WO2012105677A1 - Packet processing device, packet processing method and program - Google Patents

Packet processing device, packet processing method and program Download PDF

Info

Publication number
WO2012105677A1
WO2012105677A1 PCT/JP2012/052465 JP2012052465W WO2012105677A1 WO 2012105677 A1 WO2012105677 A1 WO 2012105677A1 JP 2012052465 W JP2012052465 W JP 2012052465W WO 2012105677 A1 WO2012105677 A1 WO 2012105677A1
Authority
WO
WIPO (PCT)
Prior art keywords
packet
processing
rule
process
target
Prior art date
Application number
PCT/JP2012/052465
Other languages
French (fr)
Japanese (ja)
Inventor
池田 聡
地引 昌弘
智義 菅原
Original Assignee
日本電気株式会社
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Priority to JP2011-022303 priority Critical
Priority to JP2011022303 priority
Application filed by 日本電気株式会社 filed Critical 日本電気株式会社
Publication of WO2012105677A1 publication Critical patent/WO2012105677A1/en

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00Data switching networks
    • H04L12/64Hybrid switching systems
    • H04L12/6418Hybrid transport
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W12/00Security arrangements, e.g. access security or fraud detection; Authentication, e.g. verifying user identity or authorisation; Protecting privacy or anonymity ; Protecting confidentiality; Key management; Integrity; Mobile application security; Using identity modules; Secure pairing of devices; Context aware security; Lawful interception
    • H04W12/08Access security

Abstract

The packet processing device is equipped with a rule table that holds rules for correlating information contained in each packet, a processing rule indicating first processing to be applied to the packet, and a processor identifier for identifying a processor that applies second processing to the packet; a rule extraction unit that extracts, from the rule table, a rule that corresponds to information contained in a subject packet, which is a packet to be processed; and a rule application unit that executes the first processing with respect to the subject packet according to the processing rule and sends a request to the processor corresponding to the processor identifier to execute the second processing on the basis of the extracted rule. In a packet transfer device equipped with multiple processors, a processor that executes the packet processing can be selected from among the multiple processors flexibly and quickly.

Description

Packet processing device, a packet processing method and program

(Description of the related application)
The present invention, Japanese Patent Application: is based on the priority claim of Japanese Patent Application No. 2011-022303 (February 4, 2011 application), the entire description of the application is incorporated herein in its citation and things.

The present invention is a packet processing apparatus, a packet processing method, and a program, in particular, the packet processing unit for transmitting and receiving packets using a plurality of processors to a packet processing method, and a program.

With the increase of Internet traffic, speed and performance of the packet processing device is proceeding to support it. Recently, the spread of high-speed network interface cards is proceeding, by using the network interface card be a general-purpose server, faster packet processing is possible. Meanwhile, since the speed with high clock of the processor have been looked limitations by increased power consumption, and they have become performance improvement by multicore multiprocessoring also become common use of symmetric multiprocessors in the packet processing device ing.

Linux If using a general-purpose OS (registered trademark) to realize a packet processing device and is equipped with a high-speed network card, the processor processes the transmitted and received becomes a bottleneck, communication wire rate It becomes difficult. Even if A multi-core processors, by processing of the packet into a single processor (core) became interrupt destination from the network interface card is concentrated, bottlenecks occur, be carefully load distribution there is a problem that can not be.

To solve this problem, Patent Document 1, based on the header information of the packet to be processed, a plurality of processors, is uniquely determined a processor to process the packet. Specifically, a hash value is calculated from a portion of the field of the header of the packet, the obtained hash value performs a modulo operation according to the number of processors (cores), seeking processor number. Then, the processor of the processor number obtained to perform the processing of the packet. Here, because a modulo operation according to the number of processors (cores), by the operation, the processor number is uniquely determined. That is, the remainder obtained from the hash value (i.e., processor number) Different, also becomes different processors for processing, it is possible to distribute the processing of packets among multiple processors (cores). Accordingly, without processing by a single processor (core) it becomes a bottleneck, it is possible to achieve load balancing.

Below, a processor and a processor core, collectively referred to as "processor".

JP-T 2002-538724 JP

Nick McKeown and 7 other people, " OpenFlow: Enabling Innovation In Campus Networks, " [Online], [December 17, 2010 search], Internet <URL: http: // www. openflowswitch. org // documents / openflow-wp- latest.pdf>. " . OpenFlow Switch Specification Version 1.0.0 (Wire Protocol 0X01), " [December 17, 2010 search], Internet <URL: http: // www. openflowswitch. org / documents / openflow-spec- v1.0.0.pdf>.

The disclosures of the aforementioned Patent Documents and Non-Patent Documents are incorporated by reference herein. The following analysis has been made by the present inventors.

In the packet processing device described in Patent Document 1, as described above, based on a portion of the field of the header of the packet, and uniquely determine the processor for processing packets. Therefore, if the hash value calculated from a part of the field of the header is the same, processor number obtained from the modulo operation is always the same, processor that processes the packet is fixed. Therefore, there is a problem that it is impossible to select the processor that executes the processing of the packet flexibly.

Therefore, in the packet forwarding device comprising a plurality of processors, it is a challenge to be able to select the processor that executes the processing of the packet from among a plurality of processors in a flexible and fast. An object of the present invention, packet processing device to solve the above problems and to provide a packet processing method, and a program.

Packet processing apparatus according to a first aspect of the present invention,
Information stored in the packet, processing rule indicating the first processing for the packet, and a rules table for holding a rule to associate with each other processor identifier identifying a processor which performs second processing for the packet,
The rule corresponding to stored in the target packet is a packet to be processed information, and rule extracting unit that extracts from the rule table,
Based on the extracted rules, and execution of the first process in accordance with the processing rules for the target packet, and rules application unit for performing a request of the second processing for the processor corresponding to the processor identifier, It is equipped with a.

Packet processing method according to a second aspect of the present invention,
One processor of the plurality of processors, associated information stored in the packet, processing rule indicating the first processing for the packet, and the processor identifier identifying a processor which performs second processing for the packet to each other from a rule table for holding a rule, a step of extracting a rule corresponding to the information stored in the target packet is a packet to be processed,
The one processor on the basis of the extracted rules, performs the execution of the first process in accordance with the processing rules for the target packet, and a request for the second processing to the processor corresponding to the processor identifier and a step, a.

A program according to a third aspect of the present invention,
Information stored in the packet, processing rule indicating the first processing for the packet, and, from the rule table holding rule that associates each other processor identifier identifying a processor which performs second processing for the packet, to be processed a process of extracting a rule corresponding to the information stored in the target packet is a packet,
Based on the extracted rule plurality and execution of the first process in accordance with the processing rule, and a process for the request of the second processing for the processor corresponding to the processor identifier for the target packet It is executed by the one of the processors.

The program may be provided as a program product recorded in a non-transient computer-readable recording medium (non-transient computer-readable storage medium).

Packet processing apparatus according to the present invention, identified according to the packet processing method, and a program, information stored in the packet, processing rule indicating the first processing for the packet, and, a processor for performing a second process on the packet to provide the rule table that associates processor identifier with each other, by setting the processor identifier of the rule table can be flexibly selecting a processor for executing processing of the packet from among a plurality of processors.

Further, according to the packet processing apparatus and packet processing method according to the present invention, extracted from the rule table, based on the rule corresponding to the to be processed packet, the execution of the first processing for the packet, processing the packet to perform the selection of the processor as one process, it can be performed to process the packet at high speed.

The configuration of a packet processing apparatus according to the present invention is a block diagram schematically showing. Is a block diagram showing the configuration of a packet processing apparatus according to the first embodiment. It is a diagram illustrating a rule table in the packet processing apparatus according to the first embodiment. Is a flowchart showing the operation of the packet processing apparatus according to the first embodiment. Is a block diagram showing the configuration of a packet processing apparatus according to the second embodiment. It is a diagram illustrating a rule table in the packet processing apparatus according to the second embodiment. Is a flowchart illustrating a transmission process by the packet processing apparatus according to the second embodiment. Is a flowchart illustrating a receiving process by the packet processing apparatus according to the second embodiment. Is a flowchart illustrating a receiving process by the packet processing apparatus according to the second embodiment. Is a block diagram showing the configuration of a packet processing apparatus according to the third embodiment. It is a diagram illustrating a rule table in the packet processing apparatus according to the third embodiment. Is a block diagram showing the configuration of a packet processing device according to the fourth embodiment. Is a diagram showing an entry of a flow table of open flow. Is a diagram showing the action of the open flow.

First, an outline of the present invention. The drawings reference numerals for appended to this summary is illustrative to assist solely understanding and is not intended to be limited to the illustrated embodiment of the present invention.

Referring to FIG. 1, the packet processing apparatus of the present invention, information stored in the packet, processing rule indicating the first processing for the packet, and the processor identifier identifying a processor for performing a second process on the packet the a rule table (110) for holding a rule to associate with each other, the matching rule to the information stored in the target packet is a packet to be processed, the rule extracting unit that extracts from the rule table (110) and (130), extracting based on the rule, with the execution of the first process in accordance with the processing rules for the target packet, rule application unit for requesting the second processing for the processor corresponding to the processor identifier and (140), the ing.

Packet processing device of the present invention includes a rule table (110) for holding a rule for associating the processor for processing matching condition and the packet for the packet. Therefore, for the rule of rule table (110), by setting the matching condition and the processor identifier directly, it is possible to select a processor to process packets flexibility, as in Patent Document 1, the same header processor for processing packets with information uniquely to it is eliminated fixed according to a predetermined operation rule. Further, according to the packet processing apparatus of the present invention, the user by rewriting the rules stored in the rule table (110), it is possible to easily change the rules processor selection for processing the packet.

Moreover, the rules in the rule table (110) in the packet processing apparatus of the present invention, information stored in the packet, processing rule indicating the first processing for the packet, and, a processor for performing a second process on the packet associate identifying processor identifier with each other. Accordingly, the rule extracting unit by (130), the rules corresponding to the target packet is extracted, not only the contents of the first process to be executed for the packet is identified, the second processing for the packet also it specified a processor to execute the. Therefore, according to the packet processing apparatus of the present invention, to identify the processing rule showing the processing for the packet by reference to the table, as compared with the case of separately specifying a processor that executes processing for a packet, it performs the processing of the packet at high speed be able to.

As described above, according to the packet processing apparatus of the present invention can be selected in the packet forwarding device comprising a plurality of processors, a processor for executing processing of a packet from a plurality of processors in a flexible and fast.

In the present invention, it is possible to form the following.

[Embodiment 1]
It is as packet processing apparatus according to the first aspect.

[Embodiment 2]
The first process is a process of determining whether to discard the target packet,
In the second process, when the target packet is a packet to be received by the packet processing device is a processing of the upper layer with respect to the target packet, the packet wherein the target packet is to be transmitted in the packet processing device there may be processing of the lower layer with respect to the target packet in the case.

[Embodiment 3]
The rule application unit, when the target packet in the first process is not a packet to be discarded, the second processing for the target packet may be requested to said processor.

[Embodiment 4]
The rule table information stored in the packet, processing rule indicating the first processing for the packet, the processor identifier identifying a processor which performs second processing for the packet, and defines a flow including the packet It holds rules that relate to each other the flow definition field indicating a field,
The rule application unit, if included multiple processor identifier to the extracted rule, the reference to the flow defined fields, to any processor of the plurality of processors corresponding to processor identifier of the plurality of Te may be requesting the second processing for all of the target packet included in the same flow.

[Embodiment 5]
The rule extracting unit, when the rule table does not hold rule corresponding to information stored in the target packet sets matching rule to the information the rule to the rule setting device capable of setting You may be asked to.

[Embodiment 6]
The first process is a process of determining the destination of the target packet,
In the second process, when the target packet is a packet to be received by the packet processing device is a processing of the upper layer with respect to the target packet, the packet wherein the target packet is to be transmitted in the packet processing device there may be processing of the lower layer with respect to the target packet in the case.

[Embodiment 7]
The rule application unit, in case the target packet is a packet to be received by the packet processing device, if the destination of the object packet is the packet processing unit, the second processing for the target packet it may be requested to said processor.

[Embodiment 8]
The rule extracting unit has a cache for temporarily storing the extracted rule, a matching rule is extracted from the cache information stored in the target packet,
The rule application unit, in case the target packet is a packet to be received by the packet processing device, when the matching rule to the target packet is extracted from the cache by the rule extracting unit is configured for the target packet the second process may be a request to said processor.

[Mode 9]
The first process is a process of identifying the control information in the transport layer for sending or receiving the target packet,
The second processing, when the target packet is a packet to be received by the packet processing device is a receiving process of the layer 4 with respect to the target packet employing the control information is identified, the target packet is If a packet to be transmitted in the packet processing device may be a transmission process of the layer 4 below for the target packet with control information specified.

[Embodiment 10]
The rule table holds a plurality of rules that are sorted according to priority,
The rule extracting unit, when a plurality of rules adapted to the information stored in the target packet is stored in the rule table, so as to extract having a high priority of the plurality of rules it may be.

[Mode 11]
Rules of the rule table, as the information stored in the packet, source address, destination address, source port number, and may comprise at least one of the destination port number.

[Mode 12]
To the rule table, additional rules, change, or may further comprise a rule setting unit to be deleted.

[Embodiment 13]
It is as packet processing method according to the second aspect.

[Embodiment 14]
Also, information stored in the packet, processing rule indicating the first processing for the packet, and, from the rule table holding rule that associates each other processor identifier identifying a processor which performs second processing for the packet, processing a process of extracting a rule corresponding to the information stored in the target packet is should do packet,
Based on the extracted rule plurality and execution of the first process in accordance with the processing rule, and a process for the request of the second processing for the processor corresponding to the processor identifier for the target packet program to be executed by one of the processors is provided.

(Embodiment 1)
The packet processing apparatus according to the first embodiment will be described with reference to the drawings. Figure 2 is a block diagram showing one example of the structure of a packet processing apparatus according to this embodiment. Referring to FIG. 2, the packet processing apparatus according to the present embodiment, the rules table 10, the rule setting unit 20, the rule extracting unit 30, rule application unit 40, the processing thread 50, transmitting receiving unit 60, and, receiving reception section 70 It is equipped with a.

The packet processing device of the present embodiment is equipped with the OS corresponding to a plurality of processors (or processor cores), connected to the network via the network interface device, processing and packet typified by IP packet and performs protocol processing in the upper layer software (including OS). That is, the components shown in FIG. 2, respectively, can be implemented by software. However, some or all of the components of FIG. 2 may be implemented by hardware.

Rule table 10 holds a dispatch rule that describes the allocation rules of filtering rules and a processor that describes the rules of filtering incoming and outgoing packets. Filtering rules and dispatching rules, managed by a single table.

Figure 3 is a diagram illustrating a rule table 10 as an example. Referring to FIG. 3, the rules table 10 is managed for each reception and transmission. One rule that corresponds to each row of the rule table 10 includes at least a matching condition, action, and, the processor identifier. Each rule in the rule table 10 may include a flow definition fields.

Matching condition represents conditions concerning the L3 field of the layer or the header of the packet. For example, the first line of the rule of FIG. 3 is a TCP protocol, indicating that the destination port number is the rule for a packet is 80.. As the collation condition, not only the protocol number and the port number shown in FIG. 3, IP address, AH header (Authentication Header), ESP (Encapsulating Security Payload) SPI in the header (Security Parameter Index) conditions related to various fields such as the value I can describe.

Action indicates the first processing for transmitting and receiving packets (first treatment, basic treatment). The action, e.g., ACCEPT to continue processing of the packet, it discards the packet DROP is used. Moreover, as an action, it in addition to two processes, may be described and the process of rewriting part of the data packet.

Processor identifier, represents a processor for matching (fit) with the processing of the packet to the matching condition. The processor identifier can describe the zero or more processor identifier.

Flow definition field represents the header field of the packet to be used to identify whether the same flow. The flow definition field, when a plurality of processor identifier to processor identifier is described as packets belonging to the same flow are processed in the same processor, the one processor from among the described processor identifier It is used to select.

Rule in the rule table 10 preferably manages aligned in order of priority.

Rule setting unit 20, additional rules, change the setting of rules for deletion performed on rules table 10. Rule setting unit 20, for example, operate as a user application, by performing message communications between users / kernel to set the rules.

Rule extraction unit 30 collates the collation condition information and rules table 10 stored in the reception packet, searches for a matching rule. Rule extraction unit 30, when a plurality of rules is matched, for example, it returned as a search result with the highest ones priority of the matching rule.

Rule application unit 40 includes a basic application unit 401 and the dispatcher 402. Rule application unit 40 receives the rules and transmitting and receiving packets, are applied filtering rules as the first treatment in the basic application unit 401, the dispatch rules are applied in the dispatch unit 402. On the other hand, when the processing is aborted by the application of filtering rules, without the application of the dispatching rules in the dispatch unit 402 ends the processing of the packet.

Basic application unit 401, a first process, performs a process relating to the action in the rule. If the rule action is DROP, the basic application section 401 discards the reception packet. On the other hand, if the action is ACCEPT, the dispatch unit 402 determines a processor for processing the outgoing and incoming packets in accordance with the processor identifier in the rule, the processing of the packet to the processing thread 50 corresponding to the processor to ask.

Processing thread 50 is a kernel thread that is prepared for each processor performs the second processing for the packet, the reception processing of Layer 3 and Layer 4 of the received packet, the transmission processing of Layer 3 and Layer 2 of the transmission packet. Processing thread 50 is provided with a reception processing section 501 and the transmission processing unit 502 holds the processing queue (not shown). The processing queue, the packet processing section (transmission / reception) is stored. Processing thread 50 sequentially takes out the data stored in the processing queue the packet, if the processing indicator transmission performs transmission processing by the transmission processing unit 502 to the packet. On the other hand, if the processing segment is received, the processing thread 50 performs a reception process by the reception processing unit 501 to the packet. The transmission processing unit 502 performs transmission processing of Layer 3 and Layer 2 for the transmission packet, and sends the packet to the network. On the other hand, the reception processing unit 501, with respect to the received packet, performs reception processing of Layer 3 and Layer 4 performs processing of passing the received packet to the user application if necessary.

Transmitting receiving unit 60 receives the transmission packet from the internal user application or kernel collates a transmission packet in the rule extracting unit 30 transfers the transmission packet and the resulting rules as the collation result to the rule application unit 40.

Receiving reception unit 70 receives a received packet from the network, checks the received packets in the rule extracting unit 30 transfers the received packet and the resulting rules as the collation result to the rule application unit 40.

Next, the operation of the packet processing apparatus according to the present embodiment will be described with reference to the drawings. Figure 4 is a flowchart showing the operation of the packet processing apparatus according to the present embodiment as an example.

Referring to FIG. 4, when a packet from the network arrives, the received packet is passed to the receiver receiving unit 70. Receiving reception section 70 having received the received packet, and searches for a rule that matches the received packet by the rule extracting unit 30 from the rule table 10 (step S1), the pass to the rule application unit 40 and the results with the received packet.

Next, the rule application unit 40 receives the rules and the received packet, the basic application unit 401 applies the action as the first process (step S2). If the action in the rule is DROP (No in step S3), and the basic application unit 401 discards the received packet (step S4), and completes processing of the received packet.

On the other hand, if the action is ACCEPT (Yes in step S3), and the dispatch unit 402 selects the processor in accordance with the rules processor identifier (Yes in step S5, S6). On the other hand, if the rule processor identifier is not designated (No in step S5), and the dispatcher 402, the processor running the current process (i.e., processor itself that is performing the processing of the dispatcher 402) to select as the processor (step S7).

Next, the dispatch unit 402, requests processing by queuing reception processing of the upper protocol of the received packet to the determined processor in the processing queue for processing thread 50 corresponds (step S8). Reception processing unit 501 of the processing threads 50 that received the request, the second processing for the packet, and executes packet reception processing (i.e., reception processing of the upper layer to the received packet).

In step S6, when using a flow-defined fields, based on the hash value of the specified field, to determine the processor from among the processors designated by the processor identifier. In particular, the flow definition field, it is preferable to select a field that can identify the same flow. This makes it possible to packets belonging to the same flow can be prevented from distributing to a plurality of processors, to reduce the overhead caused by the alignment of the exclusive control and packet.

In transmission processing of the packet, the rule matching is performed on the transmission packet during packet transmission, the same processing except that the processing thread that has received a request to perform transmission processing of the packet is performed. Therefore, the processing sequence when packet transmission is omitted.

In this embodiment, the filtering rule rule table 10 which describes the (set of the matching condition of FIG. 3 and action), the matching condition and processor identifier of dispatching rules (FIG. 3 to determine the processor for processing the transmission and reception packets and described in conjunction pairs) between the flow definition fields. According to the present embodiment, it is possible to set rules to rules table 10 from the user. Therefore, the rules for selecting a processor can be centrally managed, it is possible to perform a flexible processor selection based on the user's policy. Furthermore, in order to perform the selection of the processor performing the second processing for filtering a packet for the packet as one of the processing, it is possible to reduce the processing time for the packet.

(Embodiment 2)
The packet processing apparatus according to the second embodiment will be described with reference to the drawings. Figure 5 is a block diagram showing one example of the structure of a packet processing apparatus according to this embodiment. Referring to FIG. 5, the packet processing apparatus of this embodiment, rules table 11, the rule setting unit 21, the rule extracting unit 31, rule application unit 41, the processing thread 50, transmitting receiving unit 61, and the received receiver 71 It is provided.

Rule table 11, the path rule for determining the transfer destination from the destination address of the reception packet, and the dispatch rules to determine the processor from the destination address or the source address of the received packet of a transmission packet as a single table Hold.

Figure 6 is a diagram illustrating a rule table 11 as an example. Referring to FIG. 6, the rule table 11, a network address (address and netmask), the destination gateway, the output interface, and holds in association with processor identifier. Here, the network address, the destination gateway, and the correspondence between the output interface is used in application of the path rule. Further, correspondence between the network address and the processor identifier is used in the application of dispatching rules. Dispatching rules, rules for the destination address in the transmission packet, is interpreted as a rule for the source address in the received packet.

Rule setting unit 21, an additional path rules and dispatching rules, change the setting of rules for deletion performed on rules table 11. Rule setting unit 21, for example, operate as a user application, by performing message communication between the user and kernel to set the path rule.

Rule extraction unit 31 collates the network address of the address and rule table 11 stored in the packet, search for matching rules. Rule extraction unit 31 holds the part of the recently retrieved search results may include a high speed searchable route cache (not shown).

Rule application unit 41 includes a basic application unit 411 and the dispatcher 402. Rule application unit 41 receives the path rule and receive packets, the basic application unit 411 performs processing in accordance with the path rule as the first processing. Specifically, for the transmission packet, it sets so that the transmission packet is transmitted to the gateway from the output destination interface in the path rule. If the packet received from the route rule is determined as a packet addressed to another host, the basic application unit 411 performs transfer processing of the received packet. The operation of the dispatcher 402 is the same as the first embodiment, and detailed description thereof will be omitted.

Further, since the well operation of processing threads 50, it is similar to the first embodiment, and detailed description thereof will be omitted.

Transmitting receiving unit 61 receives the transmission packet from the internal user application or kernel searches the rule extracting unit 31 a rule corresponding to the destination address of the transmission packet, the search resulting rules and rule application unit transmission packet pass to the 41.

Receiving receiver 71 receives the reception packet from the network, the rule extracting unit 31, a route rule from the destination address of the received packet, the source address search each dispatching rule from the route rule and dispatch rules that the search, and it transfers the received packet to the rule application unit 41. If the rule extracting unit 31 is provided with a route cache, a search for dispatching rules may be performed by using a route cache.

Next, the operation of the packet processing apparatus according to the present embodiment will be described with reference to the drawings. Figure 7 is a flowchart illustrating a transmission process by the packet processing apparatus according to the present embodiment as an example.

Referring to FIG. 7, when a packet from an internal application or kernel arrives, the transmission packet to the transmission reception unit 61 is passed. Transmission reception unit 61 that has received the transmission packet, by the rule extracting unit 31 searches for a rule that matches the destination address of the transmission packet from the rule table 11 (step S11). If the rule extracting unit 31 is provided with a route cache, it is possible to speed up the subsequent search by holding the search result in the route cache. Transmitting receiving unit 61 transfers the search result of a rule in the rule applying section 41 together with the transmission packet.

Next, the rule application unit 41 receives the transmission packet and the retrieved rules, the basic application unit 411, on the basis of the rules, as the first process, to set the output interface to the transmission packet (step S12 ). If there is no corresponding path rule, the basic application unit 411 discards the transmission packet, completing the transmission process.

On the other hand, the dispatch unit 402 selects the processor in accordance with the rules processor identifier (Yes in step S13, S14). Further, when the dispatching rules processor identifier is not specified (No in step S13), the processor itself dispatcher 402, which currently process running processor (i.e., executes the processing of the dispatcher 402 ) is selected as the processor (step S15).

The dispatcher 402, the processing queue of the processing threads 50 corresponding to the determined processor, requests processing by queuing transmission processing of the upper protocol of the transmission packet (step S16). Transmission processing unit 502 of the processing threads 50 having received the request executes the transmission processing of the packet (transmission processing of the lower layer to the packet) as the second processing for the packet.

8, in a case where the rule extracting unit 31 does not have a route cache, the reception processing by the packet processing apparatus according to this embodiment is a flowchart illustrating as an example. When receiving a packet from the network arrives, it receives reception unit 71 by the rule extracting unit 31 searches for a rule that matches the destination address of the received packet from the rule table 11 (step S21).

If the search result is determined not to be the packet addressed to the packet processing unit itself (No in step S22), the basic application unit 411 of the rule application unit 41 terminates the process transfers the received packet (step S23 ). On the other hand, (Yes in step S22) When it is determined that the packet addressed to the packet processing device itself, receiving receiver 71 uses the rule extracting unit 31, a rule dispatching rule corresponding to the source address of the received packet Search the table 11 (step S24).

Dispatch unit 402 selects a processor in accordance with the rules processor identifier (Yes in Step S25, S26). On the other hand, selected when rule processor identifier is not designated (No in step S25), and the processor during the execution of the current process (i.e., processor itself that is performing the processing of the dispatcher 402) as processor (step S27).

The dispatcher 402, the processing queue of the processing threads 50 corresponding to the processor that is selected, requests processing by queuing reception processing of the upper protocol of the received packet (step S28). Reception processing unit 501 of the processing threads 50 having received the request executes the receiving process of the packet as a second processing for the packet.

9, in the case where the rule extracting unit 31 is provided with a route cache, the reception processing by the packet processing apparatus according to this embodiment is a flowchart illustrating as an example. 9, with respect to the steps S21 S23 and step S25 S28, since the rule extracting unit 31 is similar to the case without a route cache (FIG. 8), and detailed description thereof will be omitted. 9, instead of step S24 in FIG. 8, in that it includes a step S29 and step S30, differs from the FIG.

If the rule extracting unit 31 is provided with a route cache, receiving receiver 71 uses the route cache, to search for dispatching rule (step S29).

If the rule that matches the route cache is not held it is assumed that not specified (No in step S30), the processor identifier, processing is carried out. Thus, if the rule is held in route cache possible search speed (Yes in step S30), by utilizing the dispatch rules (steps S25 ~ S27), reducing the time required for the search can.

Route cache is updated with the route search in the transmission process (step S11 in FIG. 7). Therefore, if the packet received from addresses that are performed periodically transmitted, for the rule to match route cache is maintained (Yes in step S30 in FIG. 9), selection of a processor-based dispatching rule (Fig. 9 step S25 ~ S27) is possible.

In the present embodiment, as shown in FIG. 6, sets a dispatch rule that determines the processor to rule table 11. Filtering process in the first embodiment, but is not always required in the packet processing. On the other hand, the search processing of the route is essential to the processing of the packet. Thus, the packet processing apparatus according to the present embodiment, can be applied to packet transfer case without filtering process, by setting a rule to the rule table 11 from the user, performs a flexible processor selection it is possible. Further, in the transmission process by the packet processing apparatus according to this embodiment includes a process of setting the output interface to the transmission packet, and a process of selecting a processor for performing a second process on the transmission packet, as one of the processing to run, it is possible to reduce the processing time for the transmitted packet.

(Embodiment 3)
The packet processing apparatus according to the third embodiment will be described with reference to the drawings. Figure 10 is a block diagram showing one example of the structure of a packet processing apparatus according to this embodiment. Referring to FIG. 10, the packet processing apparatus according to the present embodiment, the rules table 12, the user application 22, the rule extracting unit 32, rule application unit 42, the processing thread 52, transmitting receiving unit 62, and the received reception section 72 It is provided.

Rule table 12 holds the correspondence between the address and port number and the socket. Here, the socket retains TCP, and control data relating to the connection information of the transport layer represented by UDP or the like, and a processor identifier associated with the control data.

Figure 11 is a diagram illustrating a rule table 12 in the packet processing apparatus according to the present embodiment as an example. Referring to FIG. 11, the rule table 12, as a socket, in addition to control data necessary for protocol processing, including processor identifier.

User application 22 has a file descriptor for identifying the sockets, using a system call by using the file descriptor (eg, setsockopt), it is possible to set the processor identifier of the socket. Further, the user application 22 specifies the file descriptors, the read and write system calls can transmit and receive data by using a specific socket (connection).

Rule extraction unit 32, source address stored in the packet and the port number, and four sets of the destination address and port number to identify the socket representing the control information of the transport layer.

Rule application unit 42 includes a basic application unit 421 and dispatch unit 422. Rule application unit 42 receives the transmitted packet or received packet and the socket from the transmission reception unit 62 or the receiver receiving unit 72, the basic application unit 421, as the first processing, the transmission packet or the received packet is held in the socket using control information of the transport layer, the setting of transmission or reception. Further, dispatch unit 422 selects a processor according to the processor identifier held in the socket, the corresponding processing thread 52, as a second processing, to perform a transmission processing or reception processing of the transmission packet or received packet to ask.

Processing thread 52, similar to the processing thread 50 in the first embodiment, a kernel thread that is prepared for each processor. However, in this embodiment, performs reception processing of the layer 4 reception processing unit 521 for the received packet, the transmission processing unit 522 in that performs transmission processing of Layer 4 below for the transmission packet, differs from the first embodiment . Reception processing unit 521, finally, delivers the received packet to the user application 22.

Transmitting receiving unit 62 receives the transmission packet and the file descriptor from the user application 22. Transmitting receiving unit 62 receives the transmission packet and the file descriptor, it identifies the socket shown, passed to the rule application unit 42.

Receiving reception unit 72 receives a received packet from the network, searches the rule table 12 at that address and port number. The reception reception unit 72 transfers the socket and packets received search result to the rule application unit 42.

It will now be described transmission and reception processing by the packet processing apparatus according to this embodiment.

Operation of the transmission processing is as follows. First, the user application 22 to transmit the packet with the file descriptor to identify the socket as the argument, and calls the send system call. The send system call, when receiving the transmission packet with the file descriptor, transmitting receiving unit 62, identifies the socket from a file descriptor. Next, the basic application unit 421 of the rule application unit 42, as the first process, by using the control information of the transport layer to be retained in the socket identified, and sets the transmission to the transmission packet. Further, dispatch unit 422 selects the processing thread 52 corresponding the processor identifier held in the socket, and requests the sending process of the transmission packet as the second processing.

On the other hand, the operation of the receiving process is as follows. When receiving a packet from the network arrives, receives reception unit 72 based on the address and port number of the received packet, it identifies a corresponding socket from the rule table 12. Next, the basic application unit 421 of the rule application unit 42, as the first process, by using the control information of the transport layer to be held to a particular socket, and sets the reception processing of the received packet. Further, dispatch unit 422 selects the processing thread 52 corresponding the processor identifier held in the socket, and requests the reception processing of the received packet as the second processing.

According to the packet processing apparatus according to the present embodiment, socket, by holding in association with control data and processor information about the connection of the transport layer, the setting of the transmission or reception for transmitting or receiving a packet, the transmitting or the selection of a processor for performing the second processing for the received packet, to run as a single process, it is possible to reduce the processing time for the transmission or reception packet. Further, by using the existing system call setsockopt like, setting the processor that the user application 22 performs easy second processing can be performed, it is possible to perform a flexible processor selection.

(Embodiment 4)
The packet processing apparatus according to a fourth embodiment of the present invention will be described with reference to the drawings. Figure 12 is a block diagram showing one example of the structure of a packet processing apparatus according to this embodiment. Referring to FIG. 12, the packet processing apparatus according to the present actual embodiment, rules table 13, the rule extracting unit 33, rule application unit 40, the processing thread 50, transmitting receiving unit 60, and includes a reception accepting unit 70. Among the components of the present embodiment shown in FIG. 12, the operation of those denoted by the same reference numerals as in FIG. 2 will be omitted since it is identical to the operation of the components in the first embodiment, the description.

Rule table 13, by the rule setting device 23 provided outside of the packet processing device, the rule is set. For the rule table 13 and the rule setting device 23, it is possible as an example, to adopt the open flow (OpenFlow) technique described in Non-Patent Document 1.

Open Flow captures the communication as a flow of an end-to-end routing control per flow, fault recovery, load distribution, and performs optimization. Open flow switch acting as a forwarding node (OFS: OpenFlow Switch) is an open flow controller positioned to control server: comprises a secure channel for communication with the (OFC OpenFlow Controller), is appropriately added or rewrite instruction from the open flow controller It operates in accordance with the flow table that.

Packet processing apparatus according to the present embodiment, the rule setting device 23, rules table 13, and, the rules stored in the rule table 13, respectively, open flow switch in open flow, open flow controller, the flow table, and, the flow table It corresponds to the entry.

Figure 13 is a diagram showing an example of the entry of the flow table of open flow. Referring to FIG. 13, the flow table, for each flow, a matching condition to be matched with the packet header, and action that defines the processing content (actions), the set of the flow statistics (stats) is defined.

14, the contents of the action name and action that are defined in Non-Patent Document 2 is a table illustrating as an example. OUTPUT is an action to be output to the specified port (interface). SET_TP_DST from SET_VLAN_VID is an action to modify the fields in the packet header.

Open flow switch receives a packet, searches for an entry having a flow table (Fig. 13), conforming matching condition in the header information of the received packet (FlowKey). As a result of the search, when an entry is found matching the received packet, the open flow switch, for the received packet and performs the processing contents described in the action field of the entry. On the other hand, a result of the search, when it can not find the entry matching the received packet, the open flow switch, through a secure channel, and forwards the received packet to the open flow controller, to the transmission source and transmission destination of the received packet It requests the determination of the path of the basis packet, and updates the flow table receives a flow entry to achieve this. Thus, the open flow switch transfers the packet using the entry stored in the flow table as a processing rule.

Rule table 13 of the present embodiment (FIG. 12), as shown in FIG. 13, it has a matching condition fields and actions (actions) field. Further, the matching condition fields, like the rule table 10 in the first embodiment (FIG. 3), the matching condition is stored. In addition, the action field, similar to the rule table 10 in the first embodiment (FIG. 3), the action and processor identifier is stored.

Rule extraction unit 33 refers to the rule table 13, adapted to be processed packet rules in the absence of the rule table 13 queries the rule setting device 23 corresponding to the open flow controller. Rule setting device 23 receives an inquiry from the rule extracting unit 13 sets the rules associated with the actions and processor identifier as rules in the rule table 10.

As in the present embodiment, by using the packet processing device comprising a plurality of processors as an open flow switch of open flow, each open flow switch and flexible processor for executing processing of a packet from a plurality of processors it can be selected at a high speed.

Within the bounds of the full disclosure of the present invention (including the claims), and based on the basic technical concept, it is possible to modify and adjust embodiments. Also, possible is a variety of combinations and selections of various disclosed elements (including each element of each claim, each element of each embodiment, each element of each figure) in the region of the framework of the claims of the present invention . That is, the present invention naturally including the entire disclosure, various modifications will be made by those skilled in the art according to the technical concept, modification and in the appended claims.

10 ~ 13,110 rule table 20, 21 rule setting unit 22 User Application 23 rule setting device 30 to 33,130 rule extracting unit 40,41,42,140 rule application unit 401,411,421 basic application unit 402, 422 Dispatch parts 50 and 52 processing threads 501,521 reception processing unit 502,522 transmission processing unit 60-62 transmits reception unit 70-72 receives reception unit

Claims (20)

  1. Information stored in the packet, processing rule indicating the first processing for the packet, and a rules table for holding a rule to associate with each other processor identifier identifying a processor which performs second processing for the packet,
    The rule corresponding to stored in the target packet is a packet to be processed information, and rule extracting unit that extracts from the rule table,
    Based on the extracted rules, and execution of the first process in accordance with the processing rules for the target packet, and rules application unit for performing a request of the second processing for the processor corresponding to the processor identifier, packet processing apparatus characterized by comprising a.
  2. The first process is a process of determining whether to discard the target packet,
    In the second process, when the target packet is a packet to be received by the packet processing device is a processing of the upper layer with respect to the target packet, the packet wherein the target packet is to be transmitted in the packet processing device characterized in that it is a process of the lower layer with respect to the target packet in some cases, the packet processing device according to claim 1.
  3. The rule application unit, wherein, when the target packet in the first process is not a packet to be discarded, characterized in that a request for the second processing for the target packet to the processor, in claim 2 packet processing apparatus according.
  4. The rule table information stored in the packet, processing rule indicating the first processing for the packet, the processor identifier identifying a processor which performs second processing for the packet, and defines a flow including the packet It holds rules that relate to each other the flow definition field indicating a field,
    The rule application unit, if included multiple processor identifier to the extracted rule, the reference to the flow defined fields, to any processor of the plurality of processors corresponding to processor identifier of the plurality of Te, wherein the requesting the second processing for all of the target packet included in the same flow, the packet processing apparatus according to claim 2 or 3.
  5. The rule extracting unit, when the rule table does not hold rule corresponding to information stored in the target packet sets matching rule to the information the rule to the rule setting device capable of setting characterized in that it asked to, packet processing apparatus according to any one of claims 2 to 4.
  6. The first process is a process of determining the destination of the target packet,
    In the second process, when the target packet is a packet to be received by the packet processing device is a processing of the upper layer with respect to the target packet, the packet wherein the target packet is to be transmitted in the packet processing device characterized in that it is a process of the lower layer with respect to the target packet in some cases, the packet processing device according to claim 1.
  7. The rule application unit, in case the target packet is a packet to be received by the packet processing device, if the destination of the object packet is the packet processing unit, the second processing for the target packet characterized by requesting the processor, the packet processing apparatus according to claim 6.
  8. The rule extracting unit has a cache for temporarily storing the extracted rule, a matching rule is extracted from the cache information stored in the target packet,
    The rule application unit, in case the target packet is a packet to be received by the packet processing device, when the matching rule to the target packet is extracted from the cache by the rule extracting unit is configured for the target packet wherein the requesting the second processing to the processor, the packet processing apparatus according to claim 6 or 7.
  9. The first process is a process of identifying the control information in the transport layer for sending or receiving the target packet,
    The second processing, when the target packet is a packet to be received by the packet processing device is a receiving process of the layer 4 with respect to the target packet employing the control information is identified, the target packet is If a packet to be transmitted in the packet processing apparatus is characterized in that a sending process of the layer 4 below for the target packet employing the control information is identified, the packet processing apparatus according to claim 1 .
  10. The rule table holds a plurality of rules that are sorted according to priority,
    The rule extracting unit, when a plurality of rules adapted to the information stored in the target packet is stored in the rule table, to extract those higher priority of the plurality of rules wherein the packet processing device according to claim 1.
  11. Rules of the rule table, as the information stored in the packet, source address, destination address, source port number, and is characterized in that it comprises at least one of the destination port number, claim packet processing apparatus according to 1.
  12. To the rule table, additional rules, change, or, characterized in that it further includes a rule setting unit to be deleted, the packet processing device according to claim 1.
  13. One processor of the plurality of processors, associated information stored in the packet, processing rule indicating the first processing for the packet, and the processor identifier identifying a processor which performs second processing for the packet to each other from a rule table for holding a rule, a step of extracting a rule corresponding to the information stored in the target packet is a packet to be processed,
    The one processor, based on the extracted rules, and execution of the first process in accordance with the processing rules for the target packet, and a request for the second processing to the processor corresponding to the processor identifier packet processing method characterized by comprising the step of performing, the.
  14. The first process is a process of determining whether to discard the target packet,
    In the second process, when the target packet is a packet to be received by the packet processing device is a processing of the upper layer with respect to the target packet, the packet wherein the target packet is to be transmitted in the packet processing device characterized in that it is a process of the lower layer with respect to the target packet in some cases, the packet processing method according to claim 13.
  15. The first process is a process of determining the destination of the target packet,
    In the second process, when the target packet is a packet to be received by the packet processing device is a processing of the upper layer with respect to the target packet, the packet wherein the target packet is to be transmitted in the packet processing device characterized in that it is a process of the lower layer with respect to the target packet in some cases, the packet processing method according to claim 13.
  16. The first process is a process of identifying the control information in the transport layer for sending or receiving the target packet,
    The second processing, when the target packet is a packet to be received by the packet processing device is a receiving process of the layer 4 with respect to the target packet employing the control information is identified, the target packet is If a packet to be transmitted in the packet processing apparatus is characterized in that a sending process of the layer 4 below for the target packet employing the control information is identified, the packet processing method according to claim 13 .
  17. Information stored in the packet, processing rule indicating the first processing for the packet, and, from the rule table holding rule that associates each other processor identifier identifying a processor which performs second processing for the packet, to be processed a process of extracting a rule corresponding to the information stored in the target packet is a packet,
    Based on the extracted rule plurality and execution of the first process in accordance with the processing rule, and a process for the request of the second processing for the processor corresponding to the processor identifier for the target packet a program characterized by executing the one of the processors.
  18. The first process is a process of determining whether to discard the target packet,
    In the second process, when the target packet is a packet to be received by the packet processing device is a processing of the upper layer with respect to the target packet, the packet wherein the target packet is to be transmitted in the packet processing device characterized in that it is a process of the lower layer with respect to the target packet in some cases, the program of claim 17.
  19. The first process is a process of determining the destination of the target packet,
    In the second process, when the target packet is a packet to be received by the packet processing device is a processing of the upper layer with respect to the target packet, the packet wherein the target packet is to be transmitted in the packet processing device characterized in that it is a process of the lower layer with respect to the target packet in some cases, the program of claim 17.
  20. The first process is a process of identifying the control information in the transport layer for sending or receiving the target packet,
    The second processing, when the target packet is a packet to be received by the packet processing device is a receiving process of the layer 4 with respect to the target packet employing the control information is identified, the target packet is If a packet to be transmitted in the packet processing apparatus is characterized in that a sending process of the layer 4 below for the target packet employing the control information is identified, the program of claim 17.
PCT/JP2012/052465 2011-02-04 2012-02-03 Packet processing device, packet processing method and program WO2012105677A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2011-022303 2011-02-04
JP2011022303 2011-02-04

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2012555968A JP5900352B2 (en) 2011-02-04 2012-02-03 Packet processing apparatus, packet processing method and program

Publications (1)

Publication Number Publication Date
WO2012105677A1 true WO2012105677A1 (en) 2012-08-09

Family

ID=46602877

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2012/052465 WO2012105677A1 (en) 2011-02-04 2012-02-03 Packet processing device, packet processing method and program

Country Status (2)

Country Link
JP (1) JP5900352B2 (en)
WO (1) WO2012105677A1 (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014042141A1 (en) * 2012-09-11 2014-03-20 日本電気株式会社 Controller, communication system, communication method and program
WO2015133448A1 (en) * 2014-03-04 2015-09-11 日本電気株式会社 Packet processing device, packet processing method, and program
JP5917678B1 (en) * 2014-12-26 2016-05-18 株式会社Pfu Information processing apparatus, method, and program
JP2017509055A (en) * 2014-01-29 2017-03-30 華為技術有限公司Huawei Technologies Co.,Ltd. Method and apparatus for processing data packets based on parallel protocol stack instances
WO2017110619A1 (en) * 2015-12-21 2017-06-29 Kddi株式会社 Device for controlling packet transfer device that has multi-core cpu, and computer-readable storage medium
JP2018516001A (en) * 2015-05-11 2018-06-14 日本電気株式会社 Communication apparatus, system, method, and program

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002164928A (en) * 2000-10-11 2002-06-07 Lucent Technol Inc Communication method, communication system, and communication unit
JP2006174374A (en) * 2004-12-20 2006-06-29 Fujitsu Ltd Relay system
JP2007166513A (en) * 2005-12-16 2007-06-28 Nippon Telegr & Teleph Corp <Ntt> Device and method for processing communication

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4827499A (en) * 1987-06-12 1989-05-02 American Telephone And Telegraph Company At&T Bell Laboratories Call control of a distributed processing communications switching system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002164928A (en) * 2000-10-11 2002-06-07 Lucent Technol Inc Communication method, communication system, and communication unit
JP2006174374A (en) * 2004-12-20 2006-06-29 Fujitsu Ltd Relay system
JP2007166513A (en) * 2005-12-16 2007-06-28 Nippon Telegr & Teleph Corp <Ntt> Device and method for processing communication

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014042141A1 (en) * 2012-09-11 2014-03-20 日本電気株式会社 Controller, communication system, communication method and program
JPWO2014042141A1 (en) * 2012-09-11 2016-08-18 日本電気株式会社 Control device, communication system, communication method, and program
US10069947B2 (en) 2014-01-29 2018-09-04 Huawei Technologies Co., Ltd. Method and apparatus for processing data packet based on parallel protocol stack instances
JP2017509055A (en) * 2014-01-29 2017-03-30 華為技術有限公司Huawei Technologies Co.,Ltd. Method and apparatus for processing data packets based on parallel protocol stack instances
WO2015133448A1 (en) * 2014-03-04 2015-09-11 日本電気株式会社 Packet processing device, packet processing method, and program
JPWO2015133448A1 (en) * 2014-03-04 2017-04-06 日本電気株式会社 Packet processing apparatus, packet processing method and program
US10284478B2 (en) 2014-03-04 2019-05-07 Nec Corporation Packet processing device, packet processing method and program
JP5917678B1 (en) * 2014-12-26 2016-05-18 株式会社Pfu Information processing apparatus, method, and program
JP2018516001A (en) * 2015-05-11 2018-06-14 日本電気株式会社 Communication apparatus, system, method, and program
WO2017110619A1 (en) * 2015-12-21 2017-06-29 Kddi株式会社 Device for controlling packet transfer device that has multi-core cpu, and computer-readable storage medium

Also Published As

Publication number Publication date
JPWO2012105677A1 (en) 2014-07-03
JP5900352B2 (en) 2016-04-06

Similar Documents

Publication Publication Date Title
JP5874726B2 (en) Communication control system, control server, transfer node, communication control method, and communication control program
JP5654142B2 (en) Method for configuring network switches
EP3069484B1 (en) Shortening of service paths in service chains in a communications network
US9397949B2 (en) Terminal, control device, communication method, communication system, communication module, program, and information processing device
JP5742834B2 (en) Communication system, route control device, packet transfer device, and route control method
Curtis et al. Mahout: Low-overhead datacenter traffic management using end-host-based elephant detection.
KR20110119534A (en) Load-balancing via modulus distribution and tcp flow redirection due to server overload
JPWO2012133290A1 (en) Computer system and communication method
JP2015503274A (en) System and method for mitigating congestion in a fat tree topology using dynamic allocation of virtual lanes
US20110289230A1 (en) Application switch system and application switch method
US9137165B2 (en) Methods of load balancing using primary and stand-by addresses and related load balancers and servers
WO2012137646A1 (en) Network system, switch, and connection terminal detection method
US9621642B2 (en) Methods of forwarding data packets using transient tables and related load balancers
EP2904745B1 (en) Method and apparatus for accelerating forwarding in software-defined networks
JP5621778B2 (en) Content-based switch system and content-based switch method
RU2589340C2 (en) Network system and method of acquiring vlan tag data
KR101529950B1 (en) Communication system, information processing device, communication node, communication method, and computer-readable storage medium storing program
US9130867B2 (en) Flow control for virtualization-based server
DE202015009244U1 (en) Routing of traffic within and between autonomous systems
JP2006309383A (en) Computer system
US9215175B2 (en) Computer system including controller and plurality of switches and communication method in computer system
JP5768861B2 (en) Communication system, node, control server, communication method and program
US20080069114A1 (en) Communication device and method
CN102594697B (en) Load balancing method and device
US8737215B2 (en) Packet forwarding apparatus, communication system, process rule update method, and program

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 12742523

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase in:

Ref document number: 2012555968

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase in:

Ref country code: DE

122 Ep: pct app. not ent. europ. phase

Ref document number: 12742523

Country of ref document: EP

Kind code of ref document: A1