CN108173784B - Aging method and device for data packet cache of switch - Google Patents
Aging method and device for data packet cache of switch Download PDFInfo
- Publication number
- CN108173784B CN108173784B CN201711471380.7A CN201711471380A CN108173784B CN 108173784 B CN108173784 B CN 108173784B CN 201711471380 A CN201711471380 A CN 201711471380A CN 108173784 B CN108173784 B CN 108173784B
- Authority
- CN
- China
- Prior art keywords
- aging
- packet
- unsent
- data packet
- queue
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
- H04L47/62—Queue scheduling characterised by scheduling criteria
- H04L47/625—Queue scheduling characterised by scheduling criteria for service slots or service orders
- H04L47/6275—Queue scheduling characterised by scheduling criteria for service slots or service orders based on priority
-
- 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
- H04L47/32—Flow control; Congestion control by discarding or delaying data units, e.g. packets or frames
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
- H04L47/62—Queue scheduling characterised by scheduling criteria
- H04L47/6295—Queue scheduling characterised by scheduling criteria using multiple queues, one for each individual QoS, connection, flow or priority
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/90—Buffering arrangements
- H04L49/901—Buffering arrangements using storage descriptor, e.g. read or write pointers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/90—Buffering arrangements
- H04L49/9015—Buffering arrangements for supporting a linked list
Abstract
The invention discloses an aging method and a device for a data packet cache of a switch, wherein the method is characterized in that a counter is arranged in each unsent message queue, and after a scheduling period begins, the counters of the unsent message queues are added with 1; when the unsent message queue has a data packet to send in the scheduling period, resetting the corresponding counter; and when the unsent message queue has no data packet to transmit in the scheduling period, aging the data packet of the unsent message queue according to the aging configuration file table. The device comprises an aging configuration file table and a counter arranged at the head of an unsent message queue. The invention not only can guarantee the transmission of the queue with high priority, but also can lead the queue with low priority to age the data packet in time, thus leading the memory of the switch to be recycled.
Description
Technical Field
The invention relates to the field of message cache engines of switches, in particular to an aging method and device for data packet cache of a switch.
Background
The transmission and switching speed of ethernet data restricts the development of ethernet, a higher-performance network device is required to increase the speed of the network, and a switch is used as an important two-layer switching network device, and in a network architecture, the switch is an information transfer station and forwards data received from a certain port from other ports according to a certain rule. The performance of which directly affects the overall network speed of the network in which it is located. The implementation of high performance switches is difficult.
In the process of transferring data packets, network data packets need to be stored into a data packet cache engine according to priority, and the data packet cache engine comprises a plurality of data packet cache queues.
The following detailed description:
the message cache engine is an important component of the switch message processing engine. In the process of data forwarding, the switch needs to receive the data packet into the memory, then analyzes the data packet, and performs data filling, modification, copying and forwarding according to a certain strategy. The message caching engine is a functional module for data caching, and has the following functional characteristics:
(1) memory management: carrying out centralized management on the memory of the switch;
(2) list of free memory: maintaining the exchanged free memory list to quickly obtain the free memory;
(3) message queue management: queue management is carried out on the received messages which are not forwarded;
(4) memory recovery: and recovering the memory of the sent message and putting the message into the idle memory.
The data caching mechanism of the message caching engine of the existing switch is as follows:
as shown in fig. 1, the switch packet cache engine divides the overall switch memory into three parts, which are respectively used for packet cache block management, a free memory chain table and an unsent packet queue.
I, packet cache block management:
generally, a switch divides the whole packet buffer into N packet buffer blocks with fixed length for management, and one packet may occupy one or more packet buffer blocks according to the data size of the packet, and each packet buffer block uses the starting position of an address as an index for accessing the packet buffer block, i.e. a packet buffer index of the packet buffer block. The N packet cache blocks correspond to packet cache index 0 to packet cache index N, respectively, as shown in fig. 2.
After a packet cache block is used, until the packet is forwarded, or discarded, it cannot be used by the second packet, and in order to quickly find an available free packet cache block when a new packet arrives, the switch uses a free memory linked list to store all unused packet cache blocks.
