WO2008075425A1 - 通信処理プログラム、通信処理方法および通信処理装置 - Google Patents
通信処理プログラム、通信処理方法および通信処理装置 Download PDFInfo
- Publication number
- WO2008075425A1 WO2008075425A1 PCT/JP2006/325429 JP2006325429W WO2008075425A1 WO 2008075425 A1 WO2008075425 A1 WO 2008075425A1 JP 2006325429 W JP2006325429 W JP 2006325429W WO 2008075425 A1 WO2008075425 A1 WO 2008075425A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- fiber channel
- driver
- izo
- target
- communication processing
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/2002—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where interconnections or communication control functionality are redundant
- G06F11/2007—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where interconnections or communication control functionality are redundant using redundant communication media
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/2002—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where interconnections or communication control functionality are redundant
- G06F11/2005—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where interconnections or communication control functionality are redundant using redundant communication controllers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/14—Handling requests for interconnection or transfer
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0614—Improving the reliability of storage systems
- G06F3/0617—Improving the reliability of storage systems in relation to availability
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0629—Configuration or reconfiguration of storage systems
- G06F3/0635—Configuration or reconfiguration of storage systems by changing the path, e.g. traffic rerouting, path reconfiguration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0683—Plurality of storage devices
- G06F3/0689—Disk arrays, e.g. RAID, JBOD
Definitions
- the present invention relates to a communication processing program, a communication processing method, and a communication processing device, and in particular, a communication processing program and a communication processing method used for a server connected to a disk array device through a plurality of paths via a fiber channel adapter. And a communication processing apparatus.
- Fiber Channel used mainly for servers that require high performance
- Fiber Channel uses high-speed data transfer over long distances up to a maximum transmission distance of 10 kilometers, using an optical fiber or coaxial cable with a maximum transfer speed of 200 megabytes per second for connection.
- FIG. 27 is a diagram showing a fiber channel configuration between general server disk array devices.
- the server 700 is connected to the disk array device 900 via the force switches 800a and 800b.
- the communication control related to the disk IZO requested by the application 710 is controlled on the server 700 by controlling the communication path between the server 700 and the disk array device 900.
- ⁇ Multipath control software 720, and the actual disk array This is performed by fiber channel drivers 740a and 740b that control the fiber channel adapters 730a and 730b that communicate with the device 900.
- the Fiber Channel drivers 740a and 740b receive an IZO issue request from the higher-level target drivers 750a and 750b, respectively, manage the IZO issue request (SCSI level), and send it to the disk array device 900 via Fiber Channel communication. Manages issuance issue information for publishing IZO (bre Channel communication FC—PH layer).
- IZO Tin Channel communication FC—PH layer
- FIG. 28 is a diagram showing a conventional process.
- FIG. 28 shows the case where one connection path is used.
- the Fiber Channel driver 740a when the Fiber Channel driver 740a receives an IZO stop request (abort) from the upper target driver 750a, it issues an I / O stop request to the disk array device 900, Wait for response (ACC) for ⁇ ⁇ ⁇ stop request response waiting time. If there is no response by the failure of the disk array system 900 or connection path failure until the response wait time for the ⁇ stop request elapses, ⁇ will be notified to the upper level as an error. Since an error cannot be returned and a response is expected to be returned with a delay due to the transmission line delay, the exchange issuance information is managed for the waiting time considering the transmission line delay, and the time has elapsed. Then, iZo is notified to the host as an error. For this reason, it takes a lot of time to switch the route at the time of error (route switching). In addition, the waiting time of iZo issued by application 710 also increases.
- FIG. 29 is a diagram showing another conventional process.
- Patent Document 1 Japanese Patent Laid-Open No. 6-110800
- the management time of the IZO issue request in the fiber channel driver 740a can be shortened.
- the ⁇ issued to the Fiber Channel communication path secures the ID (OX-ID, etc.) for Fiber Channel communication used for ⁇ issuance. It is necessary to keep it.
- the fiber channel driver 740a manages the exchange issuance information (FC-P) during the waiting time for the IZO stop request response waiting time and the transmission path delay.
- the disk array device 900 may be repeatedly retried. For example, when a failure occurs between paths, However, there is a problem that the same processing is repeated and the path switching time is delayed.
- the present invention has been made in view of these points, and an object of the present invention is to provide a communication processing program, a communication processing method, and a communication processing device capable of quickly switching paths.
- a communication processing program for causing a computer (sano) 1 to execute processing as shown in FIG. 1 is provided.
- the communication processing program according to the present invention is a program used for a computer 1 that includes a fiber channel adapter 2 and is connected to the disk array device 3 via the fiber channel adapter 2 through a plurality of paths 4a and 4b.
- the computer 1 that executes the communication processing program has the following functions.
- the route control means 5 controls the plurality of routes 4a and 4b and switches the route upon receiving an error notification.
- the target driver 6 issues an IZO stop request to the disk array device 3 in response to the path connection timeout detection of the path control means 5. When an error notification is received, it is output to the route control means 5.
- the Fiber Channel driver 7 controls the Fiber Channel adapter 2, and when the target driver 6 issues a ⁇ stop request, all processing for the disk array device 3 is closed and an error notification is sent to the target driver. Output to 6 ( ⁇ stop processing).
- the target driver 6 issues a habit stop request to the disk array device 3 in response to the path connection timeout detection of the path control means 5.
- a stop request is issued by the target driver 6 by the fiber channel driver 7, all processing for the disk array device 3 is blocked and an error notification is output to the target driver 6.
- the target driver 6 outputs an error notification to the route control means 5.
- the route is switched by the route control means 5 that has received the error notification.
- the fiber channel driver when the path control unit detects a timeout and issues a habit stop request, the fiber channel driver performs the process of putting all the processes into the blocked state for the target disk array. As a result, the error notification can be immediately returned from the Fiber Channel driver to the target driver. Therefore, error notification to the route control means can be performed in a short time. As a result, the route control means can quickly change the route.
- FIG. 1 is a diagram showing an outline of the present invention.
- FIG. 2 is a block diagram showing a communication processing system according to the embodiment.
- FIG. 3 is a diagram illustrating a hardware configuration example of a server. 4] server and c is a block diagram showing the function of the disk array device
- FIG. 5 is a diagram for explaining processing of the FC driver.
- FIG. 6 is a flowchart showing the FC driver switching process.
- FIG. 7 is a sequence diagram showing processing of the FC driver.
- FIG. 8 is a diagram showing an X ID management table.
- FIG. 10 is a flowchart showing process B--1.
- FIG. 12 is a flowchart showing process B--2.
- FIG. 16 is a flowchart showing process C-2.
- FIG. 17 is a flowchart showing process C--3.
- FIG. 18 is a flowchart showing process B--3.
- FIG. 19 is a flowchart showing process C--1.
- FIG. 21 is a flowchart showing the blocking process of the FC driver according to the second embodiment.
- FIG. 22 is a sequence diagram showing processing of the FC driver according to the second embodiment.
- FIG. 23 is a flowchart showing process a-3.
- FIG. 24 is a flowchart showing process c2.
- FIG. 25 is a flowchart showing process c3.
- FIG. 26 is a flowchart showing process c1.
- FIG. 27 is a diagram showing a fiber channel configuration between general server disk array devices.
- FIG. 28 is a diagram showing conventional processing.
- FIG. 29 is a diagram showing another conventional process.
- FIG. 1 is a diagram showing an outline of the present invention.
- a computer 1 shown in FIG. 1 includes a fiber channel adapter 2 for performing fiber channel connection, and is connected to the disk array device 3 through the fiber channel adapter 2 through a plurality of paths 4a and 4b. .
- the computer 1 includes a path control means 5, a target driver 6, and a fiber channel driver 7 in addition to the fiber channel adapter 2.
- the route control means 5 controls the plurality of routes 4a and 4b and switches the route upon receiving an error notification. Specifically, when data is transmitted / received to / from the disk array device 3 using the path 4a, the data transfer path is switched to the path 4b in response to an error notification. If data is exchanged with the disk array device 3 using the path 4b, an error notification is received and the data transfer path is switched to the path 4a.
- the target driver 6 issues an IZO stop request to the disk array apparatus 3 in response to the path connection timeout detection of the path control means 5.
- the timeout of the route connection for example, when a failure occurs in the disk array device 3, or when a failure occurs in the route 4a or the route 4b performing data transmission / reception.
- an error notification is received from the fiber channel driver 7, it is output to the route control means 5.
- the fiber channel driver 7 controls the fiber channel adapter 2 and mainly has a function of managing exchange issuance (Exc) and a function of managing IZO issuance information.
- the target driver 6 issues an I / O stop request
- the fiber channel driver 7 puts all processing for the disk array device 3 in a blocked state and outputs an error notification to the target driver 6. In this case, an error notification is returned for the ⁇ issue request from the host, and the response from the disk array device 3 is ignored.
- the target driver 6 issues a habit stop request to the disk array device 3 in response to the path connection timeout detection of the path control means 5.
- Stop required by fiber channel driver 7 and target driver 6 When a request is issued, all processing for the disk array device 3 is blocked and an error notification is output to the target driver 6. Then, the target driver 6 outputs an error notification to the route control means 5. The route is switched by the route control means 5 that has received the error notification. Therefore, the IZO standby time of computer 1 is reduced.
- FIG. 2 is a block diagram illustrating the communication processing system according to the embodiment.
- a server (communication processing device) 100 and a disk array device 300 are connected via a switch (fiber channel switch) 200a and a switch 200b.
- the disk array apparatus 300 has one or a plurality of disk arrays (disk array 301 in FIG. 2), and receives and stores data from the server 100.
- the route from the server 100 to the disk array device 300 via the switch 200a is the first route (main route), and the route from the server 100 to the disk array device 300 via the switch 200b Is the second route (redundant route), and if one of the routes fails, the server 100 switches to the other route and operates the system.
- FIG. 3 is a diagram illustrating a hardware configuration example of the server.
- the entire server 100 is controlled by a CPU (Central Processing Unit) 101.
- the CPU 101 is connected to a RAM (Random Access Memory) 102, a hard disk drive (HDD) 103, a graphics processing device 104, an input interface 105, a communication interface 106, and an FC (F3 ⁇ 4re Channel) via a bus 107.
- Adapters 10 8a and 108b are connected.
- the RAM 102 temporarily stores at least part of an OS (Operating System) program application program to be executed by the CPU 101.
- the RAM 102 stores various data necessary for processing by the CPU 101.
- the HDD 103 stores the OS and application programs.
- a program file is stored in the HDD 103.
- a monitor 11 is connected to the graphic processing device 104.
- the graphic processing device 104 displays an image on the screen of the monitor 11 in accordance with a command from the CPU 101.
- a keyboard 12 and a mouse 13 are connected to the input counter face 105.
- Input interface The CPU 105 transmits a signal sent from the keyboard 12 or the mouse 13 to the CPU 101 via the bus 107.
- the communication interface 106 is connected to the network 10.
- the communication interface 106 transmits / receives data to / from other computers via the network 10.
- FC adapters 108a and 108b constitute the connection portions of signal transmission cables connected to the switches 200a and 200b, respectively.
- FIG. 4 is a block diagram illustrating functions of the server and the disk array device
- FIG. 5 is a diagram illustrating processing of the FC driver.
- the functional blocks are indicated by dotted lines.
- the server 100 has an application 110, an IZO multipath controller 120, target drains 130a and 130b, and FC (Fibre Channel) drivers 140a and 140b.
- the application 110 is an application used by a user, for example, and outputs a communication control request (IZO issue request) regarding IZO with the disk array 301.
- IZO issue request a communication control request regarding IZO with the disk array 301.
- the IZO multipath control unit 120 controls a communication path between the server 100 and the disk array device 300. Specifically, the status of the connection path between the server 100 and the disk array device 300 is grasped, and the soot issue request received from the application 110 is issued through an appropriate path. The abnormality of each route is determined by whether or not an issue request issued to the lower layer that manages connection with each route is notified (response).
- the target drivers 130a and 130b issue and manage I / O processing requests to the disk array 301, respectively.
- the FC drivers 140a and 140b mainly have a function of managing I / O issuance requests and a function of managing exchange issuance.
- the FC drivers 140a and 140b control the FC adapters 108a and 108b that actually communicate with the disk array device 300, respectively, and perform communication processing with the disk array device 300 when a ⁇ / O issuance request is received. Do. This The communication process is performed by the following method.
- FC dryers 140a and 140b internally issue an X-ID (exchange ID), which is an ID for identifying one operation consisting of a group of sequences for each adapter port.
- X-ID exchange ID
- OX—ID X for sending X—ID
- RX—ID for receiving X_ID
- the FC dryinos 140a and 140b set the issued X-ID to OX-ID and issue IZO (command, address, etc.) on the FC transmission line.
- OX—ID When the disk array device 300 receives OX—ID, it sets X—ID (RX—ID) independently and responds.
- the FC drivers 140a and 140b issue the IZO using the X-ID that responds from the following as the RX_ID. Exchanges are managed by a combination of these OX_ID—R X—IDs.
- X—ID (OX—ID, RX—ID) is released at the end of the exchange or after an I / O stop request (abort) is issued and after a predetermined time (10 seconds under FC rules). . If this condition is not met and the X-ID being used is duplicated, the disk array device 300 side will not be guaranteed to change.
- the disk array device 300 includes controllers 310a and 310b that control the disk array 301 in response to IZO issuance from the server 100 side.
- the controller 310a corresponds to the main route
- the controller 310b corresponds to the redundant route.
- the disk array device 300 receives the IZO issued via the controllers 310a and 310b and returns the corresponding data to the servo 100.
- the FC drivers 140a and 140b perform the following processing when there is an IZO stop request from the target drivers 130a and 130b, respectively.
- FIG. 6 is a flowchart showing FC driver switching processing.
- the adapter port to be blocked (stopped) of the FC adapter 108a is determined (step Sl).
- the adapter port to be blocked depends on the request. [0049] (l) In the case of abort in lZO units, the adapter port for which the I / O is issued is set as the adapter port to be blocked. (2) If the disk array device is aborted in units of 300, the adapter port that is issued by the IZO is the adapter port that is to be blocked. (3) Disk array (target) In the case of abort in 301 units, the adapter port to which the I / O is issued is the adapter port to be blocked.
- a LINK DOWN instruction is issued to the adapter port to be blocked, and the link with the fiber channel transmission line is disconnected to stop the fiber channel communication (step S2).
- all IZO issued and scheduled to be issued from the adapter port to be blocked are unconditionally returned to the target driver 130a with an error, and the management (SCSI level) information of the IZO issue request is deleted (step S3).
- the IO multipath controller 120 starts switching the route.
- step S4 the exchange issuance information (FC—layer) for fiber channel communication related to the IZO returned to the target driver 130a is deleted (step S4).
- a timer for operating a certain time (for example, 60 to 180 seconds or manually canceling by a command) is operated and waits for a predetermined time (Step S5).
- a timer for example, 60 to 180 seconds or manually canceling by a command
- the timer is running, even if an IZO issue request is received from the target driver 130a to the adapter port that is the IZO issue target of the FC dry 140a, it will not be accepted and will respond immediately with an error (blocking process).
- the FC communication path since the communication path is linked down, the FC communication path also does not transmit the response regarding the adapter port that is the IZO issue target of the FC driver 140a.
- the adapter port LINK UP process is performed to release the blocking process and connect the link (step S6).
- the exchange issuance information (FC-PH layer) for Fiber Channel communication is immediately deleted without the need for management because all responses from the disk array device 300 are discarded.
- the IZO issue request (SCSI level) from the target driver 130a so an error can be returned immediately. Therefore, the multipath control unit 120 can switch the route quickly, and the waiting time of the IZO issued by the application 110 is reduced.
- the FC driver 140a Even if the upper IZO multipath control unit 120 or target driver 130a performs a retry, the FC driver 140a is not in communication with the disk array device 300, so it immediately returns an error notification, which is useless. Can be prevented.
- FIG. 7 is a sequence diagram showing processing of the FC driver.
- the FC driver 140a includes an IZO issue request management unit 141a, an exchange issue information management unit 142a, an FC connection management unit 143a, and an X-ID management unit 144a.
- the IZO issue request management unit 141a In response to the I / O issue request from the target driver 130a, the IZO issue request management unit 141a requests appropriate processing from the other part of the FC driver 140a. Then, it responds to the target driver 130a as necessary. It also manages timers (described later).
- the exchange issuance information management unit 142a receives an I / O issuance request, attempts to connect to the controller 310a, and issues an I / O to the controller 310a.
- the FC connection management unit 143a has a connectable target list for managing the connection state with the controller 310a (force or failure when connected to the controller 310a).
- the X-ID management unit 144a has an X-ID management table for managing X-IDs.
- FIG. 8 shows the X-ID management table.
- the X—ID management table Tal has columns for X—ID and usage status, and the information arranged in the horizontal direction of each column is associated with each other.
- a PKT address is set for the X—ID being used, and NULL is set for the unused X—ID.
- Fig. 7 The symbols and numbers in Fig. 7 are provided to identify the processing contents and indicate the exchange of information of each part. Further, the processing in FIG. 7 is performed in time series.
- target driver 130a (hereinafter also referred to as “upper”) is a request for higher power IZO issuance request, ( ⁇ ) is an IZO abort request from higher, ( ⁇ ) issuance of re-I / O from higher
- FC driver 140a has different processing depending on each request I do.
- the IZO issue request management unit 141a performs different processes (processes A-1 to A-3) according to each request, and the exchange issue information management unit 142a performs different processes (processes) according to each request.
- Perform processing Processing D-1 to D-2).
- process B-1 is executed as a result of process A-1.
- process B-1 is executed as a result of process A-1.
- ⁇ issue request management unit 141a performs process A-1
- process change issue information management unit 142a performs process B-1
- X- ID management unit 144a performs process D--.
- This issues an IZO to the controller 310a. If there is an IZO response from the controller 310a, the exchange issuance information management unit 142a performs processing B-2, the IZO issuance request management unit 141a performs processing A-2, and the X-ID management unit 144a performs processing D. — Do two. This returns a response to the upper level.
- FIG. 9 is a flowchart showing the process A-1.
- a process name for example, “B-1” in FIG. 9) is assigned near the step that triggers the next process.
- processing ⁇ -1 is performed.
- processing ⁇ —1 is completed.
- FIG. 10 is a flowchart showing the process B-1.
- step S21 when an IZO issue request is received from the IZO issue request management unit 141a (step S21), it is determined whether or not the controller (device to be issued) 310a exists in the connectable target list (step S22).
- step S22 When the controller 310a exists in the connectable target list (Yes in step S22), the X_ID management unit 144a is requested for X_ID (step S23). As a result, process D-1 is performed.
- step S22 if the controller 310a does not exist in the connectable target list (No in step S22), the FC connection management unit 143a is requested to connect the controller 310a (step S25). As a result, process C-1 is performed. Next, it is determined whether or not the response from the FC connection management unit 143a is “connectable” (step S26).
- step S26 If the response from the FC connection management unit 143a is "connectable" (Yes in step S26), the process proceeds to step S23, and the above-described processing is continued.
- step S26 when the response from the FC connection management unit 143a is “connection is impossible” (No in step S26), an error of the IZO issue request is returned to the IZO issue request management unit 141a (step S27). Then, process B-1 is completed.
- FIG. 11 is a flowchart showing the process D-1.
- the X—ID management unit 144a Upon receiving the X—ID request (step S31), the X—ID management unit 144a selects the lowest unused X—ID from the X—ID management table Tal, and uses the status of the selected X—ID as “Used”. Change to “Medium” (step S32).
- step S33 the exchange issuance information management unit 142a
- FIG. 12 is a flowchart showing process B-2.
- step Sbl Upon receiving an IZO response from the controller 310a (step Sbl), the X ID management unit 144a X—Request release of ID (step Sb2). As a result, process D-2 is performed.
- step Sb3 an IZO response from the controller 310a is returned to the IZO issue request management unit 141a.
- process A-2 is performed.
- FIG. 13 is a flowchart showing the process D-2.
- step S81 When an X_ID release request is received (step S81), the received X_ID (requested to be released) is searched from the X—ID management table Tal, and the status is changed to “unused” (step S82).
- FIG. 14 is a flowchart showing the process A-2.
- Step S101 the response from the exchange issuance information management unit 142a is returned to the upper level (Step S102).
- step S103 the management information of the IZO issue request is deleted. This completes process A-2.
- the IZO issue request management unit 141a performs the process A-3
- the FC connection management unit 143a performs the process C-2 and the process C-3.
- the adapter port to be blocked is blocked for a predetermined time.
- the exchange issue information management unit 142a performs the process B-3
- the X-ID management unit 144a performs the process D-2.
- FIG. 15 is a flowchart showing the process A-3.
- step S41 When IZO abort is received from the host (step S41), the adapter port to be blocked in the FC adapter 108a is determined (step S42).
- Step S43 the FC connection management unit 143a is requested to block the adapter port to be blocked.
- Step S44 an error response is sent to all iZo that are being issued through the adapter port to be blocked.
- step S45 the management information of the IZO issue request of all IZOs that are being issued through the adapter port to be blocked is deleted.
- step S46 the exchange issuance information management unit 142a is requested to delete all the IZOs being issued through the blocked adapter port.
- step S46 the exchange issuance information management unit 142a is requested to delete all the IZOs being issued through the blocked adapter port.
- process B-3 is performed.
- process A-3 is completed.
- FIG. 16 is a flowchart showing the process C2.
- the FC connection management unit 143a When receiving the adapter port blocking request (step S51), the FC connection management unit 143a deletes the controller 310a connected through the adapter port to be blocked from the connectable target list (step S52). In the present embodiment, when there are a plurality of controllers having only the controller 310a, all the controllers connected through the adapter port to be blocked are deleted.
- FC adapter 108a (chip) is instructed to stop the operation (step S53).
- step S54 a request is made to block the adapter port to be blocked.
- step S54 a request is made to block the adapter port to be blocked.
- process C 3 is performed.
- the process C 2 is thus completed.
- FIG. 17 is a flowchart showing the process C3.
- step S61 When receiving a request for blocking the adapter port to be blocked (step S61), it waits for a certain period of time (stops the adapter port) (step S62).
- the waiting time is not particularly limited, but is about 180 seconds as an example.
- FIG. 18 is a flowchart showing process B-3.
- step S71 When an IZO deletion request is received from the IZO issue request management unit 141a (step S71), the X—ID management unit 144a is requested to release the X ID (step S72). As a result, process D-2 is Done.
- step S73 the management information of the IZO that has received the deletion request is deleted. Then, process B-3 is completed.
- ⁇ issue request management unit 141a performs processing ⁇ -1 and processing A-2
- exchange issue information management unit 142a performs processing B-1
- FC connection management unit 1443a Perform process C-1.
- an error notification is returned in the case of an IZO issue request for the adapter port to be blocked.
- Processing ⁇ -1, processing A-2, and processing B-1 are performed as described above.
- FIG. 19 is a flowchart showing the process C1.
- step S91 When a connection request to the controller 310a is received (step S91), it is determined whether or not the controller 310a exists in the connectable target list (step S92).
- step S92 When the controller 310a exists in the connectable target list (Yes in step S92), the process proceeds to step S97 described later.
- step S93 if the controller 310a does not exist in the connectable target list (No in step S92), LOGIN is issued to the controller 310a (step S93).
- step S94 it is determined whether or not the FC 310 can be connected to the controller 310a.
- step S94 If FC connection to the controller 310a is possible (Yes in step S94), it is determined whether or not there is a connection preparation OK response from the controller 310a (step S95).
- step S95 When the controller 310a receives a connection preparation OK response (Yes in step S95), the controller 310a is added to the connectable target list (step S96).
- step S96 if FC connection to the controller 310a is not possible (No in step S96) and if the controller 310a does not respond to connection preparation OK even after a predetermined time has passed (No in step S97), the requester (exchange issue information management unit 142a) A connection failure response is returned to (step S98). The process C 1 is thus completed.
- the IZO multipath control unit 120 of the server (communication processing device) 100 detects a timeout and issues a habit stop request, Since all the processing for the target disk array is blocked, error notifications can be immediately returned from the FC drivers 140a and 140b to the upper target drivers 130a and 130b, respectively. .
- the IZO multipath controller 120 can retry the ⁇ issuance request on the alternative route (redundant route for the main route and the main route for the redundant route) in a short time and perform the data ⁇ ⁇ ⁇ normally.
- the application 110 can perform normal processing without timing out.
- the communication processing system according to the second embodiment is different from the first embodiment in which block power is blocked in units of adapter ports of the FC adapters 108a and 108b.
- the processing of FC drivers 140a and 140b is different.
- FIG. 20 is a diagram for explaining the processing of the FC driver according to the second embodiment
- FIG. 21 is a flowchart showing the blocking processing of the FC driver according to the second embodiment.
- the FC driver 140a determines a target to be blocked (step Sla).
- the target to be blocked depends on the request.
- the target of the I / O issue target is the tar get of the shutdown target.
- the target is set as the target to be blocked.
- the target is the target to be blocked.
- PORT LOGOUT is issued to the target to be blocked, and communication with the target to be blocked is blocked (step S2a).
- all IZO for the target to be blocked is unconditionally returned to the target driver 130a with an error, and the management (SCSI level) information of the IZO issue request is deleted (step S3a).
- step S4a the information for issuing the change to the Fiber Channel communication related to the IZO targeting the target to be blocked.
- a timer for operating a certain time (for example, 60 to 180 seconds or manually canceling with a command) is operated (step S5a). While the timer is operating, even if an IZO issue request is sent from the target driver 130a to the target tar- get target, it will be able to communicate with the target to be blocked! / Please reply with an error immediately without accepting it. Also, the response power S from the target to be blocked from the main route is not accepted and discarded.
- PORT LOGIN to the target device is performed to release the blocked state (step S 6a).
- FIG. 22 is a sequence diagram illustrating processing of the FC driver according to the second embodiment.
- the issuance request management unit 141a performs the processing a-1
- the status change issuance information management unit 142a performs the processing b-1
- the X-ID management unit 144a performs the processing d— Do one.
- Processing b-1> The same processing as the processing B-1 in the first embodiment is performed.
- Process b-2 The same process as process B-2 of the first embodiment is performed.
- the IZO issue request management unit 141a performs the process a-3
- the FC connection management unit 143a performs the process c-2 and the process c-3.
- the target to be blocked is blocked for a specified time.
- the exchange issue information management unit 142a performs the process b-3
- the X-ID management unit 144a performs the process d-2.
- the FC connection management unit 143a of the second embodiment has a block list having information on the blocked target. If there is an IZO issue request for the target to be closed added to the block list, the FC connection management unit 143a considers that the target to be blocked is not in a communicable state, and does not accept it and immediately responds with an error. . Even if there is a response from the target to be blocked from the main route, it is not accepted and discarded.
- FIG. 23 is a flowchart showing process a-3.
- step S41a When IZO abort is received from the host (step S41a), the target to be blocked is determined (step S42a).
- step S43a it is determined whether or not the target to be blocked exists in the blocked list.
- step S43a If the target to be blocked does not exist in the blocked list (No in step S43a), the FC connection management unit 143a is requested to issue PORT LOGOUT to the target to be blocked (step S44a). As a result, process c-2 is performed. Thereafter, the process proceeds to step S45a.
- step S43a when the target to be blocked exists in the blocked list (Yes in step S43a), the process proceeds to step S45a.
- step S45a an error response is sent to all IZOs that are being issued to the target to be blocked.
- step S46a the management information of the IZO issue request for all the IZOs currently issued to the target to be blocked is deleted.
- FIG. 24 is a flowchart showing the process c2.
- step S51a When a request to issue PORT LOGOUT is received (step S51a), the target to be blocked is deleted from the connectable target list (step S52a).
- PORT LOGOUT is issued to the target to be blocked (step S53a).
- step S54a the target of the target to be blocked is requested to be blocked.
- process c 3 is performed.
- process c-2 is completed.
- FIG. 25 is a flowchart showing the process c3.
- step S6la When a block request for the target to be blocked is received (step S6la), the requested tag is added to the block list (step S62a).
- the waiting time is not particularly limited, but is about 180 seconds as an example.
- step S64a the target requested to be blocked is deleted from the blocking list. Then, process c3 is completed.
- the issuance request management unit 141a performs processing a-1 and processing a-2
- the exchange issuance information management unit 142a performs processing b-1
- the FC connection management unit 1 43a Perform process c1.
- an error notification is returned in the case of an IZO issue request for the target to be blocked.
- Processing b-1> The same processing as the processing B-1 in the first embodiment is performed.
- FIG. 26 is a flowchart showing process c1.
- step S91a when a connection request to the target to be blocked is received (step S91a), It is determined whether or not target exists in the connectable target list (step S92a).
- step S92a If the target to be blocked exists in the connectable target list (Yes in step S92a), the process proceeds to step S99a described later.
- step S93a it is determined whether or not the target to be blocked exists in the blocked list.
- step S93a If the target to be blocked does not exist in the blocked list (No in step S93a), a reply indicating that the connection is not possible is returned to the ethnchange issue information management unit 142a (step S94a), and the process c-1 is terminated.
- step S 95a if the target to be blocked exists in the blocked list (Yes in step S93a), LOGIN is issued to the target to be closed (step S 95a).
- step S96a it is determined whether or not the FC connection with the disk array device 300 is possible.
- step S9 FC connection with disk array device 300 is not possible! /, If (No in step S96a), step S9
- step S96a it is determined whether or not there is a response indicating that the disk array device 300 is ready for connection.
- step S97a If the connection preparation OK response is not received even after the predetermined time has elapsed (No in step S97a), the process proceeds to step S94a.
- step S97a if there is a response indicating that connection preparation is OK (Yes in step S97a), the target to be blocked is added to the connectable target list (step S98a).
- the communication processing program, the communication processing method, and the communication processing device of the present invention have been described based on the illustrated embodiment. However, the present invention is not limited to this. The configuration of the part can be replaced with any configuration having a similar function. In addition, any other component or process may be added to the present invention.
- the present invention may be a combination of any two or more configurations (features) of the above-described embodiments.
- the above processing functions can be realized by a computer (by causing the computer to execute a predetermined communication processing program).
- a program describing the processing contents of the functions that the server 100 should have is provided.
- the program describing the processing contents can be recorded on a computer-readable recording medium.
- the computer-readable recording medium include a magnetic recording device, an optical disk, a magneto-optical recording medium, and a semiconductor memory.
- the magnetic recording device include a hard disk device (HDD), a flexible disk (FD), and a magnetic tape.
- optical disc examples include a DVD (Digital Versatile Disc), a DVD—RAM (Random Access Memory), a CD—ROM (Compact Disc Read Only Memory), and a CD-R (Recordable) / RW (Rewritable).
- magneto-optical recording medium examples include MO (Magneto-Optical disk).
- Portable recording media such as ROM are sold. It is also possible to store the program in a storage device of the server computer and transfer the program to other computers via the network.
- a computer that executes a communication processing program stores, for example, a program recorded on a portable recording medium or a program transferred with server computer power in its own storage device. Then, the computer reads the program with its own storage device capability and executes processing according to the program. The computer can also read the program directly from the portable recording medium and execute processing according to the program. In addition, each time the server computer program is transferred, the computer can sequentially execute processing according to the received program.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Quality & Reliability (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Hardware Design (AREA)
- Hardware Redundancy (AREA)
- Debugging And Monitoring (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Computer And Data Communications (AREA)
Abstract
Description
Claims
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020097007961A KR101338595B1 (ko) | 2006-12-20 | 2006-12-20 | 통신 처리 프로그램을 기록한 컴퓨터 판독가능한 기록 매체 및 통신 처리 방법 |
PCT/JP2006/325429 WO2008075425A1 (ja) | 2006-12-20 | 2006-12-20 | 通信処理プログラム、通信処理方法および通信処理装置 |
JP2008550017A JP5077240B2 (ja) | 2006-12-20 | 2006-12-20 | 通信処理プログラムおよび通信処理方法 |
EP06835049A EP2071469B1 (en) | 2006-12-20 | 2006-12-20 | Communication processing method, device and program |
CN2006800561724A CN101529402B (zh) | 2006-12-20 | 2006-12-20 | 通信处理装置以及通信处理方法 |
US12/411,102 US8478935B2 (en) | 2006-12-20 | 2009-03-25 | Program, method, and device for communication processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2006/325429 WO2008075425A1 (ja) | 2006-12-20 | 2006-12-20 | 通信処理プログラム、通信処理方法および通信処理装置 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/411,102 Continuation US8478935B2 (en) | 2006-12-20 | 2009-03-25 | Program, method, and device for communication processing |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2008075425A1 true WO2008075425A1 (ja) | 2008-06-26 |
Family
ID=39536064
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2006/325429 WO2008075425A1 (ja) | 2006-12-20 | 2006-12-20 | 通信処理プログラム、通信処理方法および通信処理装置 |
Country Status (6)
Country | Link |
---|---|
US (1) | US8478935B2 (ja) |
EP (1) | EP2071469B1 (ja) |
JP (1) | JP5077240B2 (ja) |
KR (1) | KR101338595B1 (ja) |
CN (1) | CN101529402B (ja) |
WO (1) | WO2008075425A1 (ja) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010184687A (ja) * | 2009-02-13 | 2010-08-26 | Nsk Ltd | 車両用制御装置 |
JP2012182580A (ja) * | 2011-02-28 | 2012-09-20 | Fujitsu Ltd | スイッチ、情報処理装置および情報処理システム |
JP2013008230A (ja) * | 2011-06-24 | 2013-01-10 | Hitachi Ltd | 計算機システム、ホストバスアダプタ制御方法及びそのプログラム |
WO2016189636A1 (ja) * | 2015-05-25 | 2016-12-01 | 株式会社日立製作所 | 計算機システム |
JP2018041414A (ja) * | 2016-09-09 | 2018-03-15 | 富士通株式会社 | アクセス制御装置、アクセス制御方法、およびアクセス制御プログラム |
JP2023128349A (ja) * | 2022-03-03 | 2023-09-14 | Necプラットフォームズ株式会社 | ストレージシステム、サーバ、パス切替方法、およびプログラム |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8255596B2 (en) * | 2009-06-10 | 2012-08-28 | International Business Machines Corporation | Multipath-based migration of data across storage controllers |
US8417849B2 (en) * | 2009-10-07 | 2013-04-09 | International Business Machines Corporation | Apparatus and method to adjust a multi-path device reservation |
US9792076B2 (en) * | 2011-12-23 | 2017-10-17 | Cirrus Data Solutions, Inc. | Systems, devices, apparatus, and methods for transparently inserting a virtual storage layer in a fibre channel based storage area network while maintaining continuous input/output operations |
JP5923976B2 (ja) * | 2011-12-27 | 2016-05-25 | 富士通株式会社 | 接続装置、ストレージ装置、接続装置における処理方法、および処理プログラム |
US9451024B2 (en) * | 2013-03-15 | 2016-09-20 | Futurewei Technologies, Inc. | Self-organizing disk (SoD) |
CN103354523B (zh) * | 2013-06-21 | 2017-07-07 | 新华三技术有限公司 | 一种交换机及无损切换方法 |
US9645872B1 (en) * | 2015-03-27 | 2017-05-09 | EMC IP Holding Company LLC | Method to use multipath to reduce IO error handle duration |
CN109445680B (zh) * | 2018-08-20 | 2020-03-31 | 华为技术有限公司 | 一种对硬盘进行管理的方法及装置 |
CN116701024A (zh) * | 2022-02-25 | 2023-09-05 | 戴尔产品有限公司 | 用于访问存储设备的方法、电子设备和计算机程序产品 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06110800A (ja) | 1992-09-25 | 1994-04-22 | Fujitsu Ltd | 動的パス切替方法 |
JP2000132413A (ja) * | 1998-10-22 | 2000-05-12 | Nec Corp | エラーリトライ方法、エラーリトライシステム及びその記録媒体 |
JP2001005744A (ja) * | 1999-06-18 | 2001-01-12 | Hitachi Ltd | チャネル装置 |
JP2006309506A (ja) * | 2005-04-28 | 2006-11-09 | Fujitsu Ltd | リモートコピー処理方法、プログラム及び装置 |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3582970B2 (ja) * | 1997-11-04 | 2004-10-27 | 富士通株式会社 | アダプタ、及びアダプタとディスクカートリッジ駆動装置との間の通信方法 |
JP4080629B2 (ja) * | 1999-03-30 | 2008-04-23 | 株式会社東芝 | アクセス制御装置及びプログラムを記憶したコンピュータ読み取り可能な記憶媒体 |
WO2002084471A1 (en) | 2001-04-13 | 2002-10-24 | Sun Microsystems, Inc. | Virtual host controller interface with multipath input/output |
JP2003131897A (ja) * | 2001-10-24 | 2003-05-09 | Hitachi Ltd | ポートを内蔵したストレージ |
US7702786B2 (en) * | 2002-08-09 | 2010-04-20 | International Business Machines Corporation | Taking a resource offline in a storage network |
JP4012498B2 (ja) * | 2003-11-18 | 2007-11-21 | 株式会社日立製作所 | 情報処理システム、情報処理装置、情報処理装置の制御方法及びプログラム |
JP4241405B2 (ja) * | 2004-01-23 | 2009-03-18 | 日本電気株式会社 | コンピュータシステムおよびi/oリトライ方法ならびにプログラム |
JP2006107151A (ja) * | 2004-10-06 | 2006-04-20 | Hitachi Ltd | ストレージシステム及びストレージシステムの通信パス制御方法 |
-
2006
- 2006-12-20 KR KR1020097007961A patent/KR101338595B1/ko not_active IP Right Cessation
- 2006-12-20 EP EP06835049A patent/EP2071469B1/en not_active Not-in-force
- 2006-12-20 JP JP2008550017A patent/JP5077240B2/ja not_active Expired - Fee Related
- 2006-12-20 CN CN2006800561724A patent/CN101529402B/zh not_active Expired - Fee Related
- 2006-12-20 WO PCT/JP2006/325429 patent/WO2008075425A1/ja active Application Filing
-
2009
- 2009-03-25 US US12/411,102 patent/US8478935B2/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06110800A (ja) | 1992-09-25 | 1994-04-22 | Fujitsu Ltd | 動的パス切替方法 |
JP2000132413A (ja) * | 1998-10-22 | 2000-05-12 | Nec Corp | エラーリトライ方法、エラーリトライシステム及びその記録媒体 |
JP2001005744A (ja) * | 1999-06-18 | 2001-01-12 | Hitachi Ltd | チャネル装置 |
JP2006309506A (ja) * | 2005-04-28 | 2006-11-09 | Fujitsu Ltd | リモートコピー処理方法、プログラム及び装置 |
Non-Patent Citations (1)
Title |
---|
See also references of EP2071469A4 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010184687A (ja) * | 2009-02-13 | 2010-08-26 | Nsk Ltd | 車両用制御装置 |
JP2012182580A (ja) * | 2011-02-28 | 2012-09-20 | Fujitsu Ltd | スイッチ、情報処理装置および情報処理システム |
US9331870B2 (en) | 2011-02-28 | 2016-05-03 | Fujitsu Limited | Switch, information processing apparatus, and information processing system |
JP2013008230A (ja) * | 2011-06-24 | 2013-01-10 | Hitachi Ltd | 計算機システム、ホストバスアダプタ制御方法及びそのプログラム |
WO2016189636A1 (ja) * | 2015-05-25 | 2016-12-01 | 株式会社日立製作所 | 計算機システム |
JP2018041414A (ja) * | 2016-09-09 | 2018-03-15 | 富士通株式会社 | アクセス制御装置、アクセス制御方法、およびアクセス制御プログラム |
JP2023128349A (ja) * | 2022-03-03 | 2023-09-14 | Necプラットフォームズ株式会社 | ストレージシステム、サーバ、パス切替方法、およびプログラム |
JP7409700B2 (ja) | 2022-03-03 | 2024-01-09 | Necプラットフォームズ株式会社 | ストレージシステム、サーバ、パス切替方法、およびプログラム |
Also Published As
Publication number | Publication date |
---|---|
KR20090055036A (ko) | 2009-06-01 |
US20090187708A1 (en) | 2009-07-23 |
CN101529402A (zh) | 2009-09-09 |
US8478935B2 (en) | 2013-07-02 |
EP2071469A1 (en) | 2009-06-17 |
KR101338595B1 (ko) | 2013-12-06 |
EP2071469A4 (en) | 2011-03-09 |
JPWO2008075425A1 (ja) | 2010-04-02 |
CN101529402B (zh) | 2012-02-08 |
EP2071469B1 (en) | 2012-05-16 |
JP5077240B2 (ja) | 2012-11-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2008075425A1 (ja) | 通信処理プログラム、通信処理方法および通信処理装置 | |
TWI403891B (zh) | 直接附加儲存系統之主動-主動失效切換 | |
US7111084B2 (en) | Data storage network with host transparent failover controlled by host bus adapter | |
US8621603B2 (en) | Methods and structure for managing visibility of devices in a clustered storage system | |
US8443237B2 (en) | Storage apparatus and method for controlling the same using loopback diagnosis to detect failure | |
US7536508B2 (en) | System and method for sharing SATA drives in active-active RAID controller system | |
JP4963808B2 (ja) | 記憶制御システム | |
US7194662B2 (en) | Method, apparatus and program storage device for providing data path optimization | |
US7594083B2 (en) | Storage system and storage control device | |
US20080147934A1 (en) | STORAGE SYSTEM FOR BACK-end COMMUNICATIONS WITH OTHER STORAGE SYSTEM | |
US7568119B2 (en) | Storage control device and storage control device path switching method | |
JP2000339098A (ja) | ストレージドメイン管理システム | |
TW201015336A (en) | Shared-storage bus switch | |
JP2010537267A (ja) | ストレージ・コントローラと複製エンジンとの間で書き込みを分割する方法、システムおよびプログラム | |
JP2004088570A (ja) | ネットワーク計算機システムおよび管理装置 | |
JP6005446B2 (ja) | ストレージシステム、仮想化制御装置、情報処理装置、および、ストレージシステムの制御方法 | |
JP2003131897A (ja) | ポートを内蔵したストレージ | |
JP4433372B2 (ja) | データアクセスシステム及び方法 | |
JP2005128781A (ja) | 系切り替え方法及び情報処理システム | |
JP6244970B2 (ja) | ストレージシステム、制御装置及び制御プログラム | |
US9542348B2 (en) | Arbitration monitoring for serial attached small computer system interface systems during discovery | |
US9317467B2 (en) | Session key associated with communication path | |
JP4326819B2 (ja) | ストレージシステムの制御方法、ストレージシステム、プログラム、及び記録媒体 | |
JP4080629B2 (ja) | アクセス制御装置及びプログラムを記憶したコンピュータ読み取り可能な記憶媒体 | |
JP2007193839A (ja) | ストレージシステム、ストレージシステムにおけるデータ送受信方法及びシステム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 200680056172.4 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 06835049 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2008550017 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2006835049 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1020097007961 Country of ref document: KR |
|
NENP | Non-entry into the national phase |
Ref country code: DE |