CN100338923C - Method of realizing IP message partition and recombination based on network processor - Google Patents
Method of realizing IP message partition and recombination based on network processor Download PDFInfo
- Publication number
- CN100338923C CN100338923C CNB021377987A CN02137798A CN100338923C CN 100338923 C CN100338923 C CN 100338923C CN B021377987 A CNB021377987 A CN B021377987A CN 02137798 A CN02137798 A CN 02137798A CN 100338923 C CN100338923 C CN 100338923C
- Authority
- CN
- China
- Prior art keywords
- message
- buffer storage
- address
- fragmentation
- total length
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present invention discloses a method of realizing the recombination of partitioned IP messages on the basis of a network processor, which comprises the following steps: a Hash index table is created; two buffer storage areas used for storing partitioned IP messages are distributed; a source IP address, a target IP address, an identifier, sheet offset information and length information are extracted from the IP head of a new received partitioned IP message; a Hash unit is applied; a buffer storage unit is applied from one buffer storage area; the IP head is stored in the buffer storage unit; subsequent partitioned IP messages are received; the data net loads of the partitioned messages are copied in the corresponding positions of the buffer storage unit according to the sheet offset information of the partitioned IP messages. The technical scheme of the present invention makes the realization of the recombination of the partitioned IP messages on a network processor probable by the mechanisms of the two buffer storage areas. A recombination process is simple and effective. The present invention realizes original recombination.
Description
Technical field
The present invention relates to the method for a kind of IP (Internet Protocol, i.e. Internet protocol) fragment message reorganization, relate in particular to and adopt network processing unit to realize the method for IP fragmentation message reorganization.
Background technology
Networks and Communications are one of current fields hot and the most with fastest developing speed, and in order to deal with busy day by day information flow, the speed of network develops into present 10Gb/s by several years ago 155Mb/s, will bring up to 40Gb/s in 2～3 years of future.Because optical fiber has been arranged, the speed of transmission medium is unquestionable, and unique bottleneck then appears on the processing speed of general processor.When network speed was slow, general processor was able to catch up with data flow fully, did not need special network processing unit.Afterwards, general processor was fast inadequately, and the designer just turns to application-specific integrated circuit (ASIC) (Application Specific Integrated Circuit is called for short ASIC).ASIC is unsurpassed finishing aspect the predetermined process work, but it has two shortcomings: the one, and the cycle of exploitation is oversize, will increase new function as router or switch, just needs to wait for the long time; The 2nd, ASIC is not programmable, revise the cycle that just must experience a design and make, does not adapt to the current shorter and shorter construction cycle.
Selecting special-purpose network processing unit to substitute general processor is a reasonable solution.The networking processor aims to optimize to wrap and handles and design.It adopts many central processing units (Central ProcessionUnit, be called for short CPU) mechanism, as shown in Figure 1, comprise that one is used for host CPU (Host CPU) that chain of command handles and several are used for reduced instruction structure (the Reduction InstructionSet Computer Architecture of data surface processing, the abbreviation risc architecture) CPU, i.e. RISC CPU.We make several RISC CPU carry out real-time parallel to the data surface message and handle, thereby the message of data surface can be delivered to next node with the speed (linear speed) of its arrival by being programmed in the processing that realizes talk various network protocols on the RISC CPU.But because RISC CPU is with special-purpose assembly instruction exploitation, and command function is simple, be difficult to realize the complex calculations operation, so present network processing unit is mainly used in the IP routing device, and procotol is only handled the IP layer, carry out comparatively difficulty of upper-layer protocol processing and use it for edge network equipment.
Realize that the IP fragmentation recombination function is the basis that the IP upper-layer protocol is handled.At present be to locate same component sheets to realize recombination function on general processor by the mode of traversal chained list, and timer manages the use of the internal storage location that is used to store fragment message, and the IP packet loss of soon not recombinated to after date when timer is to discharge the internal storage location that it takies.In the process that realizes reorganization, each fragment message at first will be from MAC (Media Access Control, be media interviews control) a scratchpad area (SPA) in the internal memory that copies in the buffer memory of chip, and then copy the buffer storage unit (buffer) that is used for reconstructed file to and recombinate, be that general processor is not the original position reorganization when realizing the IP fragmentation reorganization, must copy and just can finish for twice.
Realizing on the network processing unit that the simplest method of IP fragmentation message reorganization is exactly to adopt the processing mode of above-mentioned general processor to realize on Host CPU, but this mode does not have any advantage of actual performance network processing unit, because the Host CPU frequency of network processing unit is more much lower than general processor, and the restriction of its hardware configuration makes Host CPU can not therefore only realize the advantage of the recombination function competence exertion network processing unit of IP fragmentation message on RISCCPU directly to the operation of data surface message usually.But because the exploitation of RISCCPU employing assembly instruction is unsuitable for adopting the mode that travels through chained list to realize the reorganization of IP fragmentation, also be difficult to safeguard a timer queue, realize that therefore the reorganization of IP fragmentation message is relatively more difficult by complicated algorithm.
Summary of the invention
The purpose of this invention is to provide a kind of processor Network Based and realize the method for IP message fragment reorganization, be not suitable for the technical problem that edge network equipment carries out the higher layer applications protocol processes to overcome current network processing unit.
The technical scheme that realizes technical problem to be solved by this invention and take is summarized as follows,
Provide a kind of processor Network Based to realize the method for IP message fragment reorganization, may further comprise the steps:
(1) creates the hash index table;
(2) distribute two buffer storages that are used for the storing IP fragment message;
(3) from the IP stem of a new IP fragmentation message receiving, extract source IP address, purpose IP address, sign, sheet skew and length information;
(4) utilize described source IP address, purpose IP address, sign to carry out Hash operation, according to hash units of operation result application as input;
(5) buffer storage unit of application from described wherein a slice buffer storage, and judge whether this sheet buffer storage is applied and finish that if application finishes, then described another sheet buffer storage is used in application;
(6) the IP stem is saved in the described buffer storage unit;
(7) according to the sheet offset information of the described IP fragmentation message that receives this IP fragmentation message is saved in the relevant position of described buffer storage unit, and the first address of this buffer storage unit is saved in the described hash units;
(8) judge whether received IP fragmentation message is last a slice, if, then calculate the IP message total length of all the IP fragmentation message correspondences that need recombinate, and with IP message total length information stores in hash units, execution in step (9); If not, then direct execution in step (9);
(9) calculate the total length of the current IP fragmentation message of having received, with described total length information updating in hash units;
(10) total length and the described IP message total length with the current IP fragmentation message of having received of described calculating compares, if unequal, execution in step (11), if equate that then this group IP fragmentation message is all received, reorganization finishes, execution in step (13);
(11) receive follow-up IP fragmentation message, utilize source IP address, purpose IP address and sign in its IP stem to carry out Hash operation, navigate in the corresponding hash units;
(12) from hash units, take out the buffer storage unit first address, copy the data net load of this fragment message to the relevant position of described buffer storage unit, execution in step (8) according to the sheet offset information of this IP fragmentation message;
(13) discharge the employed hash units of this IP message, discharge two buffer storage units that it takies.
Adopt technical scheme of the present invention, compared with prior art, not only improved the speed and the efficient of the reorganization of IP fragmentation message, but also had the advantage of burst accurate positioning.By two buffer storage mechanism, make and realize that on network processing unit the IP fragmentation reorganization becomes possibility, and make regrouping process more simple effectively simultaneously.Can on network processing unit, carry out the IP upper-layer protocol by this method and handle, thereby make network processing unit can substitute common processor applications in edge network equipment, bring into play its important function.
Description of drawings
Fig. 1 shows network processing unit functional structure schematic diagram;
Fig. 2 shows IP heading form;
Fig. 3 shows IP message fragment process schematic diagram of the present invention;
Fig. 4 shows the present invention and realize IP fragmentation message regrouping process schematic diagram in buffer storage unit.
Embodiment
Below in conjunction with accompanying drawing, illustrate the mode of concrete enforcement of the present invention.
Fig. 2 has provided IP heading form, the burst and the reorganization that wherein identify, three fields of sign and sheet skew are used for controlling the IP datagram literary composition.The burst stem of the IP fragmentation message behind the burst has identical identification field, and to levy this message by the flag bit bit table be a burst, and the order of burst is then decided by the sheet skew.The burst process of IP message as shown in Figure 3.
When on network processing unit, adopting the inventive method to realize IP fragmentation message reorganization beginning, the initialization preparation of at first carrying out the burst reorganization, mainly finish two tasks:
1) creates a Hash (Hash) concordance list;
2) create the index queue that two management cushion (buffer) memory blocks, be responsible for the application and the release of buffer storage unit.
The hash index table is an information index table, the corresponding one group of fragment message to be recombinated of each hash units, and the in store key message relevant in this unit with reorganization, preserved following information in the methods of the invention in the hash units:
● the source IP address of IP fragmentation message;
● the purpose IP address of IP fragmentation message;
● 16 bit-identifies of IP fragmentation message;
● the total length of the current IP fragmentation message of having received;
● the total length of the IP message that all this component sheets message reorganization backs are corresponding;
● the buffer storage unit first address.
The initial value of the total length of the IP message that the total length of the wherein current fragment message of having received and all this component sheets messages reorganization back are corresponding is 0.
Represent that this unit is unoccupied when the total length information of the current fragment message of preserving in the hash units of having received is zero, the IP fragmentation message that explanation is simultaneously received is one group of new fragment message; Illustrate then that when this information is non-vanishing this burst may be a follow-up burst.
When receiving an IP fragmentation message, at first from the IP stem of this burst, take out source IP address, purpose IP address, sign, sheet skew and length information, wherein source IP address, purpose IP address and sign can one group of IP fragmentation messages of unique identification.Utilize source, purpose IP address and sign to carry out Hash operation, and navigate to a hash units according to the Hash operation result as input parameter.Whether the total length by judging the current IP fragmentation message of having received is zero to determine whether to be a new hash units, specifically is divided into following three kinds of situations according to the difference of judging as a result:
The total length that first kind of situation is the current IP message of having received is zero, promptly receives a new IP fragmentation message, and treatment step is as follows:
A) source IP address, purpose IP address, sign and the length information with this message is saved in the hash units;
B) apply for a buffer storage unit by index queue for it, the IP stem is saved in the buffer storage unit, and the data net load is saved in the relevant position of memory block according to the sheet offset information.It is directly actuated by RISC CPU preserving copy procedure, according to the position of sheet offset information determination data payload in buffer storage unit.After the memory cell in a slice buffer storage has been applied, pass through another index queue immediately from another sheet buffer storage application buffer storage unit;
C) upgrade the current fragment message total length information of having received in the hash units;
D) flag bit of the IP stem by this fragment message judges whether this burst is last burst, if, then according to the total length of sheet calculations of offset reorganization back entire I P message, and this length information is saved in the position of the total length of the corresponding IP message in all this component sheets messages reorganization backs of hash units.
The total length that second kind of situation is the current message of having received is non-vanishing, then whether source, purpose IP address and the sign of relatively preserving in source, purpose IP address and the sign in this IP fragmentation message IP stem and the hash units all equates, if all equate, then this fragment message is the follow-up IP fragmentation message of this group, and treatment step is as follows:
A) calculate the length of this IP fragmentation message data net load, be added to the current information bit of having received the fragment message total length in the hash units;
B) from hash units, take out the buffer storage unit first address, and the data net load is saved in the relevant position of memory cell according to the skew of the sheet of this sheet message, it is directly actuated by RISC CPU preserving copy procedure, according to the position of sheet offset information determination data payload in buffer storage unit, finish the reorganization of burst in the time of copy;
C) flag bit of the IP stem by this fragment message judges whether this fragment message is last burst, if, then according to the total length of sheet calculations of offset reorganization back entire I P message, and this length information is saved in the position of the total length of the corresponding IP message in all this component sheets messages reorganization backs of hash units;
D) judge whether the current fragment message total length of receiving in the hash units equates with reorganization back message total length, if equate, represent that then this organizes all IP fragmentation messages and all collect, reorganization is finished, and has received that with current the total length information zero clearing of the IP message that fragment message total length information and all this component sheets message reorganization backs are corresponding is to discharge hash units.
The third situation is that the total length of the current message of having received is non-vanishing, source, purpose IP address and the sign of storing in source, purpose IP address and sign and the hash units in this fragment message IP stem relatively, as inequal or unequal entirely entirely, then show the generation hash-collision, and determine that this fragment message is a new fragment message, treatment step is as follows:
A) with the current total length information zero clearing of having received the IP message of fragment message total length information and all this component sheets messages reorganization back correspondence in the hash units;
B) with it as a new fragment message, handle by above-mentioned first kind of situation.
From above description as can be seen each IP fragmentation message only copied once at whole regrouping process, promptly copy to the buffer storage unit from the MAC peripheral hardware.Sheet offset information according to message in copy procedure is stored in the relevant position of buffer storage unit with payload user data, thereby is realizing the original position reorganization.Fig. 4 has provided the present invention and realized the application process schematic diagram that original position is recombinated in buffer storage unit.We are transmitted as example with Ethernet, as shown in FIG.: standard MAC head length degree is 14 bytes, and IP typical length is 20 bytes, because the payload length of IP fragmentation message is a unit with 8 bytes, so for convenience of description, the buffer storage that provides for example among Fig. 4 (buffer) also is 8 bytes.
In sum, a kind of processor Network Based provided by the invention is realized the method for IP message fragment reorganization, may further comprise the steps:
(1) creates the hash index table;
(2) distribute two buffer storages that are used to store burst IP message;
(3) from the IP stem of a new IP fragmentation message receiving, extract source IP address, purpose IP address, sign, sheet skew and length information;
(4) utilize described source IP address, purpose IP address, sign to carry out Hash operation, according to hash units of operation result application as input;
(5) buffer storage unit of application from described wherein a slice buffer storage, and judge whether this sheet buffer storage is applied and finish that if application finishes, then described another sheet buffer storage is used in application;
(6) the IP stem is saved in the described buffer storage unit;
(7) according to the sheet offset information of the described IP fragmentation message that receives this IP fragmentation message is saved in the relevant position of described buffer storage unit, and the first address of this buffer storage unit is saved in the described hash units;
(8) judge whether received IP fragmentation message is last a slice, if, then calculate the IP message total length of all the IP fragmentation message correspondences that need recombinate, and with IP message total length information stores in hash units, execution in step (9); If not, then direct execution in step (9);
(9) calculate the total length of the current IP fragmentation message of having received, with described total length information updating in hash units;
(10) total length and the described IP message total length with the current IP fragmentation message of having received of described calculating compares, if unequal, execution in step (11), if equate that then this group IP fragmentation message is all received, reorganization finishes, execution in step (13);
(11) receive follow-up IP fragmentation message, utilize source IP address, purpose IP address and sign in its IP stem to carry out Hash operation, navigate in the corresponding hash units;
(12) from hash units, take out the buffer storage unit first address, copy the data net load of this fragment message to the relevant position of described buffer storage unit, execution in step (8) according to the sheet offset information of this IP fragmentation message;
(13) discharge the employed hash units of this IP message, discharge two buffer storage units that it takies.
Simultaneously as can be seen, method provided by the present invention has following three big features:
At first, adopt Hash operation to locate one group of IP fragmentation message,, adopt Hash operation to have the advantage of the fast and accurate positioning of burst locating speed with comparing of traversal chained list;
Secondly,, but adopt biplate buffer storage mechanism, deposited burst to be recombinated when a slice buffer storage uses another sheet buffer storage at once after using up at the regrouping process need no timer.Adopt biplate cache management mode, guaranteed owing to all bursts do not receive all that hanging dead buffer storage unit finally can be released.
At last, can realize the original position reorganization.But the transfer of data between the RISC CPU direct control in the network processing unit and control internal memory and MAC peripheral hardware, thus the process that data message is copied to internal memory from the buffering area of MAC peripheral hardware, can finish recombination function, need not secondary and copy.
In sum, the method of processor realization IP fragmentation message Network Based reorganization proposed by the invention is compared with the IP fragmentation message recombining method that general processor is adopted, has need no timer, original position can realize the advantage of recombinating, it locatees one group of IP fragmentation by Hash operation, not only improved the speed of reorganization, and make regrouping process become effectively simple more, thereby make network processing unit can be applicable to edge network equipment, and then alternative general processor carry out the processing of IP upper layer application protocol.For example in an enforceable typical applications of the present invention; The packet domain of WCDMA (Wideband Code Division MultipleAccess, i.e. broadband CDMA system) system is for realizing the multi-medium data business in high speed, broadband, and general processor has not met the demands, must adopt network processing unit to realize.Its two big functional entity GGSN (Gateway GPRS Support Node, it is the gateway GPRS support point, wherein GPRS is General Packet Radio Service a---grouping service wireless) and SGSN (Serving GPRSSupport Node, be the service GPRS support point) will be as edge network equipment to being carried on GTP (GPRSTunnel Protocol, being the GPRS channel protocol) user face data message on the agreement all handles, and the GTP agreement is carried on the IP agreement, so will handle the Packet data service of GTP encapsulation, can adopt processor Network Based provided by the invention to realize the method for the reorganization of IP fragmentation message.
Although the disclosed method that relates to processor realization IP message fragment Network Based reorganization has been carried out special description with reference to embodiment, those skilled in the art can understand, under the situation that does not depart from scope and spirit of the present invention, can carry out all conspicuous modification of form and details to it.Therefore, embodiment described above is illustrative and not restrictive, and under the situation that does not break away from the spirit and scope of the present invention, all variations and modification are all within the scope of the present invention.
Claims (3)
1, a kind of processor Network Based is realized the method for IP message fragment reorganization, it is characterized in that may further comprise the steps:
(1) creates the hash index table;
(2) distribute two buffer storages that are used for the storing IP fragment message;
(3) from the IP stem of a new IP fragmentation message receiving, extract source IP address, purpose IP address, sign, sheet skew and length information;
(4) utilize described source IP address, purpose IP address, sign to carry out Hash operation, according to hash units of operation result application as input;
(5) buffer storage unit of application from described wherein a slice buffer storage, and judge whether this sheet buffer storage is applied and finish that if application finishes, then described another sheet buffer storage is used in application;
(6) the IP stem is saved in the described buffer storage unit;
(7) according to the sheet offset information of the described IP fragmentation message that receives this IP fragmentation message is saved in the relevant position of described buffer storage unit, and the first address of this buffer storage unit is saved in the described hash units;
(8) judge whether received IP fragmentation message is last a slice, if, then calculate the IP message total length of all the IP fragmentation message correspondences that need recombinate, and with IP message total length information stores in hash units, execution in step (9); If not, then direct execution in step (9);
(9) calculate the total length of the current IP fragmentation message of having received, with described total length information updating in hash units;
(10) total length and the described IP message total length with the current IP fragmentation message of having received of described calculating compares, if unequal, execution in step (11), if equate that then this group IP fragmentation message is all received, reorganization finishes, execution in step (13);
(11) receive follow-up IP fragmentation message, utilize source IP address, purpose IP address and sign in its IP stem to carry out Hash operation, navigate in the corresponding hash units;
(12) from hash units, take out the buffer storage unit first address, copy the data net load of this fragment message to the relevant position of described buffer storage unit, execution in step (8) according to the sheet offset information of this IP fragmentation message;
(13) discharge the employed hash units of this IP fragmentation message, discharge two buffer storage units that it takies.
2, method according to claim 1 is characterized in that the initial value of the IP fragmentation message total length information of the total length of the described current IP fragmentation message of having received and all the IP fragmentation message correspondences that need recombinate is 0.
3, method according to claim 1 is characterized in that step (11) is further comprising the steps of:
(a) whether source, purpose IP address and the sign of relatively preserving in source, purpose IP address and the sign in this follow-up IP fragmentation message IP stem and the hash units equates, if all equate, then continues to change over to step (12) processing; Otherwise,
(b), change step (4) over to and continue to handle with the current IP fragmentation message total length information zero clearing of having received IP fragmentation message total length information and all the IP fragmentation message correspondences that need recombinate in the hash units.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB021377987A CN100338923C (en) | 2002-10-31 | 2002-10-31 | Method of realizing IP message partition and recombination based on network processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB021377987A CN100338923C (en) | 2002-10-31 | 2002-10-31 | Method of realizing IP message partition and recombination based on network processor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1494274A CN1494274A (en) | 2004-05-05 |
| CN100338923C true CN100338923C (en) | 2007-09-19 |
Family
ID=34231711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB021377987A Expired - Fee Related CN100338923C (en) | 2002-10-31 | 2002-10-31 | Method of realizing IP message partition and recombination based on network processor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100338923C (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7508771B2 (en) * | 2005-04-01 | 2009-03-24 | International Business Machines Corporation | Method for reducing latency in a host ethernet adapter (HEA) |
| CN100454900C (en) * | 2006-01-24 | 2009-01-21 | 华为技术有限公司 | Method and system for quick responding IP banding message |
| CN100420238C (en) * | 2006-04-12 | 2008-09-17 | 华为技术有限公司 | Method for partitioned recombining IP message |
| CN1921477A (en) * | 2006-09-01 | 2007-02-28 | 华为数字技术有限公司 | Method and system for complicated flow classification of arrange cutted piece message |
| CN100464536C (en) * | 2006-09-18 | 2009-02-25 | 华为技术有限公司 | Method and device for recomposing fragmented data |
| CN101237405B (en) * | 2008-03-06 | 2012-10-17 | 华为技术有限公司 | Data buffer method and device |
| CN101510815B (en) * | 2008-12-31 | 2012-01-04 | 成都市华为赛门铁克科技有限公司 | Method, apparatus and system for processing slicing message |
| CN101932006A (en) * | 2009-06-19 | 2010-12-29 | 中兴通讯股份有限公司 | Method for sending, receiving and transmitting data packets and device therefor |
| CN101645851B (en) * | 2009-09-03 | 2012-07-18 | 中兴通讯股份有限公司 | Recombination method for IP fragment messages and device thereof |
| CN102123090B (en) * | 2011-02-23 | 2012-07-04 | 中国人民解放军国防科学技术大学 | IP (Internet protocol) fragment processing method based on two-level table storage and transport layer information inquiry |
| CN102811158A (en) * | 2011-06-02 | 2012-12-05 | 中兴通讯股份有限公司 | Data positioning and recombining method and corresponding device |
| CN103501279B (en) * | 2013-09-27 | 2016-09-07 | 北京旋极信息技术股份有限公司 | A kind of avionics full-duplex real-time Ethernet data package reconstitution method and system |
| CN104639511B (en) * | 2013-11-13 | 2018-08-03 | 安凯(广州)微电子技术有限公司 | A kind of implementation method and device for saving memory |
| CN104348760B (en) * | 2014-10-11 | 2017-12-26 | 北京中创腾锐技术有限公司 | A kind of method realized IP fragmentation and sequentially sent piecewise |
| CN106685862B (en) * | 2015-11-11 | 2019-11-12 | 大唐移动通信设备有限公司 | A kind of packet segment processing method and processing device |
| CN105610744B (en) * | 2016-01-28 | 2018-10-23 | 东南大学 | A kind of IP packet fragment and recombination method and device |
| CN107065750B (en) * | 2017-05-15 | 2019-04-02 | 中国工程物理研究院计算机应用研究所 | The industrial control network dynamic security method of interior raw safety |
| CN111163022B (en) * | 2018-11-08 | 2023-01-10 | 深圳市中兴微电子技术有限公司 | Message transmission method and device and computer readable storage medium |
| CN109618020B (en) * | 2018-12-25 | 2022-01-11 | 北京物芯科技有限责任公司 | Network address conversion method and device for fragmented messages |
| CN112769520B (en) * | 2019-11-05 | 2022-11-22 | 中国科学院声学研究所 | Complete data packet retention method and system based on IP fragmentation |
| CN114553885A (en) * | 2022-03-02 | 2022-05-27 | 上海弘玑信息技术有限公司 | DHT network-based storage method and device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1221548A (en) * | 1996-04-10 | 1999-06-30 | 艾利森电话股份有限公司 | Minicell segmentation and reassembly |
| US6094432A (en) * | 1996-11-04 | 2000-07-25 | Lg Information & Communications, Ltd. | Apparatus for and method of segmenting and reassembling constant bit rate traffic in asynchronous transfer mode network |
-
2002
- 2002-10-31 CN CNB021377987A patent/CN100338923C/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1221548A (en) * | 1996-04-10 | 1999-06-30 | 艾利森电话股份有限公司 | Minicell segmentation and reassembly |
| US6094432A (en) * | 1996-11-04 | 2000-07-25 | Lg Information & Communications, Ltd. | Apparatus for and method of segmenting and reassembling constant bit rate traffic in asynchronous transfer mode network |
Non-Patent Citations (1)
| Title |
|---|
| IP数据报重组算法及实现 陈蕾蕾 曲保章，今日电子，第7期 1998 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1494274A (en) | 2004-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100338923C (en) | Method of realizing IP message partition and recombination based on network processor | |
| CN1183718C (en) | System and method for packet data servicing node (PDSN) initial assignment and reselection | |
| CN101040492A (en) | Systems and methods for packet based handoff in wireless communication systems | |
| CN1270553C (en) | System and method for discovering path mtu in ad hoc network | |
| CN1610301A (en) | A method of providing packetized data from a radio network controller to a base station | |
| CN1913534A (en) | Data processing method and communication equipment | |
| CN1528077A (en) | Protocol data unit encapsulation method | |
| CN1292961A (en) | Reduced packet header in wireless communications network | |
| JP2007511136A5 (en) | ||
| CN110768994A (en) | Method for improving SIP gateway performance based on DPDK technology | |
| CN1992672A (en) | Method for preventing network interruption caused by address aging and time inconformity | |
| CN1913454A (en) | Method and device for implementing sharing IP message load | |
| CN1742469A (en) | Methods and devices for transmitting data between storage area networks | |
| CN1302645C (en) | Method for realizing average flow bearing by bound ports of network processor system | |
| CN1798098A (en) | Method of differentiating multiple services for anti IP data stream in multicast to impact communication system | |
| CN101030937A (en) | Multilevel random accessing method based on packet | |
| CN1925458A (en) | Method for realizing network port address conversion | |
| CN1783876A (en) | System and method for realizing packet data polymerized protocol function | |
| CN1863140A (en) | Method for improving network resource utilization ratio of wireless communication system | |
| CN1301607C (en) | Method for implementing supporting virtual local network fire wall | |
| CN1787475A (en) | Access network system and method of moving internal network relay devices | |
| CN102624727B (en) | Interface configuration method, device, master control central processing unit and network equipment | |
| CN1859601A (en) | Method for configurating radio link parameter | |
| CN1697445A (en) | Implementation method for transferring data in virtual private network | |
| CN1878121A (en) | Multicast group maintaining method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20070919 Termination date: 20141031 |
|
| EXPY | Termination of patent right or utility model |