II, free memory linked list (FreeList):
in the initialization stage of the switch system, the switch packet cache engine puts all the packet cache blocks into the idle memory linked list to obtain an ordered linked list with a length of N, as shown in fig. 3.
When a new data packet arrives at the switch, the message cache engine takes out 1 or more data packet cache blocks from the head of the table of the idle memory linked list for storing the data packet. When the data packet is sent, the memory of the corresponding data packet cache block is released, and the released memory is placed at the tail of the queue of the idle memory linked list. When the free memory linked list is empty, it indicates that the switch does not have available free data packet cache blocks to use, and the newly received data packet can be directly discarded because the data packet cannot be cached.
The free memory linked list has a head pointer (Header PTR) to point to this Queue (Queue) and the Queue link list memory for the first packet, as shown in FIG. 4.
III, unsent message queue:
the message cache engine stores unsent messages by using unsent message queues, and the message cache engine is composed of M queues according to the priorities of the messages, and each queue stores messages with the same priority. The data structure used by the Queue is the same as that of the free memory Queue in fig. 4, see that the head pointer is also used to point to this Queue and the Queue link list memory of the first data packet. As shown in FIG. 5, multiple queues use an array of pointers to hold the head pointers of M queues.
And after a new message is acquired from the free memory list to the data packet cache block, deleting the data packet cache block from the head of the free memory queue, performing queue mapping operation, and inserting the head of the unsent queue. And after the message is sent, deleting the corresponding data packet cache block from the tail part of the unsent queue and inserting the data packet cache block into the head part of the idle memory queue.
Referring to fig. 6, the sending scheduling process of the unsent packet queue adopts an SP + WDRR (SP: Strict Priority, Strict Priority; WDRR: Weighted differential Round Robin) mode, as shown in fig. 6. And the SP scheduling preferentially sends the packets in the queue with higher priority according to the sequence from high priority to low priority, and then sends the packets in the queue with lower priority when the queue with higher priority is empty.
WDRR is a weighted scheduling based on message bytes, the algorithm is based on two variables: quota (quota) and balance (credit counter), quota representing weight, in bytes, are configurable parameters. The balance is used for representing the accumulation and consumption of quota, is a state parameter and is not configurable. In the initial state, the balance of each queue is equal to the quota, when the queue sends a message, the number of bytes of the message is subtracted from the balance, and when the balance is lower than 0, the scheduling of the queue is stopped. All queues are replenished with quota when they stop scheduling. The weight N ranges from 0 to 127, where N represents quota (N × MTU _ QUANTA) bytes, where (MTU _ QUANTA is 2K) and N is 0 represents strict priority.
In the process of strictly performing according to the above two scheduling rules, when the following occurs:
the high priority queue always has packets, and when the packets are sent continuously, the packets in the low priority queue rarely get a chance to send the packets, and at the moment, the unsent queue with low priority always increases the length. Two problems arise here:
(1) the low priority queue will continue to buffer because it has no chance to send, and will occupy a large amount of buffer. Because all queues are of a common packet buffer block, at this time, the low priority queue may exhaust the packet buffer block, and although the high priority queue is sending packets all the time, a new packet may still have no packet buffer block available, resulting in packet loss.
(2) Most of the existing networks are TCP/IP applications, many of the applications have timeliness, a low-priority queue stores some very old packets which are sent out by chance, and the actual significance is not achieved, and the packets are discarded at an application layer, so that the waste of network resources is caused.
Disclosure of Invention
The invention aims to provide an aging method and an aging device for a data packet buffer of a switch, which are used for solving the technical problem that a low-priority queue cannot be sent and a memory is exhausted due to the sending scheduling of the existing unsent message, so that the packet loss of a high-priority queue is caused.
In order to achieve the above object, the present invention provides an aging method for a data packet buffer of a switch, wherein a counter is set in each unsent packet queue, and single scheduling is performed according to the following steps:
after each scheduling period begins, adding 1 to the counters of all unsent message queues, and then sending messages according to the priority; when the unsent message queue has a data packet to send in the scheduling period, resetting the corresponding counter; and when the unsent message queue has no data packet to transmit in the scheduling period, aging the data packet of the unsent message queue according to the aging configuration file table.
As a further improvement of the process of the invention:
the aging configuration file table comprises more than one piece of configuration information, and the configuration information comprises a threshold value and the corresponding aging package number.
Aging the data packets of the unsent message queue according to the aging configuration file table, comprising the following steps:
when the counter of the unsent message queue reaches the corresponding threshold value, discarding the data packets with the corresponding number at the head of the unsent message queue according to the aging packet number corresponding to the threshold value in the aging configuration file table, releasing the data packet cache blocks corresponding to the data packets, and inserting the released data packet cache blocks into the idle memory linked list.
In the aging configuration file table, all unsent message queues use the same configuration information, or a plurality of unsent message queues respectively use a plurality of pieces of configuration information in a one-to-one correspondence manner.
Head pointers and corresponding counters of a plurality of unsent message queues are stored by using a pointer array.
As a general technical concept, the present invention further provides an aging apparatus for a packet buffer of a switch based on the aging method, including:
the aging configuration file table comprises more than one piece of configuration information, and the configuration information comprises a threshold value and a corresponding aging package number;
the counter is arranged at the head of the unsent message queue and is used for adding 1 after each scheduling period begins; the scheduling module is also used for clearing when the unsent message queue has a data packet to send in the scheduling period after the message is sent according to the priority; when the unsent message queue has no data packet to transmit in the scheduling period, the counter is compared with the threshold value in the aging configuration file table to age the data packet of the unsent message queue by the corresponding aging packet number.
As a further improvement of the device of the invention:
the device also comprises a pointer array used for sequentially storing the head pointer of the unsent message queue and the counter.
The invention has the following beneficial effects:
1. the aging method of the data packet cache of the switch uses dynamic configuration, and configures the aging configuration of each queue globally or individually; introducing a counter, and maintaining and calculating a blocking period of the unsent list; and introducing a scanning engine, and aging the data packets of the queue according to the configuration. The method has the advantages that the queues with different priorities can be independently aged on the basis of not changing the queue scheduling algorithm of the switch, the data packets of the queues are discarded according to actual conditions, the transmission of the queues with high priorities can be guaranteed, the aging of the data packets can be timely carried out on the queues with low priorities, and the memory of the switch can be recycled.
2. The aging device for the data packet cache of the switch has the advantages of simple structure, flexible configuration, unlimited existing form of configuration, wide applicability, and the like, and comprises files, cloud configuration, HTTP configuration, UI configuration and the like.
In addition to the objects, features and advantages described above, other objects, features and advantages of the present invention are also provided. The present invention will be described in further detail below with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of a switch message caching engine of the background art;
FIG. 2 is a diagram illustrating a structure of a packet buffer block of a related art packet buffer;
FIG. 3 is a diagram illustrating a structure of a linked list of idle memories in the background art;
FIG. 4 is a diagram illustrating a data structure of a background unsent packet queue;
FIG. 5 is a diagram illustrating a structure of a prior art unsent packet queue using an array of pointers to store head pointers of M queues;
FIG. 6 is a diagram illustrating a transmission scheduling process of an unsent queue according to the background art;
FIG. 7 is a diagram illustrating a data structure of an unsent packet queue according to a preferred embodiment of the present invention;
FIG. 8 is a diagram illustrating a structure of a unsent message queue using an array of pointers to store head pointers and counters of M queues according to a preferred embodiment of the present invention;
FIG. 9 is a schematic diagram of the aging profile table of the preferred embodiment of the present invention;
fig. 10 is a flow chart illustrating an aging method of a packet buffer of a switch according to a preferred embodiment of the present invention.
Detailed Description
The embodiments of the invention will be described in detail below with reference to the drawings, but the invention can be implemented in many different ways as defined and covered by the claims.
The present invention relates to the noun explanation:
and (3) queue: queue, in the invention, a data packet buffer Queue;
header PTR: a head pointer;
queue link list: storing a message memory queue;
NEXT PTR: a next node pointer.
Fig. 10 is a flow chart illustrating an aging method of a packet buffer of a switch according to a preferred embodiment of the present invention. Referring to fig. 7, a counter is first set in each unsent packet queue, and then single scheduling is performed according to the following steps:
after each scheduling period begins, adding 1 to the counters of all unsent message queues, and then sending messages according to the priority; when the unsent message queue has a data packet to send in the scheduling period, resetting the corresponding counter; when the unsent packet queue does not have a data packet to transmit in the scheduling period, the data packet of the unsent packet queue is aged according to an aging configuration file table (see fig. 9). As shown in fig. 9, the aging profile table includes more than one piece of configuration information, and the configuration information includes a threshold and a corresponding aging packet number. In the aging configuration file table, all unsent message queues use the same configuration information, or a plurality of unsent message queues respectively use a plurality of pieces of configuration information in a one-to-one correspondence manner.
In this embodiment, the aging of the data packets in the unsent packet queue according to the aging configuration file table includes the following steps:
when the counter of the unsent message queue reaches the corresponding threshold value, discarding the data packets with the corresponding number at the head of the unsent message queue according to the aging packet number corresponding to the threshold value in the aging configuration file table, releasing the data packet cache blocks corresponding to the data packets, and inserting the released data packet cache blocks into the idle memory linked list.
Referring to fig. 8, head pointers and corresponding counters of a plurality of unsent message queues are stored using an array of pointers.
Based on the foregoing aging method, the aging apparatus for a packet buffer of a switch in this embodiment includes:
an aging profile table (fig. 9) including one or more pieces of configuration information including a threshold value and a corresponding number of aging packets; a counter (fig. 7) disposed at the head of the unsent packet queue, the counter being configured to add 1 after each scheduling period starts; the scheduling module is also used for clearing when the unsent message queue has a data packet to send in the scheduling period after the message is sent according to the priority; when the unsent message queue has no data packet to transmit in the scheduling period, the counter is compared with the threshold value in the aging configuration file table to age the data packet of the unsent message queue by the corresponding aging packet number. The apparatus also includes an array of pointers for sequentially storing head pointers and counters of unsent message queues (fig. 8).
In summary, the present invention changes the existing message processing flow mode and introduces a new packet cache aging mechanism. The length of the low-priority unsent queue can be dynamically controlled according to the scheduling period, and the following beneficial effects can be achieved at least:
(1) the used memory of the switch can be released in time, so that the high-priority queue has available data packet cache blocks;
(2) the message with longer time can be discarded in time, and the waste of network resources is avoided. Because many applications of the existing network have timeliness, a packet with longer blocking time is sent out without meaning, and network resources are consumed by using space.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A method for aging data packet buffer of switch is characterized in that a counter is arranged in each unsent message queue, and single scheduling is carried out according to the following steps:
after each scheduling period begins, adding 1 to the counters of all unsent message queues, and then sending messages according to the priority; when the unsent message queue has a data packet to send in the scheduling period, resetting the corresponding counter; and when the unsent message queue does not have a data packet to transmit in the scheduling period, aging the data packet of the unsent message queue according to an aging configuration file table.
2. The aging method for the packet buffer of the switch according to claim 1, wherein the aging profile table includes more than one piece of configuration information, and the configuration information includes a threshold value and a corresponding aging packet number.
3. The aging method for the packet buffer of the switch according to claim 2, wherein the aging the packets in the unsent packet queue according to the aging configuration file table comprises the following steps:
when the counter of the unsent message queue reaches the corresponding threshold value, discarding the data packets with the corresponding number at the head of the unsent message queue according to the aging packet number corresponding to the threshold value in the aging configuration file table, releasing the data packet cache blocks corresponding to the data packets, and inserting the released data packet cache blocks into the idle memory linked list.
4. The aging method for a packet buffer of a switch according to any of claims 1 to 3, wherein in the aging profile table, all unsent packet queues use the same configuration information, or a plurality of unsent packet queues use a plurality of pieces of configuration information in a one-to-one correspondence respectively.
5. The method of claim 4, wherein the head pointers and corresponding counters of the plurality of unsent packet queues are stored using an array of pointers.
6. An aging apparatus for a packet buffer of a switch based on the aging method for a packet buffer of a switch according to any one of claims 1 to 5, comprising:
the aging configuration file table comprises more than one piece of configuration information, and the configuration information comprises a threshold value and a corresponding aging package number;
the counter is arranged at the head of the unsent message queue and is used for adding 1 after each scheduling period begins; the scheduling module is also used for clearing when the unsent message queue has a data packet to send in the scheduling period after the message is sent according to the priority; when the unsent message queue has no data packet to transmit in the scheduling period, the counter is compared with a threshold value in an aging configuration file table so as to age the data packet of the unsent message queue by the corresponding aging packet number.
7. The aging apparatus of claim 6, further comprising a pointer array for sequentially storing a head pointer and a counter of the unsent packet queue.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711471380.7A CN108173784B (en) | 2017-12-29 | 2017-12-29 | Aging method and device for data packet cache of switch |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711471380.7A CN108173784B (en) | 2017-12-29 | 2017-12-29 | Aging method and device for data packet cache of switch |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108173784A CN108173784A (en) | 2018-06-15 |
| CN108173784B true CN108173784B (en) | 2021-12-28 |
Family
ID=62520077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711471380.7A Active CN108173784B (en) | 2017-12-29 | 2017-12-29 | Aging method and device for data packet cache of switch |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108173784B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6222822B1 (en) * | 1996-04-23 | 2001-04-24 | Cisco Systems, Incorporated | Method for optimizing a digital transmission network operation through transient error monitoring and control and system for implementing said method |
| CN102447610A (en) * | 2010-10-14 | 2012-05-09 | 中兴通讯股份有限公司 | Method and device for realizing message buffer resource sharing |
| CN102594691A (en) * | 2012-02-23 | 2012-07-18 | 中兴通讯股份有限公司 | Method and device for processing message |
| CN102668466A (en) * | 2009-12-24 | 2012-09-12 | 意大利电信股份公司 | A method of scheduling transmission in a communication network, corresponding communication node and computer program product |
| US8614947B2 (en) * | 2010-06-11 | 2013-12-24 | Fujitsu Limited | Apparatus for transmitting packet |
| CN105610725A (en) * | 2016-01-11 | 2016-05-25 | 盛科网络（苏州）有限公司 | Dynamic queue congestion aging management method and device |
| CN105812285A (en) * | 2016-04-29 | 2016-07-27 | 华为技术有限公司 | Port congestion management method and device |
| CN106899516A (en) * | 2017-02-28 | 2017-06-27 | 华为技术有限公司 | A kind of queue emptying method and relevant device |
| CN107431667A (en) * | 2015-03-20 | 2017-12-01 | 阿尔卡特朗讯公司 | Packet is dispatched in the network device |
| CN107454014A (en) * | 2016-05-30 | 2017-12-08 | 中兴通讯股份有限公司 | A kind of method and device of Priority Queuing |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050149563A1 (en) * | 2004-01-06 | 2005-07-07 | Yong Yean K. | Random early detect and differential packet aging flow control in switch queues |
| US7974278B1 (en) * | 2007-12-12 | 2011-07-05 | Integrated Device Technology, Inc. | Packet switch with configurable virtual channels |
| WO2014101060A1 (en) * | 2012-12-27 | 2014-07-03 | 华为技术有限公司 | Data packet transmission method and device |
| CN104333520A (en) * | 2014-11-28 | 2015-02-04 | 上海斐讯数据通信技术有限公司 | Method for controlling interchanger MAC address table dual-ageing time |
| CN104639458B (en) * | 2015-01-30 | 2018-03-06 | 南京邮电大学 | A kind of active queue management method applied to real-time streaming transport |
| CN106664253A (en) * | 2015-06-30 | 2017-05-10 | 华为技术有限公司 | Flow table ageing method, switch and controller |
| CN106559354A (en) * | 2015-09-28 | 2017-04-05 | 中兴通讯股份有限公司 | A kind of method and device for preventing CPU packet congestions |
| CN105959430A (en) * | 2016-05-31 | 2016-09-21 | 深圳市风云实业有限公司 | Switcher MAC address aging method |
| CN106603290A (en) * | 2016-12-15 | 2017-04-26 | 天津交控科技有限公司 | Network management software performance optimization processing method and device |
-
2017
- 2017-12-29 CN CN201711471380.7A patent/CN108173784B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6222822B1 (en) * | 1996-04-23 | 2001-04-24 | Cisco Systems, Incorporated | Method for optimizing a digital transmission network operation through transient error monitoring and control and system for implementing said method |
| CN102668466A (en) * | 2009-12-24 | 2012-09-12 | 意大利电信股份公司 | A method of scheduling transmission in a communication network, corresponding communication node and computer program product |
| US8614947B2 (en) * | 2010-06-11 | 2013-12-24 | Fujitsu Limited | Apparatus for transmitting packet |
| CN102447610A (en) * | 2010-10-14 | 2012-05-09 | 中兴通讯股份有限公司 | Method and device for realizing message buffer resource sharing |
| CN102594691A (en) * | 2012-02-23 | 2012-07-18 | 中兴通讯股份有限公司 | Method and device for processing message |
| CN107431667A (en) * | 2015-03-20 | 2017-12-01 | 阿尔卡特朗讯公司 | Packet is dispatched in the network device |
| CN105610725A (en) * | 2016-01-11 | 2016-05-25 | 盛科网络（苏州）有限公司 | Dynamic queue congestion aging management method and device |
| CN105812285A (en) * | 2016-04-29 | 2016-07-27 | 华为技术有限公司 | Port congestion management method and device |
| CN107454014A (en) * | 2016-05-30 | 2017-12-08 | 中兴通讯股份有限公司 | A kind of method and device of Priority Queuing |
| CN106899516A (en) * | 2017-02-28 | 2017-06-27 | 华为技术有限公司 | A kind of queue emptying method and relevant device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108173784A (en) | 2018-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200241915A1 (en) | Work conserving, load balancing, and scheduling | |
| JP5863076B2 (en) | Method, apparatus, and system for reconstructing and reordering packets | |
| JP4879382B2 (en) | Packet switch, scheduling device, discard control circuit, multicast control circuit, and QoS control device | |
| CA2575869C (en) | Hierarchal scheduler with multiple scheduling lanes | |
| US7529224B2 (en) | Scheduler, network processor, and methods for weighted best effort scheduling | |
| CN106209679B (en) | Method and apparatus for using multiple linked memory lists | |
| US11637786B1 (en) | Multi-destination traffic handling optimizations in a network device | |
| CN101136854B (en) | Method and apparatus for implementing data packet linear speed processing | |
| CN109246036B (en) | Method and device for processing fragment message | |
| US20120294315A1 (en) | Packet buffer comprising a data section and a data description section | |
| JP2011024027A (en) | Packet transmission control apparatus, hardware circuit, and program | |
| CN113037640A (en) | Data forwarding method, data caching device and related equipment | |
| US11677676B1 (en) | Shared traffic manager | |
| EP2526478B1 (en) | A packet buffer comprising a data section an a data description section | |
| US11949601B1 (en) | Efficient buffer utilization for network data units | |
| CN113032295A (en) | Data packet second-level caching method, system and application | |
| CN103617132B (en) | A kind of ethernet terminal based on shared storage sends implementation method and terminal installation | |
| US10846225B1 (en) | Buffer read optimizations in a network device | |
| US7474662B2 (en) | Systems and methods for rate-limited weighted best effort scheduling | |
| CN108173784B (en) | Aging method and device for data packet cache of switch | |
| EP1508225B1 (en) | Method for data storage in external and on-chip memory in a packet switch | |
| US10742558B1 (en) | Traffic manager resource sharing | |
| US7599381B2 (en) | Scheduling eligible entries using an approximated finish delay identified for an entry based on an associated speed group | |
| US10581759B1 (en) | Sharing packet processing resources | |
| Wang et al. | Research on bandwidth control technology based on SDN |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |