CN105791163B - Update processing method and processing device - Google Patents
Update processing method and processing device Download PDFInfo
- Publication number
- CN105791163B CN105791163B CN201410836357.3A CN201410836357A CN105791163B CN 105791163 B CN105791163 B CN 105791163B CN 201410836357 A CN201410836357 A CN 201410836357A CN 105791163 B CN105791163 B CN 105791163B
- Authority
- CN
- China
- Prior art keywords
- tcam
- processing
- dram
- table handling
- updated
- 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
Landscapes
- Memory System (AREA)
- Dram (AREA)
Abstract
The invention discloses a kind of update processing method and processing devices, wherein this method comprises: determining that the TCAM of three-state content addressing TCAM entry writes table handling and dynamic random access memory DRAM writes table handling；Table handling is write to the TCAM of the ACL of the TCAM entry and the DRAM writes table handling and carries out parallel update processing.Through the invention, solve the problems, such as in the related technology to large capacity I cam entry update low efficiency, thus improve large capacity I cam entry update efficiency effect.
Description
Technical field
The present invention relates to the communications fields, in particular to a kind of update processing method and processing device.
Background technique
Network today development speed is surprising, the growth of network flow and the appearance of new business, and the network equipment is needed to have line
Fast and flexible processing capacity.Network chip includes ASIC and NP (network processing unit) two major classes at present.Network processing unit relies on
Its high speed processing and flexible programmability, it has also become the effective solution of data processing in current network.
There are many different memories in network processing unit, such as static random reservoir (Static Random Access
Ram, referred to as SRAM), three-state content addressing memory (ternary content addressable memory, referred to as
TCAM), synchronous dynamic random reservoir (Dynamic Random Access Ram, referred to as SDRAM) etc., these memories
Store various businesses list item, such as port table, MAC table, routing table.
TCAM is a kind of three-state content addressing memory, is mainly used for quickly searching the list items such as ACL, routing.The master of TCAM
Wanting feature is fast parallel lookup, and the application on network processing unit is usually that microcode extracts relevant information composition one from message
A KEY (key assignments) sends look-up command to TCAM by the TCAM controller of NP, according to result treatment message.
A kind of common network processing unit connects TCAM mode at present, and Fig. 1 is the ACL device based on TCAM in the related technology
Schematic diagram, as shown in Figure 1.CPU accesses external TCAM by the TCAM adaptable interface of NP, passes through between NP and TCAM
Interlaken bus bar.
It is accesses control list (Access Control List, referred to as ACL) that a kind of typical services of TCAM, which are applied,
As shown in Figure 1, wherein acl rule is deposited in the connected external TCAM of NP；The storage of ACL action schedule is that external dynamic is stored up at random
In storage (Dynamic Random Access Ram, referred to as DRAM).In TCAM in rule corresponding TCAM entry and DRAM
Movement table clause correspond.For NP microcode, hit TCAM entry can return to the address TCAM to NP, and NP passes through the address
It is converted into address of the corresponding actions table clause in DRAM, find action schedule and executes related ACL movement.
TCAM entry data width is usually very wide at present, and typically, IPV6ACL, TCAM key assignments usually requires 640BIT
More than；In addition, DRAM advantage is large capacity, but its renewal rate is also slow.It is TCAM that industry ACL, which updates common practice, at present
It is serial operation with DRAM update, under large capacity acl entry update status, under update efficiency is very low.
Aiming at the problem that updating low efficiency to large capacity I cam entry in the related technology, effective solution is not yet proposed at present
Scheme.
Summary of the invention
The present invention provides a kind of update processing method and processing devices, at least to solve in the related technology to large capacity I CAM item
Mesh updates the problem of low efficiency.
According to an aspect of the invention, there is provided a kind of update processing method, comprising: determine three-state content addressing TCAM
The TCAM of entry writes table handling and dynamic random access memory DRAM writes table handling；The TCAM of the TCAM entry is write
Table handling and the DRAM write table handling and carry out parallel update processing.
Further, table handling is write to the TCAM of the TCAM entry and the DRAM writes table handling and carries out parallel more
New processing include: it is no complete to write the TCAM of the TCAM entry table handling update processing in the case where, start pair
The DRAM writes table handling and is updated processing.
Further, table handling is write to the TCAM of the TCAM entry and the DRAM writes table handling and carries out parallel more
New processing includes: to judge whether to carry out parallel update processing to the TCAM of the TCAM entry and DRAM for the first time；?
Judging result is to carry out parallel update processing to the TCAM and the DRAM of the TCAM entry in the case where being.
Further, table handling is write to the TCAM of the TCAM entry and the DRAM writes table handling and carries out parallel more
Whether new processing includes: if the determination result is NO, once to complete to be updated processing to the TCAM before judgement；?
Judging result is in the case where being, to be updated processing to the TCAM；Once whether complete to carry out the DRAM before judgement
Update processing；In the case where the judgment result is yes, processing is updated to the DRAM.
Further, table handling is write to the TCAM of the TCAM entry and the DRAM writes table handling and carries out parallel more
New processing include: the TCAM of this TCAM entry write table handling and the DRAM write table handling with next time described in
The TCAM of TCAM entry writes table handling and the DRAM writes table handling and carries out parallel update processing.
Further, table handling write the TCAM of this TCAM entry and the DRAM write table handling with it is next
The TCAM of the secondary TCAM entry writes table handling and the DRAM writes table handling and carries out parallel update to handle including: to start
After being updated processing to the DRAM, in the case where preceding primary completion is updated processing to the TCAM, to described
TCAM is updated processing；And/or after starting to be updated processing to the TCAM, in preceding primary completion to described
In the case that DRAM is updated processing, processing is updated to the DRAM.
Further, the TCAM entry includes following one: access control lists ACL, routing table, service quality
(Quality of Service, referred to as QoS).
According to another aspect of the present invention, a kind of renewal processing device is provided, comprising: determining module, for determining three
The TCAM of the content addressed TCAM entry of state writes table handling and dynamic random access memory DRAM writes table handling；Update processing mould
Block writes table handling for the TCAM to the TCAM entry and the DRAM writes table handling and carries out parallel update processing.
Further, the update processing module includes: the first update processing unit, for completing no to described
In the case that the TCAM of TCAM entry writes table handling update processing, starts to write table handling to the DRAM and be updated place
Reason.
Further, the update processing module includes: the first judging unit, for judging whether for the first time to the TCAM
The TCAM and the DRAM of entry carry out parallel update processing；Second updates processing unit, for being yes in judging result
In the case where, parallel update processing is carried out to the TCAM and the DRAM of the TCAM entry.
Further, the update processing module includes: second judgment unit, the situation for being no in judging result
Under, once whether complete to be updated processing to the TCAM before judgement；Third updates processing unit, for being in judging result
In the case where being, processing is updated to the TCAM；Third judging unit, for once whether being completed to described before judging
DRAM is updated processing；4th updates processing unit, in the case where the judgment result is yes, carrying out more to the DRAM
New processing.
Further, the update processing module includes: the 5th update processing unit, for the TCAM item to this
TCAM described in purpose writes table handling and the DRAM writes table handling and the TCAM of the TCAM entry next time writes table behaviour
Make and the DRAM writes table handling and carries out parallel update processing.
Further, it includes: the first update processing subelement that the third, which updates processing unit, for starting to described
DRAM is updated after processing, it is preceding it is primary completion processing is updated to the TCAM in the case where, to the TCAM into
Row update processing；And/or second update processing subelement, for after starting to be updated processing to the TCAM, preceding
It is primary to complete in the case where being updated processing to the DRAM, processing is updated to the DRAM.
Through the invention, table handling is write using the TCAM of determining TCAM entry and dynamic random access memory DRAM writes table
Operation；Table handling is write to the TCAM of the TCAM entry and the DRAM writes table handling and carries out parallel update processing, is solved
The problem of low efficiency is updated to large capacity I cam entry in the related technology, thus the large capacity I cam entry of improving update effect
The effect of rate.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the schematic diagram of the ACL device based on TCAM in the related technology；
Fig. 2 is the flow chart according to an embodiment of the present invention for updating processing method；
Fig. 3 is the block diagram of renewal processing device according to an embodiment of the present invention；
Fig. 4 is the block diagram of the renewal processing device of preferred embodiment one according to the present invention；
Fig. 5 is the block diagram of the renewal processing device of preferred embodiment two according to the present invention；
Fig. 6 is the block diagram of the renewal processing device of preferred embodiment three according to the present invention；
Fig. 7 is the block diagram of the renewal processing device of preferred embodiment four according to the present invention；
Fig. 8 is the block diagram of the renewal processing device of preferred embodiment five according to the present invention；
Fig. 9 is the flow chart that ACL in the related technology writes table；
Figure 10 is that ACL according to an embodiment of the present invention writes table flow chart.
Specific embodiment
Hereinafter, the present invention will be described in detail with reference to the accompanying drawings and in combination with Examples.It should be noted that not conflicting
In the case of, the features in the embodiments and the embodiments of the present application can be combined with each other.
A kind of update processing method is provided in the present embodiment, and Fig. 2 is update processing side according to an embodiment of the present invention
The flow chart of method, as shown in Fig. 2, the process includes the following steps:
Step S202 determines that the TCAM of three-state content addressing TCAM entry writes table handling and dynamic random access memory
DRAM writes table handling；
Step S204 writes table handling to the TCAM of the TCAM entry and the DRAM writes table handling and carries out at parallel update
Reason.
Through the above steps, determine that the TCAM of TCAM entry writes table handling and dynamic random access memory DRAM writes table behaviour
Make；Table handling is write to the TCAM of the TCAM entry and the DRAM writes table handling and carries out parallel update processing, wherein TCAM entry
For the related service being written according to TCAM format, for example, it may be access control list ACL, routing table or QoS, solve phase
The problem of low efficiency is updated to large capacity I cam entry in the technology of pass, thus the large capacity I cam entry of improving update efficiency
Effect.
Table handling is write to the TCAM of the TCAM entry and the DRAM writes the mode that table handling carries out parallel update processing and has
Many kinds may include: in an alternative embodiment to write table handling more to the TCAM of the TCAM entry in no completion
In the case where new processing, start to write the DRAM table handling and be updated processing, due to writing table handling update without waiting for TCAM
Be disposed, so that it may table handling directly is write to DRAM and is updated processing, thus substantially reduce update TCAM entry when
Between, improve update efficiency.
Table handling write to the TCAM of the TCAM entry and the DRAM write table handling carry out parallel update processing can be with root
According to whether being the processing of update for the first time, so that different processing is made, it is first determined whether for the first time to the TCAM of the TCAM entry
And the DRAM carries out parallel update processing；In the case where the judgment result is yes, to TCAM of the TCAM entry and DRAM
It carries out parallel update processing: if the determination result is NO, once whether completing to be updated place to the TCAM before judgement
Reason；In the case where the judgment result is yes, processing is updated to the TCAM；Once whether complete to carry out the DRAM before judgement
Update processing；In the case where the judgment result is yes, processing is updated to the DRAM.
Table handling is write to the TCAM of the TCAM entry and the DRAM writes the parallel update processing of table handling progress and can also wrap
Include: table handling write to the TCAM of this TCAM entry and the DRAM writes table handling and the TCAM entry next time should
TCAM writes table handling and the DRAM writes table handling and carries out parallel update processing.It can be realized: started by mode below
After being updated processing to the DRAM, it is preceding it is primary completion processing is updated to the TCAM in the case where, to the TCAM into
Row update processing；And/or after starting to be updated processing to the TCAM, the DRAM is updated in preceding primary completion
In the case where processing, processing is updated to the DRAM, update processing is executed by repeatedly parallel, improves to TCAM entry
More line efficiency.
Above-mentioned TCAM entry may include following one: access control list ACL, routing table, service quality QoS.
The embodiment of the invention also provides a kind of renewal processing device, the device is real for realizing above-described embodiment and preferably
Mode is applied, the descriptions that have already been made will not be repeated.As used below, the soft of predetermined function may be implemented in term " module "
The combination of part and/or hardware.Although device described in following embodiment is preferably realized with software, hardware, or
The realization of the combination of software and hardware is also that may and be contemplated.
Fig. 3 is the block diagram of renewal processing device according to an embodiment of the present invention, as shown in Figure 3, comprising:
Determining module 32, for determining that the TCAM of three-state content addressing TCAM entry writes table handling and dynamic randon access storage
Storage DRAM writes table handling；
Processing module 34 is updated, table handling is write for the TCAM to the TCAM entry and the DRAM writes table handling and carries out simultaneously
Row update processing.
Fig. 4 is the block diagram of the renewal processing device of preferred embodiment one according to the present invention, as shown in figure 4, the update is handled
Module 34 includes:
First updates processing unit 42, for completing to write the TCAM of the TCAM entry table handling update processing no
In the case where, start to write the DRAM table handling and is updated processing.
Fig. 5 is the block diagram of the renewal processing device of preferred embodiment two according to the present invention, as shown in figure 5, the update is handled
Module 34 includes:
First judging unit 52 for the first time carries out parallel more TCAM of the TCAM entry and DRAM for judging whether
New processing；
Second updates processing unit 54, in the case where the judgment result is yes, the TCAM to the TCAM entry and
The DRAM carries out parallel update processing.
Fig. 6 is the block diagram of the renewal processing device of preferred embodiment three according to the present invention, as shown in fig. 6, the update is handled
Module 34 includes:
Second judgment unit 62, for if the determination result is NO, once whether being completed to the TCAM before judgement
It is updated processing；
Third updates processing unit 64, in the case where the judgment result is yes, being updated processing to the TCAM；
Third judging unit 66, for once whether completing to be updated processing to the DRAM before judging；
4th updates processing unit 68, in the case where the judgment result is yes, being updated processing to the DRAM.
Fig. 7 is the block diagram of the renewal processing device of preferred embodiment four according to the present invention, as shown in fig. 7, the update is handled
Module 34 includes:
5th updates processing unit 72, and the TCAM for the TCAM entry to this writes table handling and the DRAM writes table
The TCAM of operation and the TCAM entry next time writes table handling and the DRAM writes table handling and carries out parallel update processing.
Fig. 8 is the block diagram of the renewal processing device of preferred embodiment five according to the present invention, as shown in figure 8, the third updates
Processing unit 72 includes:
First updates processing subelement 82, for after starting to be updated processing to the DRAM, in preceding primary completion
In the case where being updated processing to the TCAM, processing is updated to the TCAM；And/or
Second updates processing subelement 84, for after starting to be updated processing to the TCAM, in preceding primary completion
In the case where being updated processing to the DRAM, processing is updated to the DRAM.
Below by taking TCAM entry is access control list ACL as an example, the embodiment of the present invention is carried out in conjunction with alternative embodiment
It further illustrates.
As shown in Figure 1, the ACL device based on TCAM includes:
101CPU, control plane CPU, complete NP and TCAM configuration and ACL issues initial data to TCAM and DRAM hardware
The conversion of entry；
102NP, network processing unit, comprising:
Cpu i/f: CPU accesses TCAM and DRAM by cpu i/f；
TCAM interface: the adaptable interface of NP and TCAM, NP are interconnected by Interlaken and TCAM, are connect additionally by MDIO
Mouth carries out the register access outside band；
DRAM interface: the adaptable interface of NP and DRAM.
Fig. 9 is the flow chart that ACL in the related technology writes table, as shown in figure 9, ACL update can be attributed to three steps:
Step 1, application software layer convert acl rule according to the format that TCAM is defined；ACL is acted according to DRAM
The format of definition is converted；
Step 2 updates TCAM rule until terminating；
Step 3 updates DRAM action schedule until terminating.
These three steps are that ACL updates main three time consumptions point.The conversion of step 1 is since upper platform passes
The data format got off is passed, it is inconsistent caused with the data format of chip bottom, it is therefore desirable to which that upper layer software (applications) is in each rule
Corresponding adaptation conversion is done when then and corresponding actions issue；It is also very long that step 2 expends the time in typical applications, such as
IPV4ACL, outside in addition to five-tuple (source IP, destination IP, protocol number, source port, destination port), it is also possible to including purpose MAC, source
MAC, EtherType (ETHERTYPE), interface number etc., and the key assignments width of TCAM be typically include 80bit, 160bit,
320bit, 640bit, therefore 640bit can only be used, according to shown in Fig. 1, the data of this 80 byte are transmitted on Interlaken,
The control word (Control Word) defined plus Interlaken is also needed, data transmission period is long, additionally needs
It can just conclude that TCAM updates after TCAM return response result to complete, can just carry out step 3；Step 3 updates DRAM movement
Table, it is similar with step 2, increase now with the complexity of network service, ACL action schedule is generally also wider, and data pass through NP
PCI-E interface reach the adaptable interface of NP and DRAM, DRAM is updated by the interface, DRAM to be written is waited to terminate to complete step behaviour
Make.
Upper-layer service often in high volume writes table, such as ACL at present, and a possible user defines up to ten thousand acl rules.Industry
Common practice is that these three sequence of steps serially execute, and primary update usually requires more than ten seconds even tens seconds.
This alternative embodiment is by hardware operation, the parallel execution of software operation, for example when step 2 TCAM update, can be not required to
It waits TCAM to write table and completes simultaneously return response result, and directly carry out step 3, in step 3, also only need to open DRAM and write
Table handling need not wait for, to carry out the update of next acl entry, one the step of second circulation, assemble next
The TCAM key assignments and DRAM table content of acl rule.
In second circulation step two, when writing TCAM again, whether once-through operation executes and terminates before needing to judge, if
The TCAM that executing terminates just start second circulation writes table handling；Second circulation step three is similar, before writing DRAM
Judge whether last execute terminates.
It is operated by above-mentioned software, hardware concurrent, ACL can be greatly improved and update efficiency.
As shown in figure 9, at present ACL more new technological process the following steps are included:
Step S902, control plane assemble hardware key assignments, the ACL initial data of upper layer transfers are decomposed, one by one
The TCAM that is converted into write table key assignments and DRAM entry contents；
Step S904, writes TCAM entry, waits for, and by step S902, the TCAM key assignments write-in TCAM after assembling is rung
Entry is answered, data are transmitted on waiting Interlaken and the successful response results of table are write in TCAM return；
Step S906 writes DRAM entry, waits for, the DRAM action schedule content write-in after step S902 is assembled
DRAM appropriate address, and wait and running succeeded；
One cycle terminates, and starts circulation next time and writes the next entry of ACL, jumps to step S902.
Figure 10 is that ACL according to an embodiment of the present invention writes table flow chart, as shown in Figure 10, comprising the following steps:
Step S1002, control plane assemble hardware key assignments, the ACL initial data of upper layer transfers are decomposed, one by one
The TCAM that is converted into write table key assignments and DRAM entry contents；
Step S1004 checks that a preceding TCAM writes whether table is completed, if completed, enters step S1008, otherwise enter
Step S1006；How to judge whether preceding TCAM update is completed, there can be different implementation methods.For example, NP is usually stateful
Register, characterizes whether data transmission on Interlaken is completed, if receives data response of Interlaken etc.；If
TCAM has corresponding registers, can also be used as a preceding TCAM updates the judgment basis whether completed.It is updated to save TCAM
Efficiency, TCAM writes table and is not usually required to wait TCAM responding and analyzing, if to do TCAM parsing, needs plus preceding primary
The judgement parsing that TCAM is returned the result, if executing failure, is added unsuccessfully chained list and is unsuccessfully rewritten.The operation is not belonging to this
The core concept of patent, does not repeat them here.
Step S1006, is waited, and some cycles are waited, and enters back into step S1004 inspection, and to write table complete until preceding once
As only, latent period is usually microsecond or Millisecond；
Step S1008 starts to write TCAM, configures TCAM related register, the step S1002 key assignments assembled is started to be written
TCAM does not need to execute step S1004 it should be noted that for writing table for the first time, judgement, directly write table；This step is only
It is the data transmission for opening TCAM data in the Interlaken bus of NP and TCAM, withouts waiting for completing；
Step S1010, judges whether preceding DRAM operation is completed；
Similar with step S1004, whether once-through operation is completed before judging, if completing to enter step S1014；Otherwise enter
Step S1012；
Step S1012 is waited, and is waited some cycles, is entered back into step S1010, is checked and is once write table completion until preceding and be
Only, latent period is usually microsecond or Millisecond；
Step S1014 starts to write DRAM, configures DRAM related register, by step S1002, the key assignments of assembling starts to write
Enter DRAM.This step is the data transmission for opening DRAM data on NP and DRAM hardware bus, withouts waiting for completing；This
Secondary circulation terminates, and enters step S1002, starts issuing for next ACL data；
After all ACL datas issue completion, update terminates.
Due to being executed using parallel, when judge whether once-through operation executes completion before hardware every time, only it is very small generally
Rate, which does not complete, to be needed to wait.Actual test, using this patent method, batch ACL, which writes the table time, can shorten to serial side
1 the percent of formula.
This alternative embodiment comes into force slow problem for writing TCAM in batches at present, provides a kind of fast literary sketch table schema.It will
Software group key assignments, hardware write TCAM, hardware writes DRAM, by common serial execution, are changed to execute parallel.Not when hardware writes table
It waits, and directly carries out next step operation, execution parallel in this way, which greatly improves, writes table efficiency.Therefore this alternative embodiment is big
Many times can be saved in the case of volume write table, greatly shorten the ACL business entry-into-force time.
This alternative embodiment is opposite to write the slow problem of watch currently based on the batch ACL of TCAM, executes step by decomposition ACL
Suddenly, table completion to be written is waited to be changed to grasp parallel by serial operation usually usual at present hardware operation therein, software operation
Make, one step completed mode before rear once-through operation waits, greatly improves the ACL based on TCAM and update efficiency, especially in great Rong
It measures under ACL update status, it appears extremely have application value.
Obviously, those skilled in the art should be understood that each module of the above invention or each step can be with general
Computing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices and formed
Network on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
It is performed by computing device in the storage device, and in some cases, it can be to be different from shown in sequence execution herein
Out or description the step of, perhaps they are fabricated to each integrated circuit modules or by them multiple modules or
Step is fabricated to single integrated circuit module to realize.In this way, the present invention is not limited to any specific hardware and softwares to combine.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (9)
1. a kind of update processing method characterized by comprising
Determine that the TCAM of three-state content addressing memory TCAM entry writes table handling and dynamic random access memory DRAM writes table
Operation；
Table handling is write to the TCAM of the TCAM entry and the DRAM writes table handling and carries out parallel update processing；
Wherein, table handling is write to the TCAM of the TCAM entry and the DRAM writes table handling and carries out parallel update processing packet
It includes: judging whether to carry out parallel update processing to the TCAM of the TCAM entry and DRAM for the first time；In judging result
In the case where being, parallel update processing is carried out to the TCAM and the DRAM of the TCAM entry；
Wherein, table handling is write to the TCAM of the TCAM entry and the DRAM writes table handling and carries out parallel update processing packet
It includes: if the determination result is NO, once whether completing to be updated processing to the TCAM before judgement；In judging result
In the case where being, processing is updated to the TCAM；Once whether complete to be updated processing to the DRAM before judgement；
In the case where the judgment result is yes, processing is updated to the DRAM.
2. the method according to claim 1, wherein writing table handling and institute to the TCAM of the TCAM entry
It states DRAM and writes the parallel update of table handling progress and handle and include:
In the case where no completion writes table handling update processing to the TCAM of the TCAM entry, start to the DRAM
It writes table handling and is updated processing.
3. the method according to claim 1, wherein writing table handling and institute to the TCAM of the TCAM entry
It states DRAM and writes the parallel update of table handling progress and handle and include:
Table handling is write the TCAM of this TCAM entry and the DRAM writes table handling and the TCAM item next time
TCAM described in purpose writes table handling and the DRAM writes table handling and carries out parallel update processing.
4. according to the method described in claim 3, it is characterized in that, the TCAM this TCAM entry writes table handling
And the DRAM write table handling and the TCAM entry next time the TCAM write table handling and the DRAM write table handling into
The parallel update of row, which is handled, includes:
After starting to be updated processing to the DRAM, the case where preceding primary completion is updated processing to the TCAM
Under, processing is updated to the TCAM；And/or
After starting to be updated processing to the TCAM, the case where preceding primary completion is updated processing to the DRAM
Under, processing is updated to the DRAM.
5. method according to claim 1 to 4, which is characterized in that the TCAM entry includes following one:
Access control list ACL, routing table, service quality QoS.
6. a kind of renewal processing device characterized by comprising
Determining module, for determining that the TCAM of three-state content addressing memory TCAM entry writes table handling and dynamic randon access storage
Storage DRAM writes table handling；
Processing module is updated, table handling is write for the TCAM to the TCAM entry and the DRAM writes table handling and carries out simultaneously
Row update processing；
Wherein, the update processing module includes: the first judging unit, for judging whether the institute to the TCAM entry for the first time
It states the TCAM and DRAM and carries out parallel update processing；Second updates processing unit, is used in the case where the judgment result is yes,
Parallel update processing is carried out to the TCAM and the DRAM of the TCAM entry；
The update processing module includes: second judgment unit, for if the determination result is NO, being once before judgement
No completion is updated processing to the TCAM；Third updates processing unit, is used in the case where the judgment result is yes, to institute
It states TCAM and is updated processing；Third judging unit, for once whether completing to be updated processing to the DRAM before judging；
4th updates processing unit, in the case where the judgment result is yes, being updated processing to the DRAM.
7. device according to claim 6, which is characterized in that the update processing module includes:
First updates processing unit, for completing to write the TCAM of the TCAM entry table handling update processing no
In the case of, start to write table handling to the DRAM and is updated processing.
8. device according to claim 6, which is characterized in that the update processing module includes:
5th updates processing unit, writes table handling for the TCAM this TCAM entry and the DRAM writes table behaviour
Make to write table handling with the TCAM of the TCAM entry next time and the DRAM writes table handling and carries out parallel update processing.
9. device according to claim 8, which is characterized in that the third updates processing unit and includes:
First updates processing subelement, for after starting to be updated processing to the DRAM, in preceding primary completion to institute
It states in the case that TCAM is updated processing, processing is updated to the TCAM；And/or
Second updates processing subelement, for after starting to be updated processing to the TCAM, in preceding primary completion to institute
It states in the case that DRAM is updated processing, processing is updated to the DRAM.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410836357.3A CN105791163B (en) | 2014-12-26 | 2014-12-26 | Update processing method and processing device |
| PCT/CN2015/078622 WO2016101490A1 (en) | 2014-12-26 | 2015-05-08 | Update processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410836357.3A CN105791163B (en) | 2014-12-26 | 2014-12-26 | Update processing method and processing device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105791163A CN105791163A (en) | 2016-07-20 |
| CN105791163B true CN105791163B (en) | 2019-09-24 |
Family
ID=56149082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410836357.3A Active CN105791163B (en) | 2014-12-26 | 2014-12-26 | Update processing method and processing device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105791163B (en) |
| WO (1) | WO2016101490A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111064714A (en) * | 2019-11-29 | 2020-04-24 | 苏州浪潮智能科技有限公司 | Intelligent network card ACL updating device based on FPGA |
| CN112667526B (en) * | 2021-03-22 | 2021-06-29 | 芯启源（南京）半导体科技有限公司 | Method and circuit for realizing access control list circuit |
| CN115499345B (en) * | 2022-09-22 | 2024-05-17 | 北京沃东天骏信息技术有限公司 | Data testing method and device, storage medium and computer product |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100407693C (en) * | 2004-12-30 | 2008-07-30 | 中兴通讯股份有限公司 | Dispatching method and equipment for searching and updating routes based on FPGA |
| US7986696B1 (en) * | 2009-02-12 | 2011-07-26 | Compass Electro-Optical Systems | Method and apparatus for longest prefix matching |
| CN101986271B (en) * | 2010-10-29 | 2014-11-05 | 中兴通讯股份有限公司 | Method and device for dispatching TCAM (telecommunication access method) query and refresh messages |
| CN102307149B (en) * | 2011-09-23 | 2014-05-07 | 中国科学院计算技术研究所 | IP (internet protocol) lookup method and device and route updating method and device |
-
2014
- 2014-12-26 CN CN201410836357.3A patent/CN105791163B/en active Active
-
2015
- 2015-05-08 WO PCT/CN2015/078622 patent/WO2016101490A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| WO2016101490A1 (en) | 2016-06-30 |
| CN105791163A (en) | 2016-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8972630B1 (en) | Transactional memory that supports a put with low priority ring command | |
| CN105791163B (en) | Update processing method and processing device | |
| US8599859B2 (en) | Iterative parsing and classification | |
| CN109495293B (en) | Method, system, equipment and storage medium for testing control surface of switch | |
| CN104239337B (en) | Processing method and processing device of tabling look-up based on TCAM | |
| US11960413B2 (en) | Flow table aging optimized for DRAM access | |
| Zhao et al. | Ruletailor: Optimizing flow table updates in openflow switches with rule transformations | |
| US9852807B1 (en) | Content addressable memory in an emulation system | |
| CN115118617A (en) | Intention-driven network measurement method and system based on P4 programmable switch | |
| Tu et al. | Linux network programming with p4 | |
| CN110324204A (en) | High-speed regular expression matching engine and method implemented in FPGA (field programmable Gate array) | |
| CN105786733A (en) | TCAM (Ternary Content Addressable Memory) entry writing method and apparatus | |
| CN108173948A (en) | A kind of Distributed Experiment data real-time exchange method | |
| CN107800571B (en) | A kind of network function dynamic method of combination, device and system | |
| Belocchi et al. | Paxos in the NIC: Hardware acceleration of distributed consensus protocols | |
| WO2016197607A1 (en) | Method and apparatus for realizing route lookup | |
| US10362093B2 (en) | NFA completion notification | |
| CN105912273A (en) | FPGA-basedmessage share storage management implementation method | |
| CN105791124A (en) | Message detection method and device | |
| CN113315664B (en) | Message processing chip verification method | |
| US9729353B2 (en) | Command-driven NFA hardware engine that encodes multiple automatons | |
| CN109783417A (en) | A kind of serial communication device and method | |
| CN118101494B (en) | Network control plane protocol simulation method and device, electronic equipment and storage medium | |
| Sun et al. | A method of verification of software based on CPN | |
| Sun et al. | Modeling and analyzing web application with aspect-oriented hierarchical coloured petri nets |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190717 Address after: 210012 Nanjing, Yuhuatai District, South Street, Bauhinia Road, No. 68 Applicant after: Nanjing Zhongxing Software Co., Ltd. Address before: 518057 Nanshan District science and technology, Guangdong Province, South Road, No. 55, No. Applicant before: ZTE Corporation |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |