报第一业务流的流量监控信息; 以及接收所述 CP 发送的第一业务流的新流量值, 根据新流量值对该 RP中的第一业务流进行流 量控制;
所述 CP用于接收 RP上报的第一业务流的流量监控信息; 当 CP中第一 业务流的拥塞状态满足拥塞条件时, 根据接收的 RP上报的第一业务流的流量 监控信息从指定 RP中确定需要调整流量的 RP, 并且, 根据所述流量监控信 息计算出各个所述需要调整流量的 RP中第一业务流的新流量值; 所述指定 RP具备流量监控功能; 将计算出的各个所述第一业务流的新流量值发送给对 应的所述需要调整流量的 RP,以便所述 RP根据新流量值对该 RP中的第一业 务流进行流量控制。
对于上述技术方案的技术效果分析如下:
接收 RP上报的第一业务流的流量监控信息; 当 CP中第一业务流的拥塞 状态满足拥塞条件时, 根据接收的 RP上报的第一业务流的流量监控信息从指 定 RP中确定需要调整流量的 RP, 并且, 根据所述流量监控信息计算出各个 所述需要调整流量的 RP中第一业务流的新流量值; 所述指定 RP具备流量监 控功能;将计算出的各个所述第一业务流的新流量值发送给对应的所述需要调 整流量的 RP,以便所述 RP根据新流量值对该 RP中的第一业务流进行流量控 制。 从而, 本申请实施例中仅从指定 RP 中选择需要调整流量的 RP, 相较于 现有技术中随机选择一个 RP, 所选择的需要调整流量的 RP更为准确, 从而 提高了网络流量控制性能; 而且,根据所述流量监控信息计算出各个所述需要 调整流量的 RP中第一业务流的新流量值, 所述 RP根据新流量值对该 RP中 的第一业务流进行流量控制, 相较于现有技术中由被选择的 RP按照某种固定 的算法进行流量降速, RP中的流量控制更为准确, 同样提高了网络流量控制 性能。 附图说明
图 1为现有技术 CN技术示意图;
图 2为本申请流量控制方法第一实施例示意图;
图 3为本申请流量控制方法第二实施例示意图;
图 4为本申请流量控制装置示意图;
图 5为城域 OTN网络的 CP和 RP配置示意图。 具体实施方式
现有技术中进行以太网流量控制时, CP随机选择一帧报文, 向发送该帧 报文的 RP发送控制信息, 并不能保证发送该帧报文的 RP就是造成数据流拥 塞的 RP, 因此, 发送该帧报文的 RP降低数据流的发送速率可能无法达到解 决数据流拥塞的问题, 影响了以太网的流量控制性能。
基于此, 本申请实施例提供一种流量控制方法、 装置及网络, 能够提高网 络流量控制的性能。本申请实施例提供的方法可以应用于数据交换网络, 例如 以太网、 IP网、 OTN网络, 在上述网络中, 以数据包的形式转发、 交换数据。 所述网络包括拥塞点 CP和反应点 RP。
图 2是本申请流量控制方法第一实施例示意图,该方法可以适用于 CP中。 如图 2所示, 该方法包括:
步骤 201: 接收 RP上报的第一业务流的流量监控信息;
步骤 202: 当 CP中第一业务流的拥塞状态满足拥塞条件时, 根据接收的 第一业务流的流量监控信息从指定 RP中确定需要调整流量的 RP, 并且, 根 据所述流量监控信息计算出各个所述需要调整流量的 RP中第一业务流的新流 量值; 所述指定 RP具有流量监控功能;
步骤 203: 将计算出的各个所述第一业务流的新流量值发送给对应的所述 需要调整流量的 RP, 以便所述 RP根据新流量值对该 RP中的第一业务流进行 流量控制。
图 2所示的流量控制方法中, 当 CP中第一业务流的拥塞状态满足拥塞条 件时, 根据接收的反应点 RP上报的第一业务流的流量监控信息从指定 RP中 确定需要调整流量的 RP, 并且, 根据所述流量监控信息计算出各个所述需要 调整流量的 RP中第一业务流的新流量值; 所述指定 RP具备流量监控功能; 将计算出的各个所述第一业务流的新流量值发送给对应的所述需要调整流量 的 RP, 以便所述 RP根据新流量值对该 RP中的第一业务流进行流量控制。 从 而, 本申请实施例中仅从指定 RP 中选择需要调整流量的 RP, 相较于现有技
术中随机选择一个 RP, 所选择的需要调整流量的 RP更为准确, 从而提高了 网络流量控制性能; 而且,根据所述流量监控信息计算出各个所述需要调整流 量的 RP中第一业务流的新流量值, 所述 RP根据新流量值对该 RP中的第一 业务流进行流量控制, 相较于现有技术中由被选择的 RP按照某种固定的算法 进行流量降速, RP中的流量控制更为准确, 同样提高了网络流量控制性能。 图 3为本申请流量控制方法第二实施例示意图,如图 3所示,该方法包括: 步骤 301: RP对第一业务流进行监控, 向 CP上报第一业务流的流量监控 信息;
其中, 所述 RP为网络中具有流量监控功能的 RP, 可以是网络中的全部
RP, 或者也可以为部分 RP。 具体哪些 RP上报第一业务流的流量监控信息可 以在具体实现中预先设置, 这里不限定。
其中, 所述第一业务流是指: 所有业务流中的任一业务流或者预先指定的 某一业务流。
所述流量监控信息包括: 该 RP中第一业务流当前的流量、 当前队列緩存 状态等。 所述当前是指 RP向 CP上报第一业务流的时刻。 当前队列緩存状态 包括: 溢出、 正常等状态。
这里, RP可以主动或者定时向 CP上报所述第一业务流的流量监控信息, 具体的:
( 1 )当 RP主动向 CP上报所述第一业务流的流量监控信息时, 可以预先 在 RP中设定第一业务流的流量门限值和 /或队列緩存状态门限值,从而所述向 CP上报第一业务流的流量监控信息可以包括:
RP监控到所述第一业务流的流量超过所述流量门限值, 和 /或, RP监控 到第一业务流的队列緩存状态超过所述队列緩存状态门限值时, 向 CP上报第 一业务流的流量监控信息。
( 2 )当 RP定时向 CP上报所述第一业务流的流量监控信息时, 可以预先 在 RP中设定上报周期, 从而所述向 CP上报第一业务流的流量监控信息可以 包括:
每个上报周期到来时, RP向 CP上报第一业务流的流量监控信息。
其中, 为了减少 RP上报流量监控信息的延时, 可以将流量监控信息携带 在带外信令或者低延时报文中,通过带外信令或者低延时报文将流量控制信息 传输给 CP。
步骤 302: CP接收 RP上报的流量监控信息。
步骤 303: 当 CP 中第一业务流的拥塞状态满足拥塞条件时, CP从指定
RP中确定需要调整流量的 RP, 并且, 根据所述流量监控信息计算出各个所述 需要调整流量的 RP中第一业务流的新流量值; 所述指定 RP为具有流量监控 功能的 RP。
其中, 所述拥塞条件包括: 第一业务流的緩存队列溢出、 或者第一业务流 的进入速率大于最大出口带宽、或者第一业务流的緩存队列长度大于预设长度 阈值、 或者第一业务流的进入速率大于预设速率阈值。
具体的, CP判断第一业务流的拥塞状态是否满足拥塞条件可以包括: CP 根据自身获取的信息判断第一业务流的拥塞状态是否满足拥塞条件; 或者 CP 根据 RP上报的流量监控信息判断第一业务流的拥塞状态是否满足拥塞条件。
具体实现时, CP根据自身获取的信息判断第一业务流的拥塞状态是否满 足拥塞条件可以包括: CP判断 CP自身当前是否有緩存队列溢出, 或者 CP判 断 CP 自身当前緩存队列长度是否大于预设长度阈值。 当 CP判断当前有緩存 队列溢出或者当前緩存队列长度大于预设长度阈值时,确定第一业务流的拥塞 状态满足拥塞条件。
另外一种可能的实现方式为, CP根据 RP上报的流量监控信息判断第一 业务流的拥塞状态是否满足拥塞条件。 其中, RP上报的流量监控信息可以包 括 RP中第一业务流当前的流量, 当前队列緩存状态等。 具体实现时, 当 CP 根据 RP上报的当前队列緩存状态判断 RP当前有緩存队列溢出或者 RP的当 前緩存队列长度大于预设长度阈值时,确定第一业务流的拥塞状态满足拥塞条 件。 或者, 当 CP根据 RP上报的第一业务流当前的流量信息判断第一业务流 的进入速率大于最大出口带宽或者第一业务流的进入速率大于预设速率阈值 时, 确定第一业务流的拥塞状态满足拥塞条件。
其中, 所述长度阈值、 速率阈值的具体数值可以在实际应用中自主设定, 这里并不限制。 其中, 在 CP中可以预先存储: 各个 RP中关于第一数据流的
CIR( Committed Information Rate,承 i若信息速率 )和 PIR( Peak Information Rate, 峰值信息速率)的配置信息。 例如, 通过表格或者数据表等方式记录例如表 1 所示的信息。 表 1
CP通过查找该表中记录的各个 RP的 CIR和 PIR即可得到各个 RP中第 一数据流的 CIR、 PIR是否进行了配置以及配置的具体数值。 例如, 表 1 中 RP1和 RP4同时配置了 CIR和 PIR, 而 RP2和 RP3则只配置了 CIR, 未配置 PIR, 因此并未同时配置 CIR和 PIR。
在实际应用中, 如果 RP只配置了 CIR, 则表明这些 RP中第一数据流的 流量变化小并且必须保证提供该数据流等于 CIR值的带宽,对于这些 RP而言, 一般并不需要调整其第一业务流的流量值。
实际上, 在步骤 301中设定部分 RP上报第一业务流的流量监控信息时, 在选择所述部分 RP时, 也可以选择同时配置了 CIR和 PIR的 RP, 也即所述 指定 RP, 或者指定 RP中的部分 RP。
其中, 从指定 RP中确定需要调整流量的 RP可以包括:
从指定 RP中按照优先级选择预设数量个 RP, 将选择的所述预设数量个 RP作为需要调整流量的 RP; 或者,
从指定 RP中按照优先级选择指定 RP总数的预设比例个 RP,将选择的所 述预设比例个 RP作为需要调整流量的 RP; 或者,
在一实施例中, 指定的 RP为还配置有 CIR值和 PIR值的 RP, 即该指定 的 RP除了具备流量监控的功能外,还配置有 CIR值和 PIR值。在该实施例中, 从指定 RP中确定需要调整流量的 RP可以包括:
对于每个指定 RP, 确定 RP中第一业务流的流量是否大于该 RP的 CIR,
选择第一业务流的流量大于 CIR的 RP作为需要调整流量的 RP。
在本发明的实施例中, 指定 RP为具备流量监控功能的 RP。 具备流量监 控功能的 RP是指能够对 RP自身流量进行监控, 并能够将业务流的流量监控 信息上报给 CP的 RP。
其中, 从指定 RP中按照优先级选择预设数量个 RP或者选择指定 RP总 数的预设比例个 RP具体可以包括: 从指定 RP中按照 RP的优先级进行选择 或者从指定 RP中按照业务流的优先级进行选择。
具体实现时, 从指定 RP中按照 RP的优选级进行选择具体为: 根据各 RP 具有的交叉业务流的数量, 进行优先级排序, 交叉业务流数量高的 RP具有高 优先级, 优先调整所述交叉业务流数量高的 RP。 这是因为, 具有多个业务流 通过的 RP往往容易造成堵塞, 因此将其作为需要调整流量的 RP进行优先调 整, 可以有效提高网络流量控制性能。
具体实现时, 从指定 RP中按照业务流的优先级进行选择具体为: 优先调 整具有低优先级业务流的 RP。 在以太网中, 预先设置了各业务流的优先级, 具有高优先级的业务流往往要求较高的带宽质量以及低延时传输, 因此,在确 定需要调整流量的 RP时, 优先调整具有低优先级业务流的 RP。
其中, 所述预设个数和预设比例的具体数值这里并不限定, 可以在实际应 用中自主设定。
其中, 所述流量监控信息包括: RP中第一业务流对应队列的緩存状态时, 所述从指定 RP中确定需要调整流量的 RP可以包括:
