JP5338367B2 - Communication control device, failure detection method, communication control circuit, and program - Google Patents

Description

  The present invention relates to a communication control device that mediates communication with other devices mounted on a computer and connected to the computer via a communication line, a failure detection method thereof, a communication control circuit, and a program

  In recent years, data transfer by Fiber Channel (FC) has been studied along with an increase in system interface speed between a storage device such as a magnetic disk and a host device that performs input and output to the storage device. Fiber channel is a high-speed interface standard used for connecting computers and connecting computers to storage devices. When performing communication using a fiber channel, a communication control device such as a fiber channel card is mounted on a computer or a storage device, and communication is performed via the fiber channel card. The fiber channel card is an option card that is mounted on a computer bus and functions as a fiber channel interface.

  In general, there are two methods for detecting a failure in a Fiber Channel card: a method in which a computer equipped with a Fiber Channel card detects a failure due to an I / O (Input / Output) timeout, and a failure by the function of the Fiber Channel card. There are roughly two types of detection methods. Here, the I / O timeout means that the computer monitors the response to the I / O instruction triggered by the issuance or acquisition of the I / O instruction, and the response to the I / O instruction cannot be detected within a predetermined time. In this case, the reset process is performed by a watchdog timer.

Conventionally, the detection of a failure in a light receiving unit in a fiber channel card is performed by a failure detection unit or the like that acquires an optical signal received by the light receiving unit and determines whether or not the optical signal is equal to or higher than a predetermined light level, or encodes the optical signal. This was done by determining whether there was an error.
On the other hand, the failure of the light emitting unit is detected by the I / O timeout of the computer equipped with the fiber channel card.

  Patent Document 1 discloses a technique for detecting a contact failure in a fiber channel switch.

JP 2007-274153 A

  The failure of the light receiving part of the fiber channel card could be detected at an early stage by the conventional method. However, since the failure of the light emitting unit of the fiber channel card is detected by the I / O timeout of the computer, it takes a long time from the occurrence of the failure to the detection. The reason for this is that the computer I / O time-out time is taken into account by the administrator of the connection between the Fiber Channel card and the computer and the failure of the communication cable, as well as the temporary response degradation of the connected device. This is because it takes a long time to set.

  The present invention has been made in view of the above points, and an object of the present invention is to provide a communication control device, a failure detection method, a communication control circuit, and a program for early detection of an abnormality in a transmission unit of a communication control device such as a fiber channel card. Is to provide.

  The present invention has been made to solve the above-described problem, and is a communication control apparatus that mediates communication with another apparatus mounted on a computer and connected to the computer via a communication line, A receiving unit that receives a connection request signal for requesting connection from another device to the own device, a counting unit that counts the number of times the connection request signal is received by the receiving unit, and a number of receptions that the counting unit counts. A determination unit that determines whether or not a predetermined threshold value or more, and a response signal for the connection request signal when the determination unit determines that the number of receptions counted by the counting unit is less than the threshold value, A failure notification that outputs a failure notification signal indicating the occurrence of a failure to the computer when it is determined by the determination unit that the number of receptions counted by the counting unit is greater than or equal to the threshold. Department and Characterized in that it comprises a.

  Further, the present invention is a failure detection method using a communication control device that mediates communication with another device mounted on a computer and connected to the computer via a communication line, wherein the receiving unit includes the other A connection request signal for requesting connection from the device to the own device, the counting unit counts the number of receptions of the connection request signal received by the receiving unit, and the determining unit counts the number of receptions counted by the counting unit. Is determined to be greater than or equal to a predetermined threshold value, and the transmission unit determines that the determination unit determines that the number of receptions counted by the counting unit is less than the threshold value, the response signal to the connection request signal The failure notification unit transmits a failure notification signal indicating the occurrence of a failure to the computer when the determination unit determines that the number of receptions counted by the counting unit is equal to or greater than the threshold. It is characterized by output .

  Further, the present invention is a communication control circuit that mediates communication with another device mounted on the computer and connected to the computer via a communication line, and requests connection from the other device to the own device. A reception circuit that receives a connection request signal to be received, a counting circuit that counts the number of receptions of the connection request signal received by the receiving unit, and whether or not the number of receptions that the counting unit counts is equal to or greater than a predetermined threshold And a transmission circuit that transmits a response signal to the connection request signal to the other device when the determination unit determines that the number of receptions counted by the counting unit is less than the threshold. And a failure notification circuit that outputs a failure notification signal indicating the occurrence of a failure to the computer when the determination unit determines that the number of receptions counted by the counting unit is equal to or greater than the threshold value.

  Further, the present invention provides a communication control device that mediates communication with another device that is mounted on a computer and connected to the computer via a communication line, and that requests connection from the other device to the own device. A receiving unit that receives a request signal, a counting unit that counts the number of receptions of a connection request signal received by the receiving unit, a determination unit that determines whether or not the number of receptions counted by the counting unit is equal to or greater than a predetermined threshold, When the determination unit determines that the number of receptions counted by the counting unit is less than the threshold, the transmission unit transmits a response signal to the connection request signal to the other device, and the determination unit performs the counting unit. Is a program for operating as a failure notification unit that outputs a failure notification signal indicating the occurrence of a failure to the computer when it is determined that the number of receptions counted by is greater than or equal to the threshold.

  According to the present invention, when the counting unit of the communication control device counts the number of receptions of the connection request signal, and the number of receptions counted by the counting unit is equal to or greater than a predetermined threshold, the failure notification unit indicates a failure indicating that a failure has occurred. A notification signal is output to the computer. As a result, the failure of the transmission unit can be detected by the function of the communication control device regardless of the I / O timeout of the computer, so that the failure can be detected early.

It is a schematic block diagram which shows the structure of the fiber channel card by one Embodiment of this invention. It is a 1st flowchart which shows operation | movement of a fiber