WO2014136864A1 - パケット書換装置、制御装置、通信システム、パケット送信方法及びプログラム - Google Patents
パケット書換装置、制御装置、通信システム、パケット送信方法及びプログラム Download PDFInfo
- Publication number
- WO2014136864A1 WO2014136864A1 PCT/JP2014/055744 JP2014055744W WO2014136864A1 WO 2014136864 A1 WO2014136864 A1 WO 2014136864A1 JP 2014055744 W JP2014055744 W JP 2014055744W WO 2014136864 A1 WO2014136864 A1 WO 2014136864A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- packet
- rewriting
- switch
- rule
- header
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/22—Parsing or analysis of headers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/46—Interconnection of networks
- H04L12/4633—Interconnection of networks using encapsulation techniques, e.g. tunneling
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/46—Interconnection of networks
- H04L12/4641—Virtual LANs, VLANs, e.g. virtual private networks [VPN]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/06—Optimizing the usage of the radio link, e.g. header compression, information sizing, discarding information
- H04W28/065—Optimizing the usage of the radio link, e.g. header compression, information sizing, discarding information using assembly or disassembly of packets
Definitions
- the present invention is based on a Japanese patent application: Japanese Patent Application No. 2013-045264 (filed on March 7, 2013), and the entire contents of this application are incorporated in the present specification by reference.
- the present invention relates to a packet rewriting device, a control device, a communication system, a packet transmission method, and a program, and more particularly, to a packet rewriting device, a control device, a communication system, a packet transmission method, and a program arranged between tunnel endpoints.
- Non-Patent Document 1 is a draft of VXLAN.
- VXLAN encapsulates layer 2 frames at the tunnel end point that is the end point of the virtual tunnel.
- VNI VXLAN Network Identifier
- Header also referred to as outer header
- VXLAN Frame Format This VNI is twice as long as the VLAN ID defined in IEEE802.1Q, and has received attention because it can dramatically increase the number of “tenants (physical network shared users)” in the cloud computing environment. (Maximum is about 16.77 million (2 ⁇ 24)).
- Non-Patent Document 2 is a draft of NVGRE that performs the same tunneling as VXLAN. Also in NVGRE, the number of segments that can be logically divided is increased by Tenant Network Identifier (TNI) having a length of 24 bits.
- TTI Tenant Network Identifier
- Non-Patent Documents 3 and 4 OpenFlow captures communication as an end-to-end flow and performs path control, failure recovery, load balancing, and optimization on a per-flow basis.
- the OpenFlow switch specified in Non-Patent Document 4 includes a secure channel for communication with the OpenFlow controller, and operates according to a flow table that is appropriately added or rewritten from the OpenFlow controller. For each flow, a set of match conditions (Match Fields), flow statistical information (Counters), and instructions (Instructions) that define processing contents are defined for each flow (non-patented). (Refer to the section “5.2 Flow Table” in Reference 4).
- the OpenFlow switch when it receives a packet, it searches the flow table for an entry having a matching condition (see “5.3 Matching” in Non-Patent Document 4) that matches the header information of the received packet. If an entry that matches the received packet is found as a result of the search, the OpenFlow switch updates the flow statistical information (counter) and processes the processing (designated) in the instruction field of the entry for the received packet. Perform packet transmission, flooding, discard, etc. from the port. On the other hand, if no entry matching the received packet is found as a result of the search, the OpenFlow switch sends an entry setting request to the OpenFlow controller via the secure channel, that is, a control for processing the received packet. An information transmission request (Packet-In message) is transmitted. The OpenFlow switch receives a flow entry whose processing content is defined and updates the flow table. As described above, the OpenFlow switch performs packet transfer using the entry stored in the flow table as control information.
- a matching condition see “5.3 Matching” in Non-Patent Document 4
- NVGRE Network Virtualization using General Router Encapsulation
- [online] [February 18, 2013 search]
- “OpenFlow: Enabling Innovation in Campus Networks” [online], [Search on February 18, 2013]
- Non-Patent Documents 3 and 4 are devices for connecting virtual tunnel endpoints.
- the OpenFlow switch that can specify the capsule header (additional header) added between the VXLAN and NVGRE tunnel end points as a match condition is not so commercialized. For this reason, in a general OpenFlow switch, there is a problem that different processes cannot be applied based on identifiers such as VNI and TNI included in a capsule header (additional header). Of course, there are switches that can specify these identifiers as matching conditions, but they are expensive.
- An object of the present invention is to provide a packet rewriting device, a control device, a communication system, a packet transmission method, and a program that can contribute to facilitating control of packets between tunnel endpoints of tunneling protocols such as VXLAN and NVGRE.
- a packet rewrite rule storage unit that stores a packet rewrite rule for writing information corresponding to a virtual network identifier included in an additional header of a packet output from a tunnel end point to a predetermined area of the original header
- a packet rewriting unit that rewrites a packet in which information corresponding to the virtual network identifier is written in the original header of the transmission packet in accordance with the packet rewriting rule, and refers to the contents of the tunnel endpoint and the original header.
- a packet rewriting device disposed between the switch and the switch that determines the processing to be applied to the packet.
- a packet rewrite rule creating unit for creating a packet rewrite rule for writing information corresponding to a virtual network identifier included in an additional header of a packet output from a tunnel end point into a predetermined area of the original header
- a control unit that distributes the created packet rewriting rule to a packet rewriting device arranged between a switch and the tunnel end point.
- the switch that determines the processing to be applied to the packet with reference to the content of the original header, the matching condition that matches the content of the original header to the switch, and the packet that matches the matching condition
- the control device that controls the switch and the information corresponding to the virtual network identifier included in the additional header of the packet output from the tunnel end point are set in the original header.
- a packet rewriting rule storage unit that stores a packet rewriting rule to be written in the area of the packet, and a packet rewriting unit that rewrites a packet in which information corresponding to the virtual network identifier is written in the original header of a transmission packet according to the packet rewriting rule.
- the tunnel endpoint A switch that determines processing to be applied to a packet with reference to the content of the original header, and a packet rewriting device that is disposed between the tunnel endpoint and the tunnel endpoint.
- a communication system that performs packet routing is provided.
- the original header of the transmission packet is in accordance with a packet rewrite rule for writing information corresponding to the virtual network identifier included in the additional header of the packet output from the tunnel end point in a predetermined area of the original header.
- a packet transmission method includes: rewriting information corresponding to the virtual network identifier into a packet written therein; and transmitting the rewritten packet to a switch via a predetermined physical port. The method is tied to a specific machine, a packet rewrite device that is placed between the tunnel endpoint and the switch.
- the original header of the transmission packet is input to the process of rewriting the information corresponding to the virtual network identifier in the packet written to the switch and the process of transmitting the rewritten packet to the switch through a predetermined physical port.
- a program to be executed by a computer is provided. This program can be recorded on a computer-readable (non-transient) storage medium. That is, the present invention can be embodied as a computer program product.
- FIG. 1 it can be realized by a packet rewriting device 1000A arranged between a tunnel end point and a switch.
- This packet rewriting apparatus 1000A has a packet rewriting rule storage unit 1005 for storing a packet rewriting rule for writing information corresponding to a virtual network identifier included in an additional header of a packet output from a tunnel end point in a predetermined area of the original header. And a packet rewriting unit 1004.
- the packet rewriting unit 1004 executes processing for rewriting the output packet of the tunnel endpoint into a packet in which information corresponding to the virtual network identifier is written in the original header according to the packet rewriting rule.
- the virtual network identifier (tenant ID) itself such as VNI or TNI included in the capsule header (additional header) itself or these Information corresponding to is written in the original header.
- a switch disposed between the packet rewriting devices 1000A can perform transfer processing based on a virtual network identifier (tenant ID) included in the header after rewriting (see FIGS. 9 and 11). .
- FIG. 2 is a diagram illustrating a configuration of the communication system according to the first embodiment. Referring to FIG. 2, there is shown a configuration in which two physical servers 1000 arranged at each base, a switch 10 that connects the bases, and a controller 100 that controls these switches 10 are connected.
- the configuration shown in FIG. 2 can be employed as a configuration for connecting data centers, for example.
- the controller 100 is connected to the switch 10 and the physical server 1000 via a control channel indicated by a broken line in the figure.
- the switch 10 is configured by an OpenFlow switch that performs packet rewriting, forwarding, and the like in accordance with control information (flow entry) set by the controller 100.
- the physical server 1000 includes a VM (Virtual Machine) 1001, a virtual switch 1002, a tunnel endpoint 1003, a packet rewriting unit 1004, a packet rewriting rule storage unit 1005, a controller. And a communication unit 1006.
- the packet rewriting unit 1004 and the packet rewriting rule storage unit 1005 in FIG. 3 correspond to the packet rewriting module 1004A in FIG. In FIG. 2, the controller communication unit 1006 is omitted.
- the VM 1001 is a virtual machine that is managed by a hypervisor (not shown) and operates on a virtualization platform on a physical server.
- the VM 1001 belongs to one of the virtual networks (hereinafter also referred to as “tenant”), and the same virtual that operates on another physical server via the virtual switch 1002, the tunnel endpoint 1003, and the packet rewriting unit 1004. It is possible to communicate with the VM 1001 belonging to the network.
- the virtual switch 1002 holds a MAC (Media Access Protocol) address table for each tenant, and transfers a packet received from the VM 1001 or the tunnel endpoint 1003 to an appropriate destination. More specifically, when receiving a packet, the virtual switch 1002 refers to the MAC address table for each tenant to which the packet belongs, and transfers the packet to the corresponding port of the same tenant.
- MAC Media Access Protocol
- the virtual switch 1002 holds information such as which tenant each VM 1001 connected to itself belongs to.
- FIG. 4 is an example of tenant information held by the virtual switch 1002.
- the virtual switch 1002 refers to the tenant information shown in FIG. 4 and identifies the ID of the tenant to which the VM that is the transmission source of the received packet belongs. Note that the tenant information illustrated in FIG. 4 is synchronously managed with the tenant information held by the controller via the controller communication unit 1006, for example.
- the virtual switch 1002 transfers the packet to that VM.
- the virtual switch 1002 transfers the packet to the tunnel endpoint 1003 in order to deliver the packet to the physical server. At that time, the virtual switch 1002 notifies the tunnel end point 1003 of the tenant ID to which the VM belongs.
- the tunnel end point (TEP) 1003 encapsulates a packet according to a tunneling protocol such as VXLAN or NVGRE.
- the tunnel end point 1003 holds VM management information.
- FIG. 5 shows an example of VM management information held by the tunnel endpoint 1003.
- information such as which tenant the VM belongs to and on which physical server is stored.
- the tunnel end point 1003 When the tunnel end point 1003 receives a packet from the virtual switch 1002, the tunnel end point 1003 searches the VM management information in FIG. 5 for a corresponding entry using the tenant ID to which the VM of the transmission source of the packet belongs and the destination MAC address of the packet as keys. Then, the packet is encapsulated based on the entry, and the encapsulated packet is transferred to the packet rewriting unit 1004.
- the tunnel endpoint stores the IP (Internet Protocol) address of the physical server retrieved from the VM management information and the header (additional header, outer header) outside the encapsulated packet of the MAC address of the physical server. .
- the tunnel end point 1003 receives a packet from the packet rewriting unit 1004, it returns the encapsulated packet to the original packet (decapsulation) and transfers it to the virtual switch 1002. At that time, the tunnel end point 1003 notifies the virtual switch 1002 of the tenant ID embedded in the encapsulation header (additional header, outer header).
- FIG. 6 is an example of packet rewrite rules held in the packet rewrite rule storage unit 1005.
- the identifier of the destination physical server (the upper 3 octets are used in the destination MAC address field of the header (original header) before the header for encapsulation (additional header, outer header) is added, the specific value.
- Shows an example of a packet rewriting rule for writing a tenant ID (using the lower 3 octets and embedding the tenant ID in the part of xx: xx: xx).
- the packet rewrite rule is set in the packet rewrite rule storage unit 1005 by the controller 100 and is synchronized with the packet rewrite rule held in the packet rewrite rule storage unit 104 of the controller 100.
- FIG. 7 is a diagram showing the contents of the destination MAC address field after rewriting according to the packet rewriting rule of FIG.
- OUI Organizationally Unique Identifier
- the upper 24 bits OUI Organizationally Unique Identifier
- the lower 24 bits NIC Network Interface
- a process of rewriting the Controller) identification unit with the tenant identifier is performed.
- the I / G bit indicates an individual address / group address identification bit
- the G / L bit indicates a global address / local address identification bit.
- the packet rewriting unit 1004 When the packet rewriting unit 1004 receives a packet from the tunnel end point 1003, it rewrites the destination MAC address of the packet according to the packet rewriting rule of the packet rewriting rule storage unit 1005. Specifically, the packet rewriting unit 1004 replaces the upper 24 bits of the destination MAC address of the original header with the identifier of the physical server specified by the packet rewriting rule. Further, the packet rewriting unit 1004 extracts the tenant ID from the header for encapsulation of the received packet (additional header, outer header) and embeds it in the lower 24 bits of the MAC address of the original header.
- the packet rewriting unit 1004 transfers the rewritten packet to the physical port.
- the packet rewriting unit 1004 when the packet rewriting unit 1004 receives a packet from the switch 10 side, the packet rewriting unit 1004 performs an operation of restoring the packet to the original packet according to the contents of the packet rewriting rule storage unit 1005. Specifically, the packet rewriting unit 1004 performs an operation of restoring the upper 24 bits and the lower 24 bits of the destination MAC address of the original header to the contents before rewriting shown in FIG.
- the controller communication unit 1006 performs an operation of transferring information (tenant information, VM management information, packet rewrite rules, etc.) distributed from the controller 100 to the virtual switch 1002, the tunnel endpoint 1003, and the packet rewrite rule storage unit 1005, respectively.
- the controller 100 sets a packet rewrite rule for the physical server 1000 and sets control information (flow entry) for transferring the rewritten packet to the switch 10 on the packet transfer path.
- FIG. 8 is a functional block diagram showing the configuration of the controller 100 of the present embodiment. Referring to FIG. 8, a configuration including a switch control unit 101, a physical server storage unit 102, a packet rewrite rule creation unit 103, a packet rewrite rule storage unit 104, and a physical server control unit 105 is shown. .
- the switch control unit 101 grasps the network topology based on the information received from the switch 10, and routes between the physical servers in the network identified using the physical server information stored in the physical server storage unit 102 Calculate In addition, the switch control unit 101 uses the physical server information and the packet rewrite rules stored in the packet rewrite rule storage unit 104 to instruct control information (flow entry) to instruct the switch 10 on the route to transfer a packet along the route. Create Further, the switch control unit 101 sets the created control information (flow entry) in each switch. In this embodiment, the switch control unit 101 creates a route between all physical servers having tunnel endpoints, and sets control information (flow entry) so that all tunnel endpoints can communicate with each other. .
- the physical server storage unit 102 stores physical server information including each physical server address and connection destination switch information.
- FIG. 9 is an example of physical server information.
- the IP address and MAC address of the physical server are used when specifying the destination address in the matching condition of the control information (flow entry).
- the connection destination switch ID and the connection destination port number are referred to when specifying a switch that is a starting point and an ending point of a route to be calculated when performing route calculation.
- the packet rewrite rule creation unit 103 creates a packet rewrite rule corresponding to the physical server.
- the packet rewrite rule creation unit 103 assigns an identifier (ID) that is unique to the system to each physical server, and based on the identifier and the added physical server MAC address, the packet shown in FIG. Create a rewrite rule.
- ID an identifier
- the created packet rewrite rule is stored in the packet rewrite rule storage unit 104, and the physical server control unit 105 transmits it to the physical server 1000 at an appropriate timing.
- the distribution timing of the packet rewriting rule can be as follows. For example, every time a packet rewrite rule is created, the packet rewrite rule may be distributed to all physical servers, or a method of distributing only to a physical server that needs the packet rewrite rule may be adopted. For example, when focusing on two physical servers, if virtual machines belonging to the same tenant are not operating on the two physical servers, the two physical servers do not need to communicate. Therefore, it is not necessary to distribute a packet rewrite rule for realizing communication with the other physical server to the two physical servers.
- each physical server inquires the controller 100 when it needs a rewrite rule, instead of being distributed in advance.
- the packet rewrite unit 1004 of the physical server 1000 receives the packet and searches for the packet rewrite rule stored in the packet rewrite rule storage unit 1005, if there is no corresponding packet rewrite rule, the packet rewrite unit 1004 A method of requesting a packet rewrite rule from the controller 100 can also be adopted.
- the packet rewriting unit 1004 of each physical server 1000 embeds the physical server identifier and tenant ID in the destination MAC address field of the packet. Then, the controller 100 sets a flow entry including the physical server identifier and the tenant ID as a match condition in each switch 10 to realize packet transfer.
- the physical server control unit 105 transmits a packet rewrite rule to the physical server 1000, and updates the stored contents of the packet rewrite rule storage unit 1005. Further, the physical server control unit 105 distributes the tenant information (see FIG. 4) and the VM management information (see FIG. 5) to each physical server 1000.
- Each unit (processing means) of the physical server and controller (including the configuration divided into the OpenFlow controller and the server controller) shown in FIGS. 2, 3, 8, and 14 is connected to the computer that constitutes these devices.
- the hardware can also be used to implement a computer program that executes the processes described above.
- FIG. 10 is a flowchart showing the operation at the time of packet transmission of the physical server of the first embodiment.
- the virtual switch 1002 receives a packet transmitted from the VM (step S110).
- step S130 when the transfer destination of the received packet is a packet addressed to a VM connected to the same virtual switch (Yes in step S120), the virtual switch 1002 sends the packet to the VM connected to the same virtual switch. Transfer (step S130).
- the virtual switch 1002 sends the received packet together with the tenant ID to the tunnel end point 1003.
- the tunnel end point 1003 performs encapsulation by adding a capsule header (additional header) including the tenant ID to the packet (step S140).
- the packet rewriting unit 1004 searches the packet rewriting rule storage unit 1005 for a packet rewriting rule to be applied to the packet using the destination MAC address of the encapsulated packet, that is, the MAC address of the destination physical server as a key. (Step S150).
- the packet rewriting unit 1004 has a MAC address of 00: 00: BB: BB in the packet rewriting rule of FIG.
- the destination MAC address of the original header of the packet is rewritten to “02: 00: 02: xx: xx: xx” using the rule: BB: BB (step S160).
- the tenant identifier included in the capsule header is set in “xx: xx: xx”.
- the packet rewriting unit 1004 transmits the rewritten packet to the switch 10 through the physical port (step S170).
- the controller 100 sets the packet rewrite rule and the physical server identifier in the switch 10 on the path between the physical servers 1000 as control information (flow entry) using the matching condition. Therefore, as shown in FIG. 11, the packet transmitted from the packet rewriting unit 1004 is transferred to the opposing physical server 1000 by the switch on the path (the number #n attached to the vicinity of the switch in FIG. 11 is the port number). Showing).
- FIG. 12 is a flowchart showing the operation at the time of packet reception of the physical server of the first embodiment.
- the packet rewriting unit 1004 reads the contents of the rewritten MAC address field from the packet rewriting rule storage unit 1005. Using the as a key, a packet rewrite rule to be applied to the rewritten packet is searched (step S220).
- the packet rewriting unit 1004 has the MAC address after rewriting of 00 in the packet rewriting rule of FIG.
- the destination MAC address of the original header of the packet is restored to “00: 00: BB: BB: BB” using the rule of 0: 00: BB: BB: BB: BB (step S230).
- the tunnel endpoint 1003 decapsulates the packet and sends it to the virtual switch 1002 (step S240).
- the virtual switch 1002 selects the MAC address table based on the tenant ID sent from the tunnel endpoint 1003, and the packet is sent to the corresponding VM based on the entry that matches the header of the decapsulated packet, that is, the original header. Is transferred (step S250).
- the switch 10 matches.
- the control information (flow entry) having the highest priority (the uppermost entry in the balloon of FIG. 13) is applied to transfer the packet from the port # 4.
- packets from other tenants do not match the uppermost entry in the callout in FIG. 13, and are transferred through the upper path in FIG. 13 (the same path as in FIG. 11).
- flow control between bases using the tunneling technology can be realized without using an expensive switch capable of interpreting the capsule header.
- label switching equivalent to MPLS can be realized using an OpenFlow switch.
- the packet rewriting unit 1004 of the physical server 1000 embeds the identifier of the tunnel endpoint 1003 in the destination MAC address field of the packet. This identifier can be handled like a label in MPLS, and the switch 10 can transfer the packet.
- the controller instructs rewriting that embeds the identifier of the tunnel end point in the packet, creates control information (flow entry) using the identifier as a match condition, and sets it in each switch 10 in the network.
- the switch 10 does not need to create a label or calculate a route, and is advantageous in that processing is reduced as compared to an MPLS router.
- FIG. 14 a configuration (second embodiment) in which the OpenFlow control function and the physical server control function of the controller 100 are divided and arranged in separate apparatuses can be employed.
- the OpenFlow controller 100B in FIG. 14 provides an interface for controlling the OpenFlow network to the server controller 100A.
- a function for registering control information (flow entry) in the switch 10 and a function for acquiring network topology information are arranged on the OpenFlow controller 100B side. Is done.
- the source physical server 1000 embeds the tenant ID to which the VM belongs in the destination MAC address, so that there are a plurality of MAC addresses to be received by the destination physical server.
- the physical server needs to operate its NIC in promiscuous mode.
- the destination of the packet must be checked by software, and the packet other than its own must be discarded, which places a heavy load on the CPU (Central Processing Unit) End up.
- CPU Central Processing Unit
- FIG. 15 shows the operation mode of the NIC in each environment.
- the number of MAC addresses to be processed by each physical server does not exceed the number of VMs operating on the physical server.
- the NIC needs to be operated in the promiscuous mode.
- it is necessary to configure the network with a switching hub so that packets other than the destination are not transferred to each physical server so that the load of packet reception processing by the software of each physical server does not increase.
- the NIC may be operated in the normal mode. No matter how many virtual servers (VMs) are operating on the physical server, the MAC address of the packet to be received by the physical server is only one MAC address of the tunnel endpoint.
- a network may be constructed using a repeater hub.
- the example in which the packet is rewritten using the destination MAC address field of the original header has been described.
- the rewritten packet can be restored by the switch on the egress side. Therefore, other fields such as the destination IP address can be rewritten.
- the content to be rewritten need not be the virtual network ID (tenant ID) itself.
- the same effect can be obtained by assigning a flow identifier or the like corresponding to the virtual network ID (tenant ID), writing this flow identifier in the original header, and using it as a matching condition for control information (flow entry).
- the packet rewriting unit is a packet rewriting device that refers to the packet rewriting rule and performs a restoration process on the received packet that has been rewritten.
- a packet rewriting device that uses a packet rewriting rule distributed from a control device that controls the switch as the packet rewriting rule.
- a packet rewriting device that uses a packet rewriting rule that rewrites the content of a predetermined area of an original header as the packet rewriting rule to the content used in the matching condition of the control information set in the switch by the control device.
- a packet rewriting apparatus that uses a packet rewriting rule that writes an identifier for uniquely identifying the virtual network as the packet rewriting rule.
- [Seventh form] (Refer to the control device (controller) according to the second viewpoint)
- [Eighth form] In the control device (controller) of the seventh aspect, A control device that creates a match condition for control information set in a subordinate switch using the packet rewrite rule.
- the controller is A packet rewrite rule creation unit for creating a packet rewrite rule to be stored in the packet rewrite rule storage unit; A control unit that distributes the created packet rewrite rule to a packet rewrite device disposed between the switch and the tunnel end point; [Eleventh form] (Refer to the packet transmission method according to the fourth aspect above) [Twelfth embodiment] (Refer to the program from the fifth viewpoint above)
- the tenth and eleventh forms can be developed into the second to sixth forms as in the first form.
- Switch 100 Controller 100A Server controller 100B Open flow controller 101 Switch control part 102 Physical server memory
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
Description
本発明は、日本国特許出願:特願2013-045264号(2013年3月7日出願)に基づくものであり、同出願の全記載内容は引用をもって本書に組み込み記載されているものとする。
本発明は、パケット書換装置、制御装置、通信システム、パケット送信方法及びプログラムに関し、特に、トンネルエンドポイント間に配置されるパケット書換装置、制御装置、通信システム、パケット送信方法及びプログラムに関する。
続いて、パケット書換装置をデータセンタ等の物理サーバ内に内蔵させた第1の実施形態について図面を参照して詳細に説明する。図2は、第1の実施形態の通信システムの構成を示す図である。図2を参照すると、それぞれの拠点に配置された2台の物理サーバ1000と、拠点間を接続するスイッチ10と、これらスイッチ10を制御するコントローラ100とを接続した構成が示されている。なお、図2に示した構成は、例えば、データセンタ間を接続する構成として採用することができる。
[第1の形態]
(上記第1の視点によるパケット書換装置参照)
[第2の形態]
第1の形態のパケット書換装置において、
前記パケット書換部は、前記パケット書換ルールを参照して、前記書き換えが行われた受信パケットの復元処理を実行するパケット書換装置。
[第3の形態]
第1又は第2の形態のパケット書換装置において、
前記パケット書換ルールとして、前記スイッチを制御する制御装置から配布されたパケット書換ルールを用いるパケット書換装置。
[第4の形態]
第1から第3いずれか一の形態のパケット書換装置において、
前記パケット書換ルールとして、オリジナルヘッダの所定の領域の内容を、前記制御装置が前記スイッチに設定した制御情報のマッチ条件に用いられた内容に書き換えるパケット書換ルールを用いるパケット書換装置。
[第5の形態]
第1から第4いずれか一の形態のパケット書換装置において、
前記パケット書換ルールとして、オリジナルヘッダの所定の領域の内容を、前記仮想ネットワークを一意に識別する識別子を書き込むパケット書換ルールを用いるパケット書換装置。
[第6の形態]
第1から第5いずれか一の形態のパケット書換装置において、
前記トンネルエンドポイントを介して通信する仮想マシンが動作する物理サーバに内蔵されているパケット書換装置。
[第7の形態]
(上記第2の視点による制御装置(コントローラ)参照)
[第8の形態]
第7の形態の制御装置(コントローラ)において、
前記パケット書換ルールを用いて、配下のスイッチに設定する制御情報のマッチ条件を作成する制御装置。
[第9の形態]
(上記第3の視点による通信システム参照)
[第10の形態]
第9の形態の通信システムにおいて、
前記制御装置は、
前記パケット書換ルール記憶部に記憶させるパケット書換ルールを作成するパケット書換ルール作成部と、
前記作成したパケット書換ルールを、前記スイッチと前記トンネルエンドポイントとの間に配置されたパケット書換装置に配付する制御部とを備える。
[第11の形態]
(上記第4の視点によるパケット送信方法参照)
[第12の形態]
(上記第5の視点によるプログラム参照)
なお、上記第10、第11の形態は、第1の形態と同様に、第2~第6の形態に展開することが可能である。
100 コントローラ
100A サーバコントローラ
100B オープンフローコントローラ
101 スイッチ制御部
102 物理サーバ記憶部
102A 制御部
102B 通信部
103 パケット書換ルール作成部
104 パケット書換ルール記憶部
105 物理サーバ制御部
1000 物理サーバ
1000A パケット書換装置
1001 VM(Virtual Machine)
1002 仮想スイッチ
1003 トンネルエンドポイント
1004 パケット書換部
1004A パケット書換モジュール
1005 パケット書換ルール記憶部
1006 コントローラ通信部
Claims (12)
- トンネルエンドポイントから出力されるパケットの追加ヘッダに含まれる仮想ネットワーク識別子に対応する情報を、オリジナルヘッダの所定の領域に書き込むパケット書換ルールを記憶するパケット書換ルール記憶部と、
前記パケット書換ルールに従い、送信パケットの前記オリジナルヘッダに前記仮想ネットワーク識別子に対応する情報を書き込んだパケットに書き換えるパケット書換部とを備え、
前記トンネルエンドポイントと、前記オリジナルヘッダの内容を参照してパケットに適用する処理を決定するスイッチと、の間に配置されるパケット書換装置。 - 前記パケット書換部は、前記パケット書換ルールを参照して、前記書き換えが行われた受信パケットの復元処理を実行する請求項1のパケット書換装置。
- 前記パケット書換ルールとして、前記スイッチを制御する制御装置から配布されたパケット書換ルールを用いる請求項1又は2のパケット書換装置。
- 前記パケット書換ルールとして、オリジナルヘッダの所定の領域の内容を、前記制御装置が前記スイッチに設定した制御情報のマッチ条件に用いられた内容に書き換えるパケット書換ルールを用いる請求項3のパケット書換装置。
- 前記パケット書換ルールとして、オリジナルヘッダの所定の領域の内容を、前記仮想ネットワークを一意に識別する識別子に書き換えるパケット書換ルールを用いる請求項1から4いずれか一のパケット書換装置。
- 前記トンネルエンドポイントを介して通信する仮想マシンが動作する物理サーバに内蔵されている請求項1から5いずれか一のパケット書換装置。
- トンネルエンドポイントから出力されるパケットの追加ヘッダに含まれる仮想ネットワーク識別子に対応する情報を、オリジナルヘッダの所定の領域に書き込むパケット書換ルールを作成するパケット書換ルール作成部と、
スイッチと前記トンネルエンドポイントとの間に配置されたパケット書換装置に前記作成したパケット書換ルールを配付する制御部とを備える制御装置。 - 前記パケット書換ルールを用いて、配下のスイッチに設定する制御情報のマッチ条件を作成する請求項7の制御装置。
- オリジナルヘッダの内容を参照してパケットに適用する処理を決定するスイッチと、
前記スイッチに、オリジナルヘッダの内容と照合するマッチ条件と該マッチ条件に適合するパケットに適用する処理とを定めた制御情報を設定することにより、前記スイッチを制御する制御装置と、
トンネルエンドポイントから出力されるパケットの追加ヘッダに含まれる仮想ネットワーク識別子に対応する情報を、オリジナルヘッダの所定の領域に書き込むパケット書換ルールを記憶するパケット書換ルール記憶部と、
前記パケット書換ルールに従い、送信パケットの前記オリジナルヘッダに前記仮想ネットワーク識別子に対応する情報を書き込んだパケットに書き換えるパケット書換部とを備え、前記トンネルエンドポイントと、前記オリジナルヘッダの内容を参照してパケットに適用する処理を決定するスイッチと、の間に配置されるパケット書換装置と、を含み、
前記スイッチ及び前記トンネルエンドポイントを介して、トンネルエンドポイント間のパケットの経路制御を行う通信システム。 - 前記制御装置は、
前記パケット書換ルール記憶部に記憶させるパケット書換ルールを作成するパケット書換ルール作成部と、
前記スイッチと前記トンネルエンドポイントとの間に配置されたパケット書換装置に前記作成したパケット書換ルールを配付する制御部とを備える請求項9の通信システム。 - トンネルエンドポイントから出力されるパケットの追加ヘッダに含まれる仮想ネットワーク識別子に対応する情報を、オリジナルヘッダの所定の領域に書き込むパケット書換ルールに従い、送信パケットの前記オリジナルヘッダに前記仮想ネットワーク識別子に対応する情報を書き込んだパケットに書き換えるステップと、
前記書き換えたパケットを所定の物理ポートを介してスイッチに送信するステップと、を含むパケット送信方法。 - トンネルエンドポイントから出力されるパケットの追加ヘッダに含まれる仮想ネットワーク識別子に対応する情報を、オリジナルヘッダの所定の領域に書き込むパケット書換ルールに従い、送信パケットの前記オリジナルヘッダに前記仮想ネットワーク識別子に対応する情報を書き込んだパケットに書き換える処理と、
前記書き換えたパケットを所定の物理ポートを介してスイッチに送信する処理と、
を前記トンネルエンドポイントから出力されたパケットが入力されるコンピュータに実行させるプログラム。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/771,028 US10237377B2 (en) | 2013-03-07 | 2014-03-06 | Packet rewriting apparatus, control apparatus, communication system, packet transmission method and program |
JP2015504375A JP5991424B2 (ja) | 2013-03-07 | 2014-03-06 | パケット書換装置、制御装置、通信システム、パケット送信方法及びプログラム |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2013045264 | 2013-03-07 | ||
JP2013-045264 | 2013-03-07 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014136864A1 true WO2014136864A1 (ja) | 2014-09-12 |
Family
ID=51491372
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/055744 WO2014136864A1 (ja) | 2013-03-07 | 2014-03-06 | パケット書換装置、制御装置、通信システム、パケット送信方法及びプログラム |
Country Status (3)
Country | Link |
---|---|
US (1) | US10237377B2 (ja) |
JP (1) | JP5991424B2 (ja) |
WO (1) | WO2014136864A1 (ja) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016134876A (ja) * | 2015-01-22 | 2016-07-25 | 富士通株式会社 | 情報処理システム、情報処理装置、および情報処理システムの制御方法 |
JP2016144144A (ja) * | 2015-02-04 | 2016-08-08 | 日本電信電話株式会社 | 負荷分散システム及び負荷分散方法 |
WO2016132262A1 (en) * | 2015-02-16 | 2016-08-25 | Telefonaktiebolaget Lm Ericsson (Publ) | Method and system for providing "anywhere access" for fixed broadband subscribers |
CN107637029A (zh) * | 2015-06-10 | 2018-01-26 | 株式会社宙连 | 用于向无线终端提供对ip网络的访问的通信系统及通信方法 |
JP2018033136A (ja) * | 2016-08-25 | 2018-03-01 | エヌエイチエヌ エンターテインメント コーポレーションNHN Entertainment Corporation | 仮想ネットワーク環境で仮想スイッチを利用してロードバランシングを処理する方法およびシステム |
US10063470B2 (en) | 2015-05-12 | 2018-08-28 | Industrial Technology Research Institute | Data center network system based on software-defined network and packet forwarding method, address resolution method, routing controller thereof |
EP3280100A4 (en) * | 2015-03-31 | 2018-12-05 | Nec Corporation | Control device, control method, and program |
JP2019514310A (ja) * | 2016-04-27 | 2019-05-30 | 新華三技術有限公司New H3C Technologies Co., Ltd. | パケット転送 |
US11075981B2 (en) | 2016-08-25 | 2021-07-27 | Nhn Entertainment Corporation | Method and system for processing direct server return load balancing using loopback interface in virtual network environment |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3091705B1 (en) * | 2014-01-23 | 2018-09-05 | Huawei Technologies Co., Ltd. | Tunnel processing method for packet, switching device and control device |
CN105515992B (zh) * | 2014-09-26 | 2019-01-11 | 新华三技术有限公司 | Vxlan网络中的流表项处理方法及装置 |
US20160173600A1 (en) * | 2014-12-15 | 2016-06-16 | Cisco Technology, Inc. | Programmable processing engine for a virtual interface controller |
US10523796B2 (en) | 2015-12-22 | 2019-12-31 | Intel Corporation | Techniques for embedding fabric address information into locally-administered Ethernet media access control addresses (MACs) and a multi-node fabric system implementing the same |
CN106936939B (zh) * | 2015-12-31 | 2020-06-02 | 华为技术有限公司 | 一种报文处理方法、相关装置及nvo3网络系统 |
US10237090B2 (en) * | 2016-10-28 | 2019-03-19 | Avago Technologies International Sales Pte. Limited | Rule-based network identifier mapping |
CN109218178B (zh) * | 2017-07-05 | 2021-06-22 | 华为技术有限公司 | 一种报文处理方法及网络设备 |
US10412047B2 (en) | 2017-08-17 | 2019-09-10 | Arista Networks, Inc. | Method and system for network traffic steering towards a service device |
US10721651B2 (en) | 2017-09-29 | 2020-07-21 | Arista Networks, Inc. | Method and system for steering bidirectional network traffic to a same service device |
US10764234B2 (en) | 2017-10-31 | 2020-09-01 | Arista Networks, Inc. | Method and system for host discovery and tracking in a network using associations between hosts and tunnel end points |
US10778464B2 (en) * | 2018-04-20 | 2020-09-15 | Futurewei Technologies, Inc. | NSH encapsulation for traffic steering establishing a tunnel between virtual extensible local area network (VxLAN) tunnel end points (VTEPS) using a NSH encapsulation header comprising a VxLAN header whose VNI field has been replaced by an NSH shim |
US10917342B2 (en) | 2018-09-26 | 2021-02-09 | Arista Networks, Inc. | Method and system for propagating network traffic flows between end points based on service and priority policies |
US10855733B2 (en) | 2018-12-04 | 2020-12-01 | Arista Networks, Inc. | Method and system for inspecting unicast network traffic between end points residing within a same zone |
US10848457B2 (en) | 2018-12-04 | 2020-11-24 | Arista Networks, Inc. | Method and system for cross-zone network traffic between different zones using virtual network identifiers and virtual layer-2 broadcast domains |
US10749789B2 (en) * | 2018-12-04 | 2020-08-18 | Arista Networks, Inc. | Method and system for inspecting broadcast network traffic between end points residing within a same zone |
DE102021113670A1 (de) * | 2021-05-27 | 2022-12-01 | Dspace Gmbh | Verfahren zur Datenübertragung in einem Netzwerksystem sowie Netzwerksystem |
US20230164073A1 (en) * | 2021-11-23 | 2023-05-25 | Google Llc | Systems and Methods for Tunneling Network Traffic to Apply Network Functions |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011037104A1 (ja) * | 2009-09-24 | 2011-03-31 | 日本電気株式会社 | 仮想サーバ間通信識別システム、及び仮想サーバ間通信識別方法 |
JP2012191554A (ja) * | 2011-03-14 | 2012-10-04 | Ntt Data Corp | サーバ装置、パケット伝送システム、パケット伝送方法及びプログラム |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7606239B2 (en) * | 2003-01-31 | 2009-10-20 | Brocade Communications Systems, Inc. | Method and apparatus for providing virtual ports with attached virtual devices in a storage area network |
US8934486B2 (en) * | 2006-03-16 | 2015-01-13 | Cisco Technology, Inc. | System and method for implementing multicast over a label-switched core network |
US8036229B2 (en) * | 2007-10-08 | 2011-10-11 | Cisco Technology, Inc. | Switch with virtual network identifier re-write capability |
-
2014
- 2014-03-06 JP JP2015504375A patent/JP5991424B2/ja not_active Expired - Fee Related
- 2014-03-06 US US14/771,028 patent/US10237377B2/en not_active Expired - Fee Related
- 2014-03-06 WO PCT/JP2014/055744 patent/WO2014136864A1/ja active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011037104A1 (ja) * | 2009-09-24 | 2011-03-31 | 日本電気株式会社 | 仮想サーバ間通信識別システム、及び仮想サーバ間通信識別方法 |
JP2012191554A (ja) * | 2011-03-14 | 2012-10-04 | Ntt Data Corp | サーバ装置、パケット伝送システム、パケット伝送方法及びプログラム |
Non-Patent Citations (1)
Title |
---|
OPENFLOW MANAGEMENT AND CONFIGURATION PROTOCOL (OF-CONFIG 1.1, 25 June 2012 (2012-06-25) * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016134876A (ja) * | 2015-01-22 | 2016-07-25 | 富士通株式会社 | 情報処理システム、情報処理装置、および情報処理システムの制御方法 |
JP2016144144A (ja) * | 2015-02-04 | 2016-08-08 | 日本電信電話株式会社 | 負荷分散システム及び負荷分散方法 |
WO2016132262A1 (en) * | 2015-02-16 | 2016-08-25 | Telefonaktiebolaget Lm Ericsson (Publ) | Method and system for providing "anywhere access" for fixed broadband subscribers |
EP3280100A4 (en) * | 2015-03-31 | 2018-12-05 | Nec Corporation | Control device, control method, and program |
US10063470B2 (en) | 2015-05-12 | 2018-08-28 | Industrial Technology Research Institute | Data center network system based on software-defined network and packet forwarding method, address resolution method, routing controller thereof |
US11310655B2 (en) | 2015-06-10 | 2022-04-19 | Soracom, Inc. | Communication system and communication method for providing access to IP network to wireless cable |
CN107637029A (zh) * | 2015-06-10 | 2018-01-26 | 株式会社宙连 | 用于向无线终端提供对ip网络的访问的通信系统及通信方法 |
US12096517B2 (en) | 2015-06-10 | 2024-09-17 | Soracom, Inc. | Communication system and communication method for providing access to IP network to wireless terminals |
EP3310008A4 (en) * | 2015-06-10 | 2018-11-21 | Soracom, Inc. | Communication system and communication method for providing ip network access to wireless terminals |
CN113473651B (zh) * | 2015-06-10 | 2024-04-30 | 株式会社宙连 | 用于向无线终端提供对ip网络的访问的通信系统及通信方法 |
US11765571B2 (en) | 2015-06-10 | 2023-09-19 | Soracom, Inc. | Communication system and communication method for providing access to IP network to wireless terminals |
CN113473651A (zh) * | 2015-06-10 | 2021-10-01 | 株式会社宙连 | 用于向无线终端提供对ip网络的访问的通信系统及通信方法 |
JP2019514310A (ja) * | 2016-04-27 | 2019-05-30 | 新華三技術有限公司New H3C Technologies Co., Ltd. | パケット転送 |
US10547567B2 (en) | 2016-04-27 | 2020-01-28 | New H3C Technologies Co., Ltd | Packet forwarding |
US11330044B2 (en) | 2016-08-25 | 2022-05-10 | Nhn Entertainment Corporation | Method and system for processing load balancing using virtual switch in virtual network environment |
US11075981B2 (en) | 2016-08-25 | 2021-07-27 | Nhn Entertainment Corporation | Method and system for processing direct server return load balancing using loopback interface in virtual network environment |
JP2018033136A (ja) * | 2016-08-25 | 2018-03-01 | エヌエイチエヌ エンターテインメント コーポレーションNHN Entertainment Corporation | 仮想ネットワーク環境で仮想スイッチを利用してロードバランシングを処理する方法およびシステム |
Also Published As
Publication number | Publication date |
---|---|
JPWO2014136864A1 (ja) | 2017-02-16 |
US10237377B2 (en) | 2019-03-19 |
JP5991424B2 (ja) | 2016-09-14 |
US20160014241A1 (en) | 2016-01-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5991424B2 (ja) | パケット書換装置、制御装置、通信システム、パケット送信方法及びプログラム | |
US12021826B2 (en) | Techniques for managing software defined networking controller in-band communications in a data center network | |
US10320664B2 (en) | Cloud overlay for operations administration and management | |
US9215175B2 (en) | Computer system including controller and plurality of switches and communication method in computer system | |
US9577958B2 (en) | Method and apparatus for implementing communication between virtual machines | |
US10237177B2 (en) | Transfer device and transfer system | |
CN104580024B (zh) | 扩展的以太网互联结构交换机 | |
CN102857416B (zh) | 一种实现虚拟网络的方法、控制器和虚拟网络 | |
EP3197107B1 (en) | Message transmission method and apparatus | |
WO2016173271A1 (zh) | 报文处理方法、设备及系统 | |
US9491000B2 (en) | Data transport system, transmission method, and transport apparatus | |
JP6248938B2 (ja) | 通信システム、仮想ネットワーク管理装置、仮想ネットワークの管理方法及びプログラム | |
EP3069471B1 (en) | Optimized multicast routing in a clos-like network | |
JP6206508B2 (ja) | パケット転送装置、制御装置、通信システム、通信方法及びプログラム | |
EP2915315B1 (en) | Otv scaling using site virtual mac addresses | |
JP5860423B2 (ja) | キャリア網仮想化システム及び方法 | |
US20160277251A1 (en) | Communication system, virtual network management apparatus, communication node, communication method, and program | |
KR20160062688A (ko) | 오버레이 네트워크 기반에서의 오리지널 패킷 플로우 매핑 장치 및 그 방법 | |
JP2016103697A (ja) | ネットワークシステム、制御装置、通信装置、通信装置の制御方法及びプログラム | |
JP6264469B2 (ja) | 制御装置、通信システム及び中継装置の制御方法 | |
JP2016225933A (ja) | 制御装置、中継装置の制御方法、プログラム及び通信システム |
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: 14760818 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14771028 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 2015504375 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 14760818 Country of ref document: EP Kind code of ref document: A1 |