从上报第一业务流的流量监控信息的 RP中, 选择队列的緩存状态为溢出 的 RP作为需要调整流量的 RP。
所述流量监控信息包括: 第一业务流的流量; 所述根据所述流量监控信息 计算出各个所述需要调整流量的 RP中第一业务流的新流量值包括:
计算 CP中第一业务流的进入速率与最大出口带宽之间的比值, 计算所述 需要调整流量的 RP上报的流量与所述比值之间的乘积, 将所述乘积作为该需 要调整流量的 RP中第一业务流的新流量值。
例如,假设网络中包括表 1所记载的 4个 RP, CP中第一业务流的最大出 口带宽为 100Mbps。 假设 RP1上报的第一业务流的流量为 30M, RP4上报的
第一业务流的流量为 30M, 四个 RP中第一业务流的流量总和为 25 + 25 + 30 + 30 = 110, 大于最大出口带宽 100Mbps, 因此, RP1 的新流量值等于 30 χ 100/110=27Μ, 同样的, RP4的新流量值也等于 27Μ。
或者, 所述根据所述流量监控信息计算出各个所述需要调整流量的 RP中 第一业务流的新流量值可以包括:
计算 CP中第一业务流的最大出口带宽与所有非指定 RP中第一业务流的 流量总和的第一差值, 并且, 计算 CP中第一业务流的进入速率与所有非指定 RP中第一业务流的流量总和的第二差值, 计算第一差值与第二差值的比值, 将需要调整流量的 RP上报的流量与所述比值相乘得到的乘积作为该需要调整 流量的 RP中第一业务流的新流量值。
仍以上一个举例为例, 则, 第一差值 =100-25-25=50; 第二差值 =110-25-25=60; 则, RP1的新流量值 =30 χ 50/60=25; 同样的, RP4的新流量 值也等于 25Μ。
另外, 在实际应用中, 还可以为按照各个需要调整流量的 RP中的 CIR值 计算各个 RP对应的权重, 将需要调整流量的 RP上报的流量与对应的权重相 乘得到的乘积作为该需要调整流量的 RP中第一业务流的新流量值等, 这里不 赘述。
步骤 304: CP将计算出的各个所述第一业务流的新流量值发送给对应的 所述需要调整流量的 RP。
现有技术中, CP向选定的 RP发送的控制信息一般通过数据帧发送, 而 携带控制信息的数据帧与普通的数据帧采用相同的转发方式, 经过网络,逐跳 的转发到目的 RP, 数据帧的转发时延长并且不固定, 造成目的 RP收到携带 控制信息的数据帧的时延长,相应的,根据所述控制信息降低数据流发送速率 的时延长, 因此, 目的 RP进行流量控制的时间远远滞后于拥塞的发生时刻, 同样影响了以太网的流量控制性能。
基于此, 在本发明实施例中, 为了减少 CP将新流量值传输给 RP所产生 的传输延时,也可以将所述新流量值携带在带外信令或者低延时报文中,通过 带外信令或者低延时报文将流量控制信息发送给 RP,从而降低 CP与 RP之间 新流量值的传输延时, 进一步提高网络流量控制性能。
步骤 305: 所述 RP根据新流量值对该 RP中的第一业务流进行流量控制。 其中,所述 RP根据新流量值对该 RP中的第一业务流进行流量控制包括: 所述 RP将第一业务流的流量降速为所述新流量值。
当指定的 RP为配置有 CIR值和 PIR值的 RP, 则所述 RP根据新流量值 对该 RP中的第一业务流进行流量控制包括:
将 RP中的 CIR和 /或 PIR配置为所述新流量值。
图 3所示的以太网流量控制方法,相较于图 2所示的本申请实施例,通过 带外信令或者低延时报文传输流量控制信息和 /或第一业务流的新流量值, 从 而降低了 CP与 RP之间的数据传输延时, 进一步提高了网络流量控制性能。 与上述方法相对应的, 本申请实施例还提供一种流量控制装置, 如图 4 所示, 该装置包括:
接收单元 410, 用于接收 RP上报的第一业务流的流量监控信息; 计算单元 420, 用于当 CP中第一业务流的拥塞状态满足拥塞条件时, 根 据接收 RP上报的第一业务流的流量监控信息从指定 RP中确定需要调整流量 的 RP, 并且, 根据接收单元接收到的流量监控信息计算出各个所述需要调整 流量的 RP中第一业务流的新流量值; 所述指定 RP具备流量监控功能;
发送单元 430, 用于将计算单元计算出的各个所述第一业务流的新流量值 发送给对应的所述需要调整流量的 RP, 以便所述 RP根据新流量值对该 RP中 的第一业务流进行流量控制。
其中, 计算单元 420可以包括:
第一选择子单元, 用于从指定 RP中按照优先级选择预设数量个 RP, 将 选择的所述预设数量个 RP作为需要调整流量的 RP; 或者,
第二选择子单元, 从指定 RP中按照优先级选择指定 RP总数的预设比例 个 RP, 将选择的所述预设比例个 RP作为需要调整流量的 RP。
在一实施例中, 指定的 RP为还配置有 CIR值和 PIR值的 RP, 即该指定 的 RP除了具备流量监控的功能外,还配置有 CIR值和 PIR值。在该实施例中, 计算单元 420可以包括:
第三选择子单元, 对于每个指定 RP, 确定 RP中第一业务流的流量是否 大于该 RP的 CIR, 选择第一业务流的流量大于 CIR的 RP作为需要调整流量 的 RP。
其中, 所述流量监控信息包括: RP中第一业务流对应队列的緩存状态; 计算单元 420可以包括:
第四选择子单元, 用于从上报第一业务流的流量监控信息的 RP中, 选择 队列的緩存状态为溢出的 RP作为需要调整流量的 RP。
其中, 所述流量监控信息包括: 第一业务流的流量; 计算单元 420还可以 包括:
第一计算子单元, 用于计算 CP中第一业务流的进入速率与最大出口带宽 之间的比值,计算所述需要调整流量的 RP上报的流量与所述比值之间的乘积, 将所述乘积作为该需要调整流量的 RP中第一业务流的新流量值; 或者,
第二计算子单元, 用于计算 CP中第一业务流的最大出口带宽与所有非指 定 RP中第一业务流的流量总和的第一差值, 并且, 计算 CP中第一业务流的 进入速率与所有非指定 RP中第一业务流的流量总和的第二差值, 计算第一差 值与第二差值的比值, 将需要调整流量的 RP上报的流量与所述比值相乘得到 的乘积作为该需要调整流量的 RP中第一业务流的新流量值。
在本申请实施例的一种实现方式中, 所述指定 RP为同时配置了 7|诺信息 速率 CIR值和峰值信息速率 PIR值的 RP, 且具备流量监控功能。
当指定的 RP中配置有 CIR值和 PIR值,则发送单元将计算单元计算出的 各个所述第一业务流的新流量值发送给对应的所述需要调整流量的 RP, 以便 接收到新流量值的 RP根据接收到的新流量值重新配置各自的 CIR值和 PIR 值, 从而实现第一业务流的流量进行控制。 例如, 可以将 PR 中的 CIR值和 PIR值都配置成 RP接收到的由发送单元发送的新流量值。 上述仅仅是根据新 流量值配置各个 RP的 CIR值和 PIR值的一种示例, 可以理解的是, 有多种配 置方式, 本发明对此不进行限制。
接收 RP上报的第一业务流的流量监控信息; 当 CP中第一业务流的拥塞 状态满足拥塞条件时, 从指定 RP 中确定需要调整流量的 RP, 并且, 根据所 述流量监控信息计算出各个所述需要调整流量的 RP 中第一业务流的新流量
值; 所述指定 RP具有流量监控功能; 将计算出的各个所述第一业务流的新流 量值发送给对应的所述需要调整流量的 RP, 以便所述 RP根据新流量值对该 RP 中的第一业务流进行流量控制。 从而, 本申请实施例中仅从指定 RP中选 择需要调整流量的 RP, 相较于现有技术中随机选择一个 RP, 所选择的需要调 整流量的 RP更为准确, 从而提高了网络流量控制性能; 而且, 根据所述流量 监控信息计算出各个所述需要调整流量的 RP中第一业务流的新流量值, 所述 RP根据新流量值对该 RP中的第一业务流进行流量控制, 相较于现有技术中 由被选择的 RP按照某种固定的算法进行流量降速, RP中的流量控制更为准 确, 同样提高了网络流量控制性能。
本申请还提供了一种数据交换网络, 所述网络包括反应点 RP和拥塞点
CP, 其中,
所述反应点 RP用于向拥塞点 CP上报第一业务流的流量监控信息; 以及 接收所述拥塞点 CP发送的第一业务流的新流量值, 根据新流量值对该反应点 RP中的第一业务流进行流量控制;
所述拥塞点 CP用于接收反应点 RP上报的第一业务流的流量监控信息; 当拥塞点 CP中第一业务流的拥塞状态满足拥塞条件时, 根据接收的反应点 RP上报的第一业务流的流量监控信息从指定反应点 RP中确定需要调整流量 的反应点 RP, 并且, 根据所述流量监控信息计算出各个所述需要调整流量的 反应点 RP中第一业务流的新流量值;所述指定反应点 RP具备流量监控功能; 将计算出的各个所述第一业务流的新流量值发送给对应的所述需要调整流量 的反应点 RP, 以便所述反应点 RP根据新流量值对该反应点 RP中的第一业务 流进行流量控制。
在本申请实施例可能的一种实现方式中, 所述指定 RP为同时配置了 7 诺 信息速率 CIR值和峰值信息速率 PIR值的 RP,且所述 RP具备流量监控功能。
在本发明实施例提供的数据网络中, CP可以集成有前文实施例中描述的 流量控制装置。
最后, 以以太网为例, 说明在所述数据交换网络配置 CP和 RP的方法。 例如在如图 5所示的城域 OTN网络中, 包括: 城域网络接入点 (如图示 三层交换机, Layer 3 Switch, L3SW )和业务处理点(如图示业务路由器, Service
Router, SR )。城域 OTN网络中的每个节点集成 OTN功能和以太网交换功能。 在配置城域 OTN网络中的 CP和对应的 RP时,一般可以选取网络中的业 务汇聚节点, 作为 CP, 如图 5所示, 与业务处理点相连的节点可以被选取为 CP。 CP确认后, 需配置对应的 RP, —个 CP可以配置多个 RP。 RP可根据网 络拓朴和业务配置信息由网管系统自动选取或人工选取。 具体的, RP—般根 据节点的业务流量和业务连接数量来选取, 比如业务流量大于线路速率 50% 以上的节点、或者业务连接数原大于各节点平均数量的节点。 另外还可以将某 条业务连接所经过的节点作为 RP, 来专门针对这条流进行流量控制。 本领域普通技术人员可以理解,实现上述实施例的方法的过程可以通过程 序指令相关的硬件来完成, 所述的程序可以存储于可读取存储介质中, 该程序 在执行时执行上述方法中的对应步骤。 所述的存储介质可以如: ROM/RAM、 磁碟、 光盘等。 以上所述仅是本申请的优选实施方式,应当指出,对于本技术领域的普通 技术人员来说, 在不脱离本申请原理的前提下, 还可以做出若干改进和润饰, 这些改进和润饰也应视为本申请的保护范围。
+
Claims
1、 一种流量控制方法, 其特征在于, 包括:
接收反应点 RP上报的第一业务流的流量监控信息;
当拥塞点 CP中第一业务流的拥塞状态满足拥塞条件时, 根据接收的 RP 上报的第一业务流的流量监控信息从指定 RP中确定需要调整流量的 RP, 并 且, 根据所述流量监控信息计算权出各个所述需要调整流量的 RP中第一业务流 的新流量值; 所述指定 RP具备流量监控功能;
利
将计算出的各个所述第一业务流的 1新流量值发送给对应的所述需要调整
6
流量的 RP,以便所述 RP根据新流量值对要该 RP中的第一业务流进行流量控制。
2、 根据权利要求 1所述的方法, 其特征求在于, 根据接收的 RP上报的第 一业务流的流量监控信息从指定 RP中确定需要调整流量的 RP包括:
从指定 RP中按照优先级选择预设数量个 RP, 将选择的所述预设数量个 RP作为需要调整流量的 RP; 或者,
从指定 RP中按照优先级选择指定 RP总数的预设比例个 RP,将选择的所 述预设比例个 RP作为需要调整流量的 RP。
3、 根据权利要求 1所述的方法, 其特征在于, 所述指定 RP为还同时配 置了承诺信息速率 CIR值和峰值信息速率 PIR值的 RP。
4、 根据权利要求 3所述的方法, 其特征在于, 根据接收的 RP上报的第 一业务流的流量监控信息从指定 RP中确定需要调整流量的 RP包括:
对于每个指定 RP, 确定 RP中第一业务流的流量是否大于该 RP的 CIR, 选择第一业务流的流量大于 CIR的 RP作为需要调整流量的 RP。
5、根据权利要求 1所述的方法,其特征在于,所述流量监控信息包括: RP 中第一业务流对应队列的緩存状态; 根据接收的 RP上报的第一业务流的流量 监控信息确定需要调整流量的 RP包括:
从上报第一业务流的流量监控信息的 RP中, 选择队列的緩存状态为溢出 的 RP作为需要调整流量的 RP。
6、 根据权利要求 1至 5任一项所述的方法, 其特征在于, 所述流量监控 信息包括: 第一业务流的流量; 所述根据所述流量监控信息计算出各个所述需 要调整流量的 RP中第一业务流的新流量值包括:
计算 CP中第一业务流的进入速率与最大出口带宽之间的比值, 计算所述 需要调整流量的 RP上报的流量与所述比值之间的乘积, 将所述乘积作为该需 要调整流量的 RP中第一业务流的新流量值; 或者,
计算 CP中第一业务流的最大出口带宽与所有非指定 RP中第一业务流的 流量总和的第一差值, 并且, 计算 CP中第一业务流的进入速率与所有非指定 RP中第一业务流的流量总和的第二差值, 计算第一差值与第二差值的比值, 将需要调整流量的 RP上报的流量与所述比值相乘得到的乘积作为该需要调整 流量的 RP中第一业务流的新流量值。
7、 根据权利要求 1至 6任一项所述的方法, 其特征在于, 所述第一业务 流的流量监控信息通过带外信令或者低延时报文传输; 和 /或,
所述第一业务流的新流量参数通过带外信令或者低延时报文传输。
8、 根据权利要求 1至 7任一项所述的方法, 其特征在于, 所述 RP根据 新流量值对该 RP中的第一业务流进行流量控制包括:
所述 RP将第一业务流的流量降速为所述新流量值。
9、 根据权利要求 3或 4所述的方法, 其特征在于, 所述 RP根据新流量 值对该 RP中的第一业务流进行流量控制包括:
将 RP中的 CIR和 /或 PIR配置为所述新流量值。
10、 一种流量控制装置, 其特征在于, 包括:
接收单元, 用于接收反应点 RP上报的第一业务流的流量监控信息; 计算单元, 用于当拥塞点 CP中第一业务流的拥塞状态满足拥塞条件时, 根据接收的 RP上报的第一业务流的流量监控信息从指定 RP中确定需要调整 流量的 RP, 并且, 根据接收单元接收到的流量监控信息计算出各个所述需要 调整流量的 RP中第一业务流的新流量值; 所述指定 RP具备流量监控功能; 发送单元,用于将计算单元计算出的各个所述第一业务流的新流量值发送 给对应的所述需要调整流量的 RP,以便所述 RP根据新流量值对该 RP中的第 一业务流进行流量控制。
11、 根据权利要求 10所述的装置, 其特征在于, 计算单元包括: 第一选择子单元, 用于从指定 RP中按照优先级选择预设数量个 RP, 将 选择的所述预设数量个 RP作为需要调整流量的 RP; 或者,
第二选择子单元, 从指定 RP中按照优先级选择指定 RP总数的预设比例 个 RP, 将选择的所述预设比例个 RP作为需要调整流量的 RP。
12、 根据权利要求 10所述的装置, 其特征在于, 所述指定 RP为还同时 配置了承诺信息速率 CIR值和峰值信息速率 PIR值的 RP。
13、 根据权利要求 12所述的装置, 其特征在于, 计算单元包括: 第三选 择子单元, 对于每个指定 RP, 确定 RP中第一业务流的流量是否大于该 RP的 CIR, 选择第一业务流的流量大于 CIR的 RP作为需要调整流量的 RP。
14、 根据权利要求 10所述的装置, 其特征在于, 所述流量监控信息包括: RP中第一业务流对应队列的緩存状态; 计算单元包括:
第四选择子单元,用于从上报第一业务流的流量监控信息的反应点 RP中, 选择队列的緩存状态为溢出的 RP作为需要调整流量的 RP。
15、 根据权利要求 10至 14任一项所述的装置, 其特征在于, 所述流量监 控信息包括: 第一业务流的流量; 计算单元还包括:
第一计算子单元, 用于计算 CP中第一业务流的进入速率与最大出口带宽 之间的比值,计算所述需要调整流量的 RP上报的流量与所述比值之间的乘积, 将所述乘积作为该需要调整流量的 RP中第一业务流的新流量值; 或者,
第二计算子单元, 用于计算 CP中第一业务流的最大出口带宽与所有非指 定 RP中第一业务流的流量总和的第一差值, 并且, 计算 CP中第一业务流的 进入速率与所有非指定 RP中第一业务流的流量总和的第二差值, 计算第一差 值与第二差值的比值, 将需要调整流量的 RP上报的流量与所述比值相乘得到 的乘积作为该需要调整流量的 RP中第一业务流的新流量值。
16、 一种数据交换网络, 其特征在于, 所述网络包括反应点 RP和拥塞点
CP, 其中,
所述 RP用于向 CP上报第一业务流的流量监控信息; 以及接收所述 CP 发送的第一业务流的新流量值, 根据新流量值对该 RP中的第一业务流进行流 量控制;
所述 CP用于接收 RP上报的第一业务流的流量监控信息; 当 CP中第一 业务流的拥塞状态满足拥塞条件时, 根据接收的 RP上报的第一业务流的流量 监控信息从指定 RP中确定需要调整流量的 RP, 并且, 根据所述流量监控信 息计算出各个所述需要调整流量的反应点 RP中第一业务流的新流量值; 所述 指定 RP具备流量监控功能; 将计算出的各个所述第一业务流的新流量值发送 给对应的所述需要调整流量的 RP,以便所述 RP根据新流量值对该 RP中的第 一业务流进行流量控制。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2012/081892 WO2014047771A1 (zh) | 2012-09-25 | 2012-09-25 | 一种流量控制方法、装置及网络 |
CN201280002772.8A CN103416031B (zh) | 2012-09-25 | 2012-09-25 | 一种流量控制方法、装置及网络 |
EP12885822.2A EP2887590B1 (en) | 2012-09-25 | 2012-09-25 | Flow control method, device and network |
US14/668,621 US9998378B2 (en) | 2012-09-25 | 2015-03-25 | Traffic control method, device, and network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2012/081892 WO2014047771A1 (zh) | 2012-09-25 | 2012-09-25 | 一种流量控制方法、装置及网络 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/668,621 Continuation US9998378B2 (en) | 2012-09-25 | 2015-03-25 | Traffic control method, device, and network |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014047771A1 true WO2014047771A1 (zh) | 2014-04-03 |
Family
ID=49608191
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2012/081892 WO2014047771A1 (zh) | 2012-09-25 | 2012-09-25 | 一种流量控制方法、装置及网络 |
Country Status (4)
Country | Link |
---|---|
US (1) | US9998378B2 (zh) |
EP (1) | EP2887590B1 (zh) |
CN (1) | CN103416031B (zh) |
WO (1) | WO2014047771A1 (zh) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114338425A (zh) * | 2021-12-31 | 2022-04-12 | 中国联合网络通信集团有限公司 | 一种网络规划方法、装置和存储介质 |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106330742B (zh) * | 2015-06-23 | 2019-12-06 | 华为技术有限公司 | 一种流量控制的方法及网络控制器 |
CN107276909B (zh) * | 2016-04-07 | 2021-04-06 | 深圳市中兴微电子技术有限公司 | 端口流量管理方法及装置 |
CN107547414A (zh) * | 2016-06-24 | 2018-01-05 | 中兴通讯股份有限公司 | 报文发送方法及装置 |
CN106059942A (zh) * | 2016-08-02 | 2016-10-26 | 浪潮集团有限公司 | 一种sdn网络中基于负载预测的流量控制方法 |
WO2018195728A1 (zh) | 2017-04-24 | 2018-11-01 | 华为技术有限公司 | 一种客户业务传输方法和装置 |
JP6863091B2 (ja) * | 2017-05-31 | 2021-04-21 | 富士通株式会社 | 管理装置、管理方法及び管理プログラム |
US10992580B2 (en) * | 2018-05-07 | 2021-04-27 | Cisco Technology, Inc. | Ingress rate limiting in order to reduce or prevent egress congestion |
CN108959399B (zh) * | 2018-06-04 | 2022-07-15 | 平安科技(深圳)有限公司 | 分布式数据删除流控方法、装置、电子设备及存储介质 |
US11843533B2 (en) * | 2022-02-28 | 2023-12-12 | Microsoft Technology Licensing, Llc | End-to-end performance aware traffic engineering for internet peering |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101253729A (zh) * | 2005-10-11 | 2008-08-27 | 思科技术公司 | 后向拥塞通知的方法和设备 |
US20080298248A1 (en) * | 2007-05-28 | 2008-12-04 | Guenter Roeck | Method and Apparatus For Computer Network Bandwidth Control and Congestion Management |
US20090052326A1 (en) * | 2007-08-21 | 2009-02-26 | Cisco Technology, Inc., A Corporation Of California | Backward congestion notification |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1182567B1 (en) * | 2000-08-21 | 2012-03-07 | Texas Instruments France | Software controlled cache configuration |
CN100486188C (zh) | 2001-12-29 | 2009-05-06 | 中兴通讯股份有限公司 | 以太网流量控制装置及方法 |
US7945945B2 (en) | 2004-08-06 | 2011-05-17 | Enterasys Networks, Inc. | System and method for address block enhanced dynamic network policy management |
US7796507B2 (en) * | 2005-12-29 | 2010-09-14 | Telefonaktiebolaget Lm Ericsson (Publ) | Method and apparatus for communication network congestion control |
US7773519B2 (en) * | 2008-01-10 | 2010-08-10 | Nuova Systems, Inc. | Method and system to manage network traffic congestion |
EP2417719B1 (en) * | 2009-04-07 | 2017-01-11 | Cisco Technology, Inc. | Method and system to manage network traffic congestion |
JP5497529B2 (ja) * | 2010-05-13 | 2014-05-21 | 日本電気株式会社 | ネットワーク中継装置及びQoS制御方法 |
CN102025617B (zh) * | 2010-11-26 | 2015-04-01 | 中兴通讯股份有限公司 | 以太网拥塞控制方法及装置 |
US9237107B2 (en) * | 2011-11-15 | 2016-01-12 | New Jersey Institute Of Technology | Fair quantized congestion notification (FQCN) to mitigate transport control protocol (TCP) throughput collapse in data center networks |
IL219391A0 (en) * | 2012-04-24 | 2012-07-31 | Eci Telecom Ltd | Technique of congestion control of packet switches |
JP6007595B2 (ja) * | 2012-05-28 | 2016-10-12 | 富士通株式会社 | 伝送方法、装置及びプログラム |
US9391910B2 (en) * | 2012-07-20 | 2016-07-12 | Cisco Technology, Inc. | Smart pause for distributed switch fabric system |
-
2012
- 2012-09-25 CN CN201280002772.8A patent/CN103416031B/zh active Active
- 2012-09-25 WO PCT/CN2012/081892 patent/WO2014047771A1/zh active Application Filing
- 2012-09-25 EP EP12885822.2A patent/EP2887590B1/en active Active
-
2015
- 2015-03-25 US US14/668,621 patent/US9998378B2/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101253729A (zh) * | 2005-10-11 | 2008-08-27 | 思科技术公司 | 后向拥塞通知的方法和设备 |
US20080298248A1 (en) * | 2007-05-28 | 2008-12-04 | Guenter Roeck | Method and Apparatus For Computer Network Bandwidth Control and Congestion Management |
US20090052326A1 (en) * | 2007-08-21 | 2009-02-26 | Cisco Technology, Inc., A Corporation Of California | Backward congestion notification |
Non-Patent Citations (1)
Title |
---|
See also references of EP2887590A4 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114338425A (zh) * | 2021-12-31 | 2022-04-12 | 中国联合网络通信集团有限公司 | 一种网络规划方法、装置和存储介质 |
CN114338425B (zh) * | 2021-12-31 | 2023-09-19 | 中国联合网络通信集团有限公司 | 一种网络规划方法、装置和存储介质 |
Also Published As
Publication number | Publication date |
---|---|
US9998378B2 (en) | 2018-06-12 |
CN103416031B (zh) | 2016-11-23 |
EP2887590A4 (en) | 2015-12-02 |
EP2887590B1 (en) | 2017-09-20 |
US20150200856A1 (en) | 2015-07-16 |
EP2887590A1 (en) | 2015-06-24 |
CN103416031A (zh) | 2013-11-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2014047771A1 (zh) | 一种流量控制方法、装置及网络 | |
US10044593B2 (en) | Smart ethernet edge networking system | |
US9634916B2 (en) | Signalling congestion | |
US7733770B2 (en) | Congestion control in a network | |
CN111316605B (zh) | 第3层公平速率拥塞控制通知 | |
CN102223675B (zh) | 拥塞告警及处理方法、系统和设备 | |
JP2008507204A (ja) | 二方向メッセージングネットワークでゾーン間帯域を管理する方法 | |
US9432874B2 (en) | Service-aware profiling for transport networks | |
WO2012065477A1 (zh) | 报文拥塞避免方法及系统 | |
CN107342947B (zh) | 流量整形方法、控制器、网络设备和流量整形系统 | |
WO2008104100A1 (fr) | Appareil et procédé servant à réaliser un contrôle de flux sur la base d'une vitesse restreinte pour un dispositif mstp | |
WO2014101439A1 (zh) | 业务流监测相关的方法、装置和系统 | |
WO2008089639A1 (fr) | Procédé d'application de contre-pression massique de ports, et dispositif associé | |
Yi et al. | Proxy‐RED: an AQM scheme for wireless local area networks | |
Mliki et al. | A comprehensive survey on carrier ethernet congestion management mechanism | |
WO2014000467A1 (zh) | 一种网络虚拟化系统中带宽调整的方法及装置 | |
JP5249966B2 (ja) | スループットを向上させる通信制御方法および通信システム、ならびにそのためのプログラム | |
CN106685849B (zh) | 基于sdn的wred报文丢弃方法及系统 | |
CN112714072B (zh) | 一种调整发送速率的方法及装置 | |
JP5753918B2 (ja) | ネットワーク中継装置 | |
Nabeshima et al. | Performance improvement of active queue management with per-flow scheduling | |
Lovewell et al. | Impact of cross traffic burstiness on the packet-scale paradigm | |
JP2007215061A (ja) | トラヒックシェーピング装置 | |
Lovewell et al. | Impact of Cross Traffic Burstiness on the Packet-scale Paradigm-Extended Analysis | |
Hongwei et al. | Achieving proportional loss differentiation using RED with maximum drop probability adjustment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 12885822 Country of ref document: EP Kind code of ref document: A1 |
|
REEP | Request for entry into the european phase |
Ref document number: 2012885822 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2012885822 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |