CN106572036A - SKB management method and apparatus - Google Patents
SKB management method and apparatus Download PDFInfo
- Publication number
- CN106572036A CN106572036A CN201610986064.2A CN201610986064A CN106572036A CN 106572036 A CN106572036 A CN 106572036A CN 201610986064 A CN201610986064 A CN 201610986064A CN 106572036 A CN106572036 A CN 106572036A
- Authority
- CN
- China
- Prior art keywords
- skb
- hardware interface
- queues
- cpu
- hard
- 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/30—Peripheral units, e.g. input or output ports
- H04L49/3018—Input queuing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/30—Peripheral units, e.g. input or output ports
- H04L49/3027—Output queuing
Abstract
The application provides a struct sk_buffer (SKB) management method and apparatus. The method comprises: under the circumstance that a hardware interface receives a data packet, a CPU determines whether the hardware interface has an SKB for data packet storage; if not, one SKB is distributed to the hardware interface in a hard buffer queue, wherein the hard buffer queue is formed by a preset number of SKBs; after the CPU completes processing of the data packet, whether a to-be-recycled SKB has a preset field is determined; and if so, the SKB is recycled to the hard buffer queue. Using the method and apparatus provided by the invention, the influence on the forwarding performance of the network device by frequent internal memory operations can be avoided because of cyclic utilization of SKBs in the hard buffer queue, so that the forwarding performance of the network device can be improved.
Description
Technical field
The application is related to Internet technical field, more particularly to a kind of socket caching SKB management methods and device.
Background technology
SKB (Struct sk_buff, socket caching) is data structure important in a kind of mixed-media network modules mixed-media code, CPU
Packet to be forwarded can be encapsulated according to its address pointed to.
In prior art, the CPU of the network equipment can be used for the SKB of data storage bag to kernel application, so as to supply network
The hardware interface of equipment is used;After the hardware interface receives packet, CPU can be according to distributing to the hardware interface
SKB pointers point to memory address process the packet;Afterwards, the packet is sent to the hardware interface of the network equipment
Afterwards, recovery information and sending can be generated to CPU;The CPU is recovered to the SKB interior after the recovery message is received
In core.
However, either CPU is to kernel application SKB, or SKB is recovered in kernel, CPU is required for internally depositing into row
Operation, and frequently operate internal memory to consume equipment performance, so as to affect the forwarding performance of the network equipment.
The content of the invention
The socket caching SKB management methods and device that the application is provided, to solve prior art in frequent operation internal memory
Affect the problem of the forwarding performance of the network equipment.
According to a kind of socket caching SKB management methods that the embodiment of the present application is provided, methods described includes:
In the case where hardware interface receives packet, CPU judges whether the hardware interface has for data storage
The SKB of bag;
In the case where the hardware interface does not have the SKB for data storage bag, one is distributed from hard buff queues
SKB gives the hardware interface;Wherein, the hard buff queues are made up of the SKB of predetermined number;
After CPU has processed packet, judge whether SKB to be recycled has preset field;
In the case where the SKB to be recycled has preset field, the SKB is recovered to into the hard buff queues.
Optionally, the hard buff queues are obtained by the following manner:
After the network equipment is started, SKBs of the CPU to kernel application predetermined number;
The SKB of the predetermined number applied is constituted into a hard buff queue, so as to provide hardware interface for the CPU
Use.
Optionally, the predetermined number caches SKB quantity according to hardware interface and software caching SKB quantity determines.
Optionally, methods described also includes:
In the case where the SKB to be recycled does not have preset field, the SKB is recovered in kernel.
Optionally, it is described that the SKB is recovered to into the hard buff queues, specifically include:
The SKB is recovered to into the afterbody of the hard buff queues, and initializes the SKB.
According to a kind of socket caching SKB managing devices that the embodiment of the present application is provided, described device includes:
First judging unit, in the case where hardware interface receives packet, CPU judges whether the hardware interface has
For the SKB of data storage bag;
SKB allocation units, in the case where the hardware interface does not have the SKB for data storage bag, from hard buff teams
Distribute a SKB in row to the hardware interface;Wherein, the hard buff queues are made up of several SKB;
Second judging unit, after CPU has processed packet, judges whether SKB to be recycled has preset field;
SKB recovery units, in the case where the SKB to be recycled has preset field, the SKB are recovered to described hard
Buff queues.
Optionally, the hard buff queues apply for that subelement and queue generate subelement and obtain by SKB:
SKB applies for subelement, after the network equipment is started, SKBs of the CPU to kernel application predetermined number;
Queue generates subelement, the SKB of the predetermined number applied is constituted into a hard buff queue, so as to for described
CPU provides hardware interface and uses.
Optionally, the predetermined number caches SKB quantity according to hardware interface and software caching SKB quantity determines.
Optionally, described device also includes:
Second recovery unit, in the case where the SKB of the hardware interface does not have preset field, the SKB is recovered to
In kernel.
Optionally, it is described that the SKB is recovered to into the hard buff queues, specifically include:
The SKB is recovered to into the afterbody of the hard buff queues, and initializes the SKB.
In the embodiment of the present application, CPU constitutes a hard buff team by the advance SKB to kernel application predetermined number
Row are used for hardware interface.When hardware interface receives packet, CPU without to kernel application SKB, but from hard buff teams
Distribute SKB in row;And when SKB is reclaimed, it is not necessary to reclaim to kernel, but be re-added in the hard buff queues.Such as
This, can use the SKB in this hard buff queue, it is to avoid frequent operation internal memory affects the forwarding performance of the network equipment with cycle,
Realize the forwarding performance for improving the network equipment.
Description of the drawings
Fig. 1 is the schematic diagram for distributing SKB in prior art;
Fig. 2 is the schematic diagram of processing data bag in prior art;
Fig. 3 is the flow chart that the socket that the embodiment of the application one is provided caches SKB management methods;
Fig. 4 is that the hard buff that the embodiment of the application one is provided goes out team and the schematic diagram joined the team;
Fig. 5 is a kind of hardware structure diagram of the application socket caching SKB managing devices place equipment;
Fig. 6 is the module map that the socket that the embodiment of the application one is provided caches SKB managing devices.
Specific embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Explained below is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.Conversely, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects described in detail in claims, the application.
It is, only merely for the purpose of description specific embodiment, and to be not intended to be limiting the application in term used in this application.
" one kind ", " described " and " being somebody's turn to do " of singulative used in the application and appended claims is also intended to include majority
Form, unless context clearly shows that other implications.It is also understood that term "and/or" used herein is referred to and wrapped
Containing one or more associated any or all possible combinations for listing project.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the application
A little information should not necessarily be limited by these terms.These terms are only used for that same type of information is distinguished from each other out.For example, without departing from
In the case of the application scope, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as
One information.Depending on linguistic context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determining ".
As it was previously stated, the CPU of the network equipment can be used for the SKB of data storage bag to kernel application, so as to set for network
Standby hardware interface is used.Specifically, in the schematic diagram of distribution SKB as shown in Figure 1, CPU can be by alloc_skb from interior
Apply for several SKB for hardware interface eth in core, and distribute to the hardware interface eth.General, a hardware interface point
With a SKB, such as when having N number of hardware interface, need to apply for N number of SKB.The SKB can be used for storage hardware interface
The packet for arriving.
Then, after the hardware interface receives packet, CPU can be according to the SKB for distributing to the hardware interface
The memory address that pointer is pointed to processes the packet.Specifically, in the schematic diagram of processing data bag as shown in Figure 2, hardware connects
Mouth eth0 is being received after the packet of Ethernet, can pass through DMA (Direct Memory Access, direct internal memory
Access) mode the packet is stored in the memory address pointed to the SKB pointers of hardware interface eth0, and notify CPU
Process the packet;Further, CPU process is stored in the packet in the memory address that the SKB pointers are pointed to.Other hardware interfaces
Such as eth1 processing procedures are identical, and here is omitted.
Then, the packet is sent to after the hardware interface of the network equipment, can generate recovery information and sending to
CPU.Specifically, CPU has been processed after packet, the packet for having processed can be sent to into hardware interface and be forwarded, and raw
Information is reclaimed into one notify CPU.
Finally, the CPU is recovered to the SKB in kernel after the recovery message is received.Specifically, CPU exists
After receiving recovery message, illustrate that the SKB can be recycled, so the memory address that the SKB and SKB pointers are pointed to is returned
In receiving kernel.
In sum, a packet is often processed in hardware interface, is required for CPU to carry out applying for SKB and recovery SKB,
But regardless of be CPU to kernel application SKB, or SKB is recovered in kernel, CPU is required for internally depositing into capable operation.For net
For network equipment, frequently internal memory operation can greatly consume equipment performance, so as to affect the forwarding performance of the network equipment.
In order to solve the problems, such as that above-mentioned frequent operation internal memory affects the forwarding performance of the network equipment, Fig. 3 is referred to, be this Shen
Please the socket that provides of an embodiment cache the flow chart of SKB management methods, the embodiment is described from network equipment side, wraps
Include following steps:
Step 110:In the case where hardware interface receives packet, CPU judges whether the hardware interface has to be used for
The SKB of data storage bag.
In the present embodiment, in the case where hardware interface receives packet, CPU needs first to judge the hardware network equipment
Whether interface has the SKB for data storage.
If the hardware interface has the SKB for data storage bag, what CPU directly can be pointed to by the SKB
The received packet of memory address process.
If the hardware interface does not have the SKB for data storage bag, need to perform subsequent step 120.
Step 120:In the case where the hardware interface does not have the SKB for data storage bag, from hard buff queues
Distribution one SKB give the hardware interface.
In the present embodiment, the hard buff queues can be made up of the SKB of predetermined number.
Specifically, the hard buff queues can be obtained by the following manner:
After the network equipment is started, SKBs of the CPU to kernel application predetermined number;
The SKB of the predetermined number applied is constituted into a hard buff queue, so as to provide hardware interface for the CPU
Use.
That is, after equipment starts, CPU automatically to the SKB of kernel application predetermined number, and then will can be applied
The SKB of the predetermined number for arriving constitutes a hard buff queue.The hard buff queues could be for being supplied to hardware interface to make
.
Institute's predetermined number can be the artificial empirical value for arranging.
Be worth mentioning when, the quantity of SKB in hard buff queues, i.e., described predetermined number can be according to hardware interface
Caching SKB quantity and software caching SKB quantity determine.
General in the present embodiment, for hardware, the network equipment has how many hardware interfaces, it is necessary to take
The SKB of equal number;For software, the software of processing data bag can process how many packets, need also exist for taking
The SKB of equal number.In order to hard buff queues can ensure that the demand that the network equipment is forwarded, when CPU is to kernel application SKB, need
Simultaneously SKB quantity is cached according to hardware interface and software caching SKB quantity determines.For example, the network equipment has 10 hardware
Interface, while software can simultaneously process 10 packets, then CPU is needed to 20 SKB of kernel application, that is, hard buff teams
The quantity of SKB is 20 in row, this way it is secured that the demand of network equipment forwarding, it is to avoid the not enough situations of SKB occur.
Step 130:After CPU has processed packet, judge whether SKB to be recycled has preset field.
In the present embodiment, in the hard buff shown in Fig. 4 goes out team and the schematic diagram joined the team, CPU is from hard buff queues
SKB distributes to hardware interface eth.General, a hardware interface distributes a SKB.This process is exactly that hard buff goes out team
Process.
Hardware interface eth is being received after the packet of Ethernet, can pass through DMA (Direct Memory
Access, direct memory access) mode by packet storage to the SKB pointers sensing for distributing to hardware interface eth
In memory address, and notify that CPU processes the packet.
After CPU has processed the packet being stored in the memory address that the SKB pointers are pointed to, it is necessary to which the SKB is entered
Row recycling;
In particular it is required that judging whether SKB to be recycled has preset field.
In the present embodiment, each SKB can arrange one for indicating whether to belong to the predetermined word of hard buff queues
Section.
For example, if certain SKB has preset field, illustrate that the SKB is to go out team from hard buff queues, so right
The SKB needs execution step 140.
The application another specifically in embodiment, methods described can also include:
In the case where the SKB of the hardware interface does not have preset field, the SKB is recovered in kernel.
For example, if certain SKB does not have preset field, illustrate that the SKB can't not be team from hard buff queues, and
Be according in prior art to the SKB of kernel application, so for this SKB in the hardware interface have preset field
In the case of, the SKB can be recovered in kernel.
Step 140:In the case where the SKB of the hardware interface has preset field, the SKB is recovered to described hard
Buff queues.
In the present embodiment, the SKB is recovered to into the hard buff queues, can be any position for putting into hard buff queues
Put.
But, the SKB is recovered to into the afterbody of the hard buff queues, and initialize the SKB.
So, it is ensured that the SKB of stem must can be normally to use in the hard buff queues, thus, needing
When wanting the hard buff queues to go out group, directly SKB can be extracted from stem, so as to improve SKB dequeuing efficiencies.
By the way that in the embodiment of the present application, CPU constitutes one firmly by the advance SKB to kernel application predetermined number
Buff queues are used for hardware interface.When hardware interface receives packet, CPU without to kernel application SKB, but from hard
Distribute SKB in buff queues;And when SKB is reclaimed, it is not necessary to reclaim to kernel, but be re-added to the hard buff queues
In.Thus, the SKB in this hard buff queue can be used with cycle, it is to avoid frequent operation internal memory affects the forwarding of the network equipment
Performance, realizes the forwarding performance for improving the network equipment.
It is noted that for the network equipment of multinuclear, multinuclear can be carried out concurrently, need simultaneously in multiple CPU
When operating hard buff queues, conflict just would tend to occur.
In order to solve this problem, in the further embodiment of the application, for multinuclear it is concurrent when, each can be allowed
CPU applies for SKB, so that each CPU has the hard buff queues of oneself.
Specifically, locking protection is added to hard buff queues, each hard buff queue only have corresponding CPU just can unlock from
And operate hard buff queues.Thus, when multinuclear can be avoided concurrent, the problem of CPU conflicts.
It is corresponding with aforementioned socket caching SKB management method embodiments, present invention also provides socket caching SKB pipes
The embodiment of reason device.
The embodiment of the application socket caching SKB managing devices can be applied respectively on safety protection equipment.Device
Embodiment can be realized by software, it is also possible to be realized by way of hardware or software and hardware combining.As a example by implemented in software,
It is by corresponding calculating in nonvolatile memory by the processor of its place equipment as the device on a logical meaning
Machine programmed instruction reads what operation in internal memory was formed.From for hardware view, as shown in figure 5, caching for the application socket
A kind of hardware structure diagram of SKB managing devices place equipment, except the processor shown in Fig. 5, network interface, internal memory and it is non-easily
Outside the property lost memorizer, the equipment that device is located in embodiment is gone back generally according to the actual functional capability of the socket caching SKB management
Other hardware can be included.
Fig. 6 is referred to, for the module map that the socket that the embodiment of the application one is provided caches SKB managing devices, the dress
Putting to include:First module 210, SKB allocation units 220, the second judging unit 230 and SKB recovery units 240.
Wherein, the first judging unit 210, in the case where hardware interface receives packet, CPU judges the hardware interface
Whether there is the SKB for data storage bag;
SKB allocation units 220, in the case where the hardware interface does not have the SKB for data storage bag, from hard buff
Distribute a SKB in queue to the hardware interface;Wherein, the hard buff queues are made up of the SKB of predetermined number;
Second judging unit, after CPU has processed packet, judges whether SKB to be recycled has preset field;
SKB recovery units, in the case where the SKB to be recycled has preset field, the SKB are recovered to described hard
Buff queues.
In an optional implementation:
The hard buff queues apply for that subelement and queue generate subelement and obtain by SKB:
SKB applies for subelement, after the network equipment is started, SKBs of the CPU to kernel application predetermined number;
Queue generates subelement, the SKB of the predetermined number applied is constituted into a hard buff queue, so as to for described
CPU provides hardware interface and uses.
In an optional implementation:
The predetermined number caches SKB quantity and determines according to hardware interface;
And/or,
The predetermined number caches SKB quantity and determines according to software.
In an optional implementation:
Described device also includes:
Second recovery unit, in the case where the SKB to be recycled does not have preset field, the SKB is recovered to interior
In core.
In an optional implementation:
It is described that the SKB is recovered to into the hard buff queues, specifically include:
The SKB is recovered to into the afterbody of the hard buff queues, and initializes the SKB.
By the way that in the embodiment of the present application, CPU constitutes one firmly by the advance SKB to kernel application predetermined number
Buff queues are used for hardware interface.When hardware interface receives packet, CPU without to kernel application SKB, but from hard
Distribute SKB in buff queues;And when SKB is reclaimed, it is not necessary to reclaim to kernel, but be re-added to the hard buff queues
In.Thus, the SKB in this hard buff queue can be used with cycle, it is to avoid frequent operation internal memory affects the forwarding of the network equipment
Performance, realizes the forwarding performance for improving the network equipment.
In sum, hard buff mechanism not only meets and reduce in the network equipment repeating process expense to internal memory operation,
Such that it is able to improve the forwarding performance of the network equipment;Due also to having no effect on CPU processes the original flow processs of SKB, it is possible to protect
The card network equipment normally runs.
The function of unit and effect realizes that process specifically refers in said method correspondence step in said apparatus
Process is realized, be will not be described here.
For device embodiment, because it corresponds essentially to embodiment of the method, so related part is referring to method reality
Apply the part explanation of example.Device embodiment described above is only schematic, wherein described as separating component
The unit of explanation can be or may not be physically separate, can be as the part that unit shows or can also
It is not physical location, you can be located at a place, or can also be distributed on multiple NEs.Can be according to reality
Need the purpose for selecting some or all of module therein to realize application scheme.Those of ordinary skill in the art are not paying
In the case of going out creative work, you can to understand and implement.
Those skilled in the art will readily occur to its of the application after considering description and putting into practice invention disclosed herein
Its embodiment.The application is intended to any modification, purposes or the adaptations of the application, these modifications, purposes or
Person's adaptations follow the general principle of the application and including the undocumented common knowledge in the art of the application
Or conventional techniques.Description and embodiments are considered only as exemplary, and the true scope of the application and spirit are by following
Claim is pointed out.
It should be appreciated that the application is not limited to the precision architecture for being described above and being shown in the drawings, and
And can without departing from the scope carry out various modifications and changes.Scope of the present application is only limited by appended claim.
Claims (10)
1. a kind of socket caches SKB management methods, it is characterised in that methods described includes:
In the case where hardware interface receives packet, CPU judges whether the hardware interface has for data storage bag
SKB;
In the case where the hardware interface does not have the SKB for data storage bag, distribute a SKB from hard buff queues and give
The hardware interface;Wherein, the hard buff queues are made up of the SKB of predetermined number;
After CPU has processed packet, judge whether SKB to be recycled has preset field;
In the case where the SKB to be recycled has preset field, the SKB is recovered to into the hard buff queues.
2. method according to claim 1, it is characterised in that the hard buff queues are obtained by the following manner:
After the network equipment is started, SKBs of the CPU to kernel application predetermined number;
The SKB of the predetermined number applied is constituted into a hard buff queue, is made so as to provide hardware interface for the CPU
With.
3. method according to claim 2, it is characterised in that the predetermined number caches SKB quantity according to hardware interface
Determine with software caching SKB quantity.
4. method according to claim 1, it is characterised in that methods described also includes:
In the case where the SKB to be recycled does not have preset field, the SKB is recovered in kernel.
5. method according to claim 1, it is characterised in that described that the SKB is recovered to into the hard buff queues, specifically
Including:
The SKB is recovered to into the afterbody of the hard buff queues, and initializes the SKB.
6. a kind of socket caches SKB managing devices, it is characterised in that described device includes:
First judging unit, in the case where hardware interface receives packet, CPU judges whether the hardware interface has to be used for
The SKB of data storage bag;
SKB allocation units, in the case where the hardware interface does not have the SKB for data storage bag, from hard buff queues
Distribution one SKB give the hardware interface;Wherein, the hard buff queues are made up of several SKB;
Second judging unit, after CPU has processed packet, judges whether SKB to be recycled has preset field;
SKB recovery units, in the case where the SKB to be recycled has preset field, by the SKB the hard buff are recovered to
Queue.
7. device according to claim 6, it is characterised in that the hard buff queues apply for subelement and team by SKB
Column-generation subelement is obtained:
SKB applies for subelement, after the network equipment is started, SKBs of the CPU to kernel application predetermined number;
Queue generates subelement, the SKB of the predetermined number applied is constituted into a hard buff queue, so as to for the CPU
There is provided hardware interface to use.
8. device according to claim 7, it is characterised in that the predetermined number caches SKB quantity according to hardware interface
Determine with software caching SKB quantity.
9. device according to claim 6, it is characterised in that described device also includes:
Second recovery unit, in the case where the SKB of the hardware interface does not have preset field, by the SKB kernel is recovered to
In.
10. method according to claim 6, it is characterised in that described that the SKB is recovered to into the hard buff queues, tool
Body includes:
The SKB is recovered to into the afterbody of the hard buff queues, and initializes the SKB.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610986064.2A CN106572036A (en) | 2016-11-09 | 2016-11-09 | SKB management method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610986064.2A CN106572036A (en) | 2016-11-09 | 2016-11-09 | SKB management method and apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106572036A true CN106572036A (en) | 2017-04-19 |
Family
ID=58540769
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610986064.2A Pending CN106572036A (en) | 2016-11-09 | 2016-11-09 | SKB management method and apparatus |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106572036A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108595270A (en) * | 2018-04-27 | 2018-09-28 | 新华三信息安全技术有限公司 | A kind of recovery method and device of memory source |
CN112702426A (en) * | 2020-12-23 | 2021-04-23 | 北京天融信网络安全技术有限公司 | Data packet forwarding method and device, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101789959A (en) * | 2009-12-30 | 2010-07-28 | 北京天融信科技有限公司 | SKB reusing method and device in multinuclear system |
CN102508783A (en) * | 2011-10-18 | 2012-06-20 | 深圳市共进电子股份有限公司 | Memory recovery method for avoiding data chaos |
US20130110968A1 (en) * | 2011-11-02 | 2013-05-02 | Neil R.T. Horman | Reducing latency in multicast traffic reception |
CN105939293A (en) * | 2016-01-22 | 2016-09-14 | 杭州迪普科技有限公司 | SKB (Struct sk_buff) recycling method and device |
-
2016
- 2016-11-09 CN CN201610986064.2A patent/CN106572036A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101789959A (en) * | 2009-12-30 | 2010-07-28 | 北京天融信科技有限公司 | SKB reusing method and device in multinuclear system |
CN102508783A (en) * | 2011-10-18 | 2012-06-20 | 深圳市共进电子股份有限公司 | Memory recovery method for avoiding data chaos |
US20130110968A1 (en) * | 2011-11-02 | 2013-05-02 | Neil R.T. Horman | Reducing latency in multicast traffic reception |
CN105939293A (en) * | 2016-01-22 | 2016-09-14 | 杭州迪普科技有限公司 | SKB (Struct sk_buff) recycling method and device |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108595270A (en) * | 2018-04-27 | 2018-09-28 | 新华三信息安全技术有限公司 | A kind of recovery method and device of memory source |
CN112702426A (en) * | 2020-12-23 | 2021-04-23 | 北京天融信网络安全技术有限公司 | Data packet forwarding method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7853951B2 (en) | Lock sequencing to reorder and grant lock requests from multiple program threads | |
US20200192715A1 (en) | Workload scheduler for memory allocation | |
US8321385B2 (en) | Hash processing in a network communications processor architecture | |
US7366865B2 (en) | Enqueueing entries in a packet queue referencing packets | |
US8990801B2 (en) | Server switch integration in a virtualized system | |
US20200159654A1 (en) | Pipelined hash table with reduced collisions | |
EP0947926A2 (en) | System and method for multi-tasking, resource sharing, and execution of computer instructions | |
US20070124728A1 (en) | Passing work between threads | |
US10671530B1 (en) | High-speed and memory-efficient flow cache for network flow processors | |
US20040199916A1 (en) | Systems and methods for multi-tasking, resource sharing, and execution of computer instructions | |
US9059945B2 (en) | Work request processor | |
CN103946803A (en) | Processor with efficient work queuing | |
US7467256B2 (en) | Processor having content addressable memory for block-based queue structures | |
US20070044103A1 (en) | Inter-thread communication of lock protected data | |
US7418543B2 (en) | Processor having content addressable memory with command ordering | |
US20130061009A1 (en) | High Performance Free Buffer Allocation and Deallocation | |
US7277990B2 (en) | Method and apparatus providing efficient queue descriptor memory access | |
CN106572036A (en) | SKB management method and apparatus | |
US7477641B2 (en) | Providing access to data shared by packet processing threads | |
US8156289B2 (en) | Hardware support for work queue management | |
CN109117189A (en) | Data processing method, device and computer equipment | |
US9288163B2 (en) | Low-latency packet receive method for networking devices | |
US20060161647A1 (en) | Method and apparatus providing measurement of packet latency in a processor | |
US9811403B1 (en) | Method, apparatus and system for performing matching operations in a computing system | |
WO2010117359A1 (en) | Transmit-side scaler and method for processing outgoing information packets using thread-based queues |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170419 |
|
RJ01 | Rejection of invention patent application after publication |