CN104333469B - A kind of storage system Fibre Channel conversation managing method and system - Google Patents
A kind of storage system Fibre Channel conversation managing method and system Download PDFInfo
- Publication number
- CN104333469B CN104333469B CN201410641039.1A CN201410641039A CN104333469B CN 104333469 B CN104333469 B CN 104333469B CN 201410641039 A CN201410641039 A CN 201410641039A CN 104333469 B CN104333469 B CN 104333469B
- Authority
- CN
- China
- Prior art keywords
- port
- node
- firmware
- drive module
- port information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 239000000835 fiber Substances 0.000 title claims abstract description 19
- 230000008859 change Effects 0.000 claims abstract description 46
- 239000013307 optical fiber Substances 0.000 claims abstract description 13
- 230000007246 mechanism Effects 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 9
- 239000003999 initiator Substances 0.000 claims description 33
- 230000004044 response Effects 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 9
- 230000001360 synchronised effect Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 6
- 230000000052 comparative effect Effects 0.000 claims description 4
- 238000011084 recovery Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 2
- RGNPBRKPHBKNKX-UHFFFAOYSA-N hexaflumuron Chemical compound C1=C(Cl)C(OC(F)(F)C(F)F)=C(Cl)C=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F RGNPBRKPHBKNKX-UHFFFAOYSA-N 0.000 abstract description 7
- 238000007726 management method Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000012217 deletion Methods 0.000 description 3
- 230000037430 deletion Effects 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Computer And Data Communications (AREA)
- Stored Programmes (AREA)
Abstract
The invention discloses a kind of storage system Fibre Channel conversation managing method and system, including：When storage system starts, initialization firmware Firmware and drive module, Firmware are established and are safeguarded first port information database, and drive module is established and safeguards second port information database；When Firmware or drive module detect equipment state change, node port information in Firmware renewal first port information databases, and notify drive module, node port information in the second port information database of drive module renewal drive module layer, and according to timing mechanism more new session and the processing to input and output I/O request.By the solution of the present invention, situations such as FCSAN topologies changes, optical fiber OIR, sonet card plug, FC networks extend can be heat-treated, it is not necessary to which stop doing business business, ensure that the continuity and reliability of data service.
Description
Technical field
The present invention relates to computer field of storage, more particularly to a kind of storage system Fibre Channel conversation managing method and
System.
Background technology
(Storage Area Network and SAN Protocols, write a Chinese character in simplified form SAN, i.e. memory block to storage area network
Domain network and its agreement) it is a kind of express network or sub-network, there is provided the data transfer between computer and storage system.Deposit
Storage equipment refers to one or more disk unit to storing computer data, is often referred to disk array.
The birth of storage area network, make memory space more fully utilized and installed and manage more added with
Effect.SAN is a kind of technology by storage device, connection equipment and Interface integration in an express network.SAN inherently one
Individual storage network, data storage task is assume responsibility for, SAN network is isolated with LAN business networks, and data storage stream will not take industry
Business network bandwidth.
Existing SAN technologies can be divided into IPSAN and FCSAN because realizing the difference of agreement.Wherein IPSAN passes through iSCSI
(i.e. Internet SCSI) agreement realizes that FCSAN passes through FCP (i.e. Fibre Channel Protocol, optical-fibre channel association
View) realize.FCSAN has transmission bandwidth high, stable and reliable for performance, safe, technology maturation, is compared in practical application
Universal enterprise data center's storage network standard, occupies critical role in high-end storage market.
But FCSAN is a dedicated network, is weak on scalability and ease for use.There is FCSAN point to arrive
Tri- kinds of point, ring and fabic topological structures, the different FC end equipments that can be directed to particular topology agreement optimize.But
FCSAN generally requires to stop data when processing topological structure thermal conversion, optical fiber card hot plug, optical fiber cable hot plug
Business, the topological structure converted could be applied by shutting down to restart, and the conversion of carry out topological structure and extension that can not be online.Therefore,
The present invention provides a kind of method, can support the online topological transformation and extension of storage system FC networks, reliable in time to safeguard more
New link session.
Session (session) is a unbroken request response sequence between client and server.To client's
Each request, server can recognize that request comes from same client.
The content of the invention
In order to solve the above problems, the present invention proposes a kind of storage system Fibre Channel conversation managing method and is
System, situations such as FCSAN topologies changes, optical fiber OIR, sonet card plug, FC networks extend can be heat-treated, it is not necessary to
Shutdown stops doing business business, ensure that the continuity and reliability of data service.
In order to achieve the above object, the present invention proposes a kind of storage system Fibre Channel conversation managing method, the party
Method includes：
When storage system starts, initialization firmware Firmware and drive module, Firmware are established and are safeguarded first end
Mouth information database, drive module are established and safeguard second port information database.
When Firmware and/or drive module detect equipment state change, Firmware renewal first port information
Node port information in database, and drive module is notified, the second port information database of drive module renewal driving layer
In node port information, and according to timing mechanism more new session and the processing to input and output I/O request.
Preferably, this method also includes：FC transport protocol entities use node-title Node-Name, port-title
Port-Name, port identities identification Port-ID mark node ports, using Port-ID as address, Target Board during communication
Target transport layer functionality is completed by FC Target device hardwares, Firmware and drive module.
Preferably, FC transport protocol entities are referred to using Node-Name, Port-Name, Port-ID mark node port：
When server host and the storage system establish session, Firmware and drive module record node port respectively
Node-Name, Port-Name, Port-ID are into first port information database and second port information database.
Preferably, Firmware or drive module detect that equipment state change refers to：Firmware detects Target Board
The equipment state change or drive module timing of Target ports are examined to the ADISC information that initiator Initiator ports are sent
Measure the equipment state change of Initiator ports.
Preferably, equipment state change refers to：FC connections between storage system and Initiator ports disconnect, recover,
Topologies change；Including：Port do not exchange in the case of disconnection or under recovery, point-to-point mode port connection exchange,
Port connection under fabic patterns is exchanged, the interchanger under fabic patterns is restarted, server host is restarted, server host and
The hardware state change of fibre channel host bus adapter FC-HBA cards, and optical-fibre channel storage area network FCSAN points
To the change of tri- kinds of point, ring and fabic topological structures.
Preferably, when Firmware detects the equipment state change of Target Board Target ports, method includes：If
Firmware detects that the FC connections of equipment disconnect, then I/O request all on drive module pause link.
When reach predetermined time-out time it is untreated when, drive module removes the session of the link, and removes the second end
Corresponding port information in mouth information database, Firmware synchronized update first port information databases.
When not up to predetermined time-out time, if Firmware detects FC, connection has recovered, and Firmware is first
By the port information of node port compared with the port information stored in first port information database, according to different ratios
Relatively result carries out different operations.
Preferably, different operations is carried out according to different comparative results to refer to：
If Node-Name, Port-Name, Port-ID and first port Information Number in the port information of node port
According to completely the same in storehouse, then predicate node port for original login and has not timed out port, then recovers the session, recover data
I/O request.
If Node-Name, Port-Name, Port-ID and first port Information Number in the port information of node port
According to inconsistent in storehouse, when Node-Name, Port-Name are consistent, then predicate node port has been changed, and Firmware deletes former
There is the port information of node port, re-establish new port information, and the replacing information of node port is notified into the driving
Module, drive module delete the port information of original node port from second port information database, re-establish new end
Message ceases, and deletes original session, establishes new session.
If Node-Name, Port-Name, Port-ID and first port Information Number in the port information of node port
According in storehouse completely it is inconsistent, then be determined as new port information, Firmware records new port information to first port information
In database, by notifying drive module, the new port information of drive module synchronized update is into second port information database.
Preferably, drive module timing to initiator Initiator ports send ADISC infomation detections to
During the equipment state change of Initiator ports, this method includes：The thread of drive module setting one sends and handled ADISC
Information, every a timing point, the information in second port information database in drive module, sent out to all node ports
ADISC information is sent, the node port for being successfully received its response message, is not processed；For in predetermined time-out time
The node port of its response message is inside not received by, or receives the node port of the response message of failure, record failure
Number, suspend I/O request；After Failure count reaches reservation threshold, drive module publishes the node port, deletion of node end
The session information of mouth, and delete the port information in second port information database, Firmware synchronized update first end messages
Cease database；If before the predetermined threshold of not up to Failure count, the response message of node port is successfully received, then
The Failure count is removed, recovers session and I/O request.
The present invention also proposes a kind of storage system Fibre Channel conversation management system, and the system includes：Initialization module,
Firmware Firmware and drive module.
Initialization module, for when storage system starts, initialization firmware Firmware and drive module.
Firmware, for first port information database to be established and safeguarded after initialization, when Firmware and/or driving
When module detects equipment state change, the node port information in Firmware renewal first port information databases, and lead to
Know drive module.
Drive module, for second port information database to be established and safeguarded after initialization, when Firmware and/or driving
When module detects equipment state change, Firmware notice is received, renewal drives the second port information database of layer, and
Handled according to timing mechanism more new session and input and output I/O request.
Preferably, the system also includes protocol entity module：For providing FC transport protocol entities for system, it uses section
Point-title Node-Name, port-title Port-Name, port identities identification Port-ID mark node ports, will during communication
The Port-ID is as address.
Preferably, Firmware is additionally operable to：When server host and storage system establish session, node port is recorded
Node-Name, Port-Name, Port-ID are into first port information database.
Drive module is additionally operable to：When server host and storage system establish session, the Node- of node port is recorded
Name, Port-Name, Port-ID are into second port information database.
Preferably, Firmware is additionally operable to：Detect the equipment state change of Target Board Target ports.
Drive module：It is additionally operable to the ADISC infomation detections Initiator that timing is sent to initiator Initiator ports
The equipment state change of port.
Compared with prior art, the present invention includes：When storage system starts, initialization firmware Firmware and driving mould
Block, Firmware are established and are safeguarded first port information database, and drive module is established and safeguards second port information database；
When Firmware or drive module detect equipment state change, the section in Firmware renewal first port information databases
Point port information, and drive module is notified, the node port in the second port information database of drive module renewal driving layer
Information, and according to timing mechanism more new session and the processing to input and output I/O request., can be at heat by the solution of the present invention
Situations such as managing FCSAN topologies changes, optical fiber OIR, sonet card plug, the extension of FC networks, it is not necessary to stop doing business business,
It ensure that the continuity and reliability of data service.
Brief description of the drawings
The accompanying drawing in the embodiment of the present invention is illustrated below, the accompanying drawing in embodiment is for entering one to the present invention
Step understands, is used to explain the present invention together with specification, does not form limiting the scope of the invention.
Fig. 1 is the storage system Fibre Channel conversation managing method flow chart of the present invention；
Fig. 2 is the storage system Fibre Channel conversation management system block diagram of the present invention.
Embodiment
For the ease of the understanding of those skilled in the art, the invention will be further described below in conjunction with the accompanying drawings, not
It can be used for limiting the scope of the invention.
Existing storage system software is in processing FCSAN topological structures conversion, sonet card plug, optical fiber OIR, FC nets
When network extension, it is on the premise of data service is stopped, changing its topological structure after shutdown, should after turning back on
With, online warm connection function is not carried out, results in the need for shutting down and interrupts data service, can traffic affecting continuation.This hair
It is bright to provide a kind of storage system software FC sessions High Availabitity management method, FCSAN topologies changes, optical fiber cable can be heat-treated
Situations such as plug, sonet card plug, extension of FC networks, it is not necessary to stop doing business business, ensure that the continuity of data service with can
By property.
Storage system software FC sessions High Availabitity management method provided by the invention, it is that providing a kind of storage system is based on
FC topologies changes and the High Availabitity treatment mechanism of immediate updating session：Including realizing a kind of timeout mechanism, management failure or
Useless fiber port, the invalid port information/session of timely recovery/deletion；And realize a kind of self-timing detection port shape
The mechanism of state, find that scanning changes to port status in time.Enable storage system be heat-treated FCSAN topologies changes,
Situations such as optical fiber OIR, sonet card plug, extension of FC networks, it is not necessary to which stop doing business business, ensure that the continuous of data service
Property and reliability.
Specifically, the present invention proposes a kind of storage system Fibre Channel conversation managing method, and this method includes following step
Suddenly：
When S101, storage system start, initialization firmware Firmware and drive module.
S102, Firmware are established and are safeguarded first port information database, and drive module is established and safeguards second port
Information database.
S103, Firmware and/or drive module detection device state change.
Preferably, Firmware or drive module detect that equipment state change refers to：Firmware detects Target Board
The equipment state change or drive module timing of Target ports are examined to the ADISC information that initiator Initiator ports are sent
Measure the equipment state change of Initiator ports.
Preferably, equipment state change refers to：FC connections between storage system and Initiator ports disconnect, recover,
Topologies change；Including：Port do not exchange in the case of disconnection or under recovery, point-to-point mode port connection exchange,
Port connection under fabic patterns is exchanged, the interchanger under fabic patterns is restarted, server host is restarted, server host and
The hardware state change of fibre channel host bus adapter FC-HBA cards, and optical-fibre channel storage area network FCSAN points
To the change of tri- kinds of point, ring and fabic topological structures.
Node port information in S104, Firmware renewal first port information database, and drive module is notified, drive
Node port information in the second port information database of dynamic model block renewal driving layer.
S105, drive module are according to timing mechanism more new session and the processing to input and output I/O request.
Preferably, this method also includes：FC transport protocol entities use node-title Node-Name, port-title
Port-Name, port identities identification Port-ID mark node ports, using the Port-ID as address, the mesh during communication
Target Target transport layer functionality is completed by FC Target device hardwares, the Firmware and the drive module.
Wherein, worldwide name WWN is the numbering of fibre channel host bus adapter FC HBA cards, and each optical fiber leads to
Road equipment has a unique mark, referred to as WWN (world wide name), is responsible for distribution by IEEE.WWN includes the whole world
Port name WWPN and global node title WWNN, the corresponding WWNN of an autonomous device that can not be split, a port pair
Answer a WWPN.Node-Name, Port-Name correspond to WWNN and WWPN respectively, and Port-ID is port numbers, to be driven when logging in
The unique identifying number that program assigns, Node-Name, Port-Name, Port-ID triplicity, the node port of unique mark one.
FC agreements are actually sonet card SCSI (Small Computer System Interface, miniature computer
Unite interface) agreement, FC Target correspond to SCSI destination end, and FC Initiator correspond to SCSI originating end.It is corresponding to be
FC HBA cards in storage system are FC Target ends, and the FC HBA cards on server are FC Initiator；
Firmware is exactly the program write in erasable read-only memory EROM or programmable read only memory EEPROM.
Firmware serves as the software of the most basic bottom work of a system.And in hardware device, firmware is exactly the spirit of hardware device
Soul, firmware are the bridges for connecting driver and hardware device, and driver is obtained and set hardware device state by firmware,
Hardware device informs driver state change, message informing etc. by firmware.
Firmware safeguards node port information storehouse, and driver also safeguards node port information database, when there is node
When port login is to Target, Firmware updates node port into information bank, and notifies to drive, and driver also updates it
Port information database.
Firmware internally updates port information when receiving port login, publishing and notifies to drive, and drives also more
The port information of new driving layer.
Preferably, FC transport protocol entities identify the node using described Node-Name, Port-Name, Port-ID
Port refers to：When server host and the storage system establish session, the Firmware and drive module difference
Node-Name, Port-Name, Port-ID of the node port are recorded to the first port information database and described
In Two-port netwerk information database.
Preferably, when the Firmware detects the equipment state change of Target Board Target ports, institute's this method
Including：If Firmware detects that the FC connections of equipment disconnect, all I/O requests on drive module pause link.
When reach predetermined time-out time it is untreated when, drive module removes the session of link, and removes second port letter
Cease corresponding port information in database, Firmware synchronized update first port information databases.
When not up to predetermined time-out time, if Firmware detects FC, connection has recovered, and Firmware is first
By the port information of node port compared with the port information stored in first port information database, according to different ratios
Relatively result carries out different operations.
Preferably, different operations is carried out according to different comparative results to refer to：
If Node-Name, Port-Name, Port-ID and first port Information Number in the port information of node port
According to completely the same in storehouse, then predicate node port for original login and has not timed out port, then recovers session, and the IO for recovering data please
Ask.
If Node-Name, Port-Name, Port-ID and first port Information Number in the port information of node port
According to inconsistent in storehouse, when Node-Name, Port-Name are consistent, then predicate node port has been changed, and Firmware deletes former
There is the port information of node port, re-establish new port information, and the replacing information of node port is notified into drive module,
Drive module deletes the port information of original node port from second port information database, re-establishes new port letter
Breath, and original session is deleted, establish new session.
If Node-Name, Port-Name, Port-ID and first port Information Number in the port information of node port
According in storehouse completely it is inconsistent, then be determined as new port information, Firmware records new port information to first port information
In database, by notifying drive module, the new port information of drive module synchronized update is into second port information database.
Preferably, drive module timing to initiator Initiator ports send ADISC infomation detections to
During the equipment state change of Initiator ports, this method includes：The thread of drive module setting one sends and handled ADISC
Information, every a timing point, the information in second port information database in drive module, sent out to all node ports
ADISC information is sent, the node port for being successfully received its response message, is not processed；For in predetermined time-out time
The node port of its response message is inside not received by, or receives the node port of the response message of failure, record failure
Number, suspend I/O request；After Failure count reaches reservation threshold, drive module publishes node port, deletion of node port
Session information, and delete the port information in second port information database, Firmware synchronized update first port Information Numbers
According to storehouse；If before the predetermined threshold of not up to Failure count, the response message of node port is successfully received, then described in removing
Failure count, recover session and I/O request.
The present invention also proposes a kind of storage system Fibre Channel conversation management system 01, and the system includes：Initialize mould
Block 02, firmware Firmware03 and drive module 04.
Initialization module 02, for when storage system starts, initialization firmware Firmware and drive module.
Firmware03, for first port information database to be established and safeguarded after initialization, when Firmware03 or drive
When dynamic model block 04 detects equipment state change, the node side message in Firmware03 renewal first port information databases
Breath, and notify drive module.
Drive module 04, for second port information database to be established and safeguarded after initialization, when Firmware03 or drive
When dynamic model block 04 detects equipment state change, Firmware03 notice, the second port Information Number of renewal driving layer are received
Handled according to storehouse, and according to timing mechanism more new session and input and output I/O request.
Preferably, the system 01 also includes protocol entity module 05：For providing FC transport protocol entities for system, it makes
With node-title Node-Name, port-title Port-Name, port identities identification Port-ID mark node ports, communication
When using Port-ID as address.
Preferably, Firmware03 is additionally operable to：When server host and storage system establish session, node port is recorded
Node-Name, Port-Name, Port-ID into first port information database.
Drive module 04 is additionally operable to：When server host and the storage system establish session, node port is recorded
Node-Name, Port-Name, Port-ID are into second port information database.
Preferably, Firmware03 is additionally operable to：Detect the equipment state change of Target Board Target ports.
Drive module 04：It is additionally operable to the ADISC infomation detections that timing is sent to initiator Initiator ports
The equipment state change of Initiator ports.
From embodiments of the present invention, the technical scheme is that by Firmware layers and driver layer
Port information database is established, with (Node-Name, Port-Name, Port-ID) ternary usually unique mark port information, is led to
Cross and actively and passively detect, to obtain FCSAN topological environmental modification informations, and according to the analyzing and processing to information, to realize
Timely, accurate, the reliable renewal of session in storage system software.So as to ensure that the continuity of data service, enhance
FCSAN scalability and ease for use, it ensure that the stabilization and safety of data.Realize a kind of storage system FC session High Availabitities
Management method.
Compared with prior art, the invention provides a kind of more reliable, more reasonably storage system FC conversation managing methods,
The continuity of data service can be kept.The invention is applied to tri- kinds of FCSAN point-to-points, ring and fabic topological structures, by these three
Structure change and many topologies changes, the processing of two class situations is abstracted as, one kind is that Firmware detects that Target ends are set
Standby state change, one kind are that timing sends ADISC to detect Initiator end equipment state changes.By establishing driver
Port information database and Firmware port informations storehouse, to safeguard the change of all of the port information and management.Greatly improve
FCSAN scalability and ease for use, avoid when topological environmental changes caused by artificial or other reasonses, business may be caused
Data loss problem, there is provided FCSAN reliability.
It should be noted that embodiment described above be for only for ease of it will be understood by those skilled in the art that, and
It is not used in and limits the scope of the invention, on the premise of the inventive concept of the present invention is not departed from, those skilled in the art couple
Any obvious replacement and improvement that the present invention is made etc. is within protection scope of the present invention.
Claims (12)
1. a kind of storage system Fibre Channel conversation managing method, it is characterised in that methods described includes：
When storage system starts, initialization firmware Firmware and drive module, the Firmware are established and are safeguarded first end
Mouth information database, the drive module are established and safeguard second port information database；
When the Firmware and/or the drive module detect equipment state change, described in the Firmware renewals
Node port information in first port information database, and the drive module is notified, the drive module renewal driving layer
The second port information database in the node port information, and according to timing mechanism more new session and to input it is defeated
Go out the processing of I/O request.
2. the method as described in claim 1, it is characterised in that methods described also includes：FC transport protocol entities using node-
Title Node-Name, port-title Port-Name, port identities identification Port-ID mark node ports, during communication will described in
Port-ID is as address, and Target Board Target transport layer functionality is by FC Target device hardwares, the Firmware and institute
Drive module is stated to complete.
3. method as claimed in claim 2, it is characterised in that the FC transport protocol entities using the Node-Name,
Port-Name, Port-ID identify the node port and referred to：When server host and the storage system establish session, institute
State Firmware and the drive module records Node-Name, Port-Name, Port-ID of the node port to institute respectively
State in first port information database and the second port information database.
4. method as claimed in claim 3, it is characterised in that the Firmware or described drive modules detect equipment shape
State change refers to：The Firmware detects the equipment state change or drive module timing of Target Board Target ports
Equipment state to the ADISC infomation detections that initiator Initiator ports are sent to Initiator ports changes.
5. method as claimed in claim 4, it is characterised in that the equipment state change refers to：The storage system and institute
The FC connections between Initiator ports are stated to disconnect, recover, topologies change；Including：Port do not exchange in the case of disconnection
Or the port connection under recovery, point-to-point mode exchanges, the port connection under fabic patterns exchanges, the exchange under fabic patterns
Machine is restarted, server host is restarted, the hardware state of server host and fibre channel host bus adapter FC-HBA cards becomes
Change, and optical-fibre channel storage area network FCSAN point-to-points, the change of tri- kinds of topological structures of ring and fabic.
6. method as claimed in claim 4, it is characterised in that when the Firmware detects Target Board Target ports
When equipment state changes, methods described includes：If the Firmware detects that the FC connections of equipment disconnect, the driving
All I/O requests on module pause link；
When reach predetermined time-out time it is untreated when, the drive module removes the session of the link, and removes described the
Corresponding port information in Two-port netwerk information database, first port information database described in the Firmware synchronized updates；
When the not up to predetermined time-out time, if the Firmware detects that the FC connections have recovered, institute
Firmware is stated first to carry out the port information stored in the port information of node port and the first port information database
Compare, different operations is carried out according to different comparative results.
7. method as claimed in claim 6, it is characterised in that described different operations is carried out according to different comparative result to be
Refer to：
If described Node-Name, Port-Name, Port-ID and the first end in the port information of the node port
It is completely the same in mouth information database, then the node port is judged for original login and has not timed out port, then recovers the meeting
Words, recover the I/O request of data；
If described Node-Name, Port-Name, Port-ID and the first end in the port information of the node port
It is inconsistent in mouth information database, when described Node-Name, Port-Name are consistent, then judge the node port more
Changing, the Firmware deletes the port information of original node port, re-establishes new port information, and by the node side
The replacing information of mouth notifies the drive module, and the drive module deletes original section from the second port information database
The port information of point port, re-establishes new port information, and deletes original session, establishes new session；
If described Node-Name, Port-Name, Port-ID and the first end in the port information of the node port
It is completely inconsistent in mouth information database, then it is determined as new port information, the Firmware records the new port letter
Cease in the first port information database, it is new described in the drive module synchronized update by notifying the drive module
Port information into the second port information database.
8. method as claimed in claim 4, it is characterised in that the drive module is regularly to initiator Initiator ports
The ADISC infomation detections of transmission to Initiator ports equipment state change when, methods described includes：The drive module
One thread is set to send and handle the ADISC information, every a timing point, described second in the drive module
Information in port information database, the ADISC information is sent to all node ports, believed for being successfully received its response
The node port of breath, is not processed；Node port for being not received by its response message in predetermined time-out time, or
Person receives the node port of the response message of failure, records Failure count, suspends I/O request；When the Failure count reaches pre-
After determining threshold value, the drive module publishes the node port, deletes the session information of the node port, and deletes described
Port information in Two-port netwerk information database, first port information database described in the Firmware synchronized updates；If
Before the predetermined threshold of not up to described Failure count, the response message of node port is successfully received, then described in removing
Failure count, recover session and I/O request.
9. a kind of storage system Fibre Channel conversation management system, it is characterised in that the system includes：Initialization module,
Firmware Firmware and drive module；
The initialization module, for when storage system starts, initializing the firmware Firmware and the drive module；
The Firmware, for first port information database to be established and safeguarded after initialization, as the Firmware and/or
When the drive module detects equipment state change, the Firmware updates the section in the first port information database
Point port information, and notify the drive module；
The drive module, for second port information database to be established and safeguarded after initialization, as the Firmware and/or
When the drive module detects equipment state change, the notice of the Firmware is received, renewal drives described the second of layer
Port information database, and handled according to timing mechanism more new session and input and output I/O request.
10. system as claimed in claim 9, it is characterised in that the system also includes protocol entity module：For to be described
System provides FC transport protocol entities, and it is known using node-title Node-Name, port-title Port-Name, port identities
Other Port-ID identifies node port, using the Port-ID as address during communication.
11. system as claimed in claim 10, it is characterised in that the Firmware is additionally operable to：In server host and institute
When stating storage system and establishing session, Node-Name, Port-Name, Port-ID of the node port are recorded to described first
In port information database；
The drive module is additionally operable to：When server host and the storage system establish session, the node port is recorded
Node-Name, Port-Name, Port-ID into the second port information database.
12. system as claimed in claim 9, it is characterised in that the Firmware is additionally operable to：Detect Target Board Target ends
The equipment state change of mouth；
The drive module：It is additionally operable to the ADISC infomation detections Initiator that timing is sent to initiator Initiator ports
The equipment state change of port.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410641039.1A CN104333469B (en) | 2014-11-13 | 2014-11-13 | A kind of storage system Fibre Channel conversation managing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410641039.1A CN104333469B (en) | 2014-11-13 | 2014-11-13 | A kind of storage system Fibre Channel conversation managing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104333469A CN104333469A (en) | 2015-02-04 |
| CN104333469B true CN104333469B (en) | 2018-02-27 |
Family
ID=52408128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410641039.1A Active CN104333469B (en) | 2014-11-13 | 2014-11-13 | A kind of storage system Fibre Channel conversation managing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104333469B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10509706B2 (en) * | 2017-09-14 | 2019-12-17 | Hewlett Packard Enterprise Development Lp | Identification of an alternate principal member port by a target device in a storage area network |
| CN108512706A (en) * | 2018-04-16 | 2018-09-07 | 郑州云海信息技术有限公司 | A kind of HBA card failures processing method, system, medium and equipment |
| CN110377800B (en) * | 2019-06-28 | 2022-02-18 | 苏州浪潮智能科技有限公司 | FC chip data sending method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101945310A (en) * | 2010-09-16 | 2011-01-12 | 中兴通讯股份有限公司 | Method for reporting capacity of ONU port in real time and ONU |
| CN103414597A (en) * | 2013-08-30 | 2013-11-27 | 上海寰创通信科技股份有限公司 | Status updating system and status updating method of logical ports |
| CN103777895A (en) * | 2012-10-18 | 2014-05-07 | 株式会社日立制作所 | Method and apparatus of storage volume migration in cooperation with takeover of storage area network configuration |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7404012B2 (en) * | 2002-05-06 | 2008-07-22 | Qlogic, Corporation | System and method for dynamic link aggregation in a shared I/O subsystem |
| CN102044792A (en) * | 2009-10-23 | 2011-05-04 | 鸿富锦精密工业（深圳）有限公司 | Socket device |
-
2014
- 2014-11-13 CN CN201410641039.1A patent/CN104333469B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101945310A (en) * | 2010-09-16 | 2011-01-12 | 中兴通讯股份有限公司 | Method for reporting capacity of ONU port in real time and ONU |
| CN103777895A (en) * | 2012-10-18 | 2014-05-07 | 株式会社日立制作所 | Method and apparatus of storage volume migration in cooperation with takeover of storage area network configuration |
| CN103414597A (en) * | 2013-08-30 | 2013-11-27 | 上海寰创通信科技股份有限公司 | Status updating system and status updating method of logical ports |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104333469A (en) | 2015-02-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10986171B2 (en) | Method for unified communication of server, baseboard management controller, and server | |
| EP3235199B1 (en) | Multicast advertisement message for a network switch in a storage area network | |
| US8171170B2 (en) | Storage switch task processing synchronization | |
| CN100414542C (en) | System and method for managing memory source in cluster computer system | |
| WO2018045860A1 (en) | File system mounting method, apparatus and equipment | |
| US9983813B2 (en) | Maintenance of a fabric priority during synchronous copy operations | |
| US20080089336A1 (en) | Location of a probe algorithm | |
| JP2007257180A (en) | Network node, switch, and network fault recovery method | |
| CN104333469B (en) | A kind of storage system Fibre Channel conversation managing method and system | |
| CN114598735B (en) | Data processing method and system | |
| US20180048704A1 (en) | Network Device Clusters | |
| CN109547875A (en) | A kind of FC exchange network arbitrary port access design method | |
| WO2021098425A1 (en) | Qos policy method, device, and computing device for service configuration | |
| CN105025063A (en) | Online data transmission method for large-scale terminal equipment | |
| US10659348B2 (en) | Holding of a link in an optical interface by a lower level processor until authorization is received from an upper level processor | |
| CN103207801A (en) | Method, device and system for migrating virtual machine and fiber channel switch | |
| CN101621526B (en) | iSCSI method and apparatus for preventing useless connection from occupying system resources | |
| US20080101236A1 (en) | Storage system and communication bandwidth control method | |
| US9614910B2 (en) | Maintenance of a fabric priority among operations in related fibre channel exchanges | |
| CN105763599B (en) | T-CDP implementation method and device under a kind of IPSAN | |
| CN104081728B (en) | Network management | |
| US9071544B2 (en) | Method and system for managing network elements | |
| CN101076012B (en) | Date telecommunication system and method and interface controller of Internet microcomputer system | |
| CN108259228B (en) | Network equipment virtualization system and equipment configuration method and device thereof | |
| CN109039680B (en) | Method and system for switching main Broadband Network Gateway (BNG) and standby BNG and BNG |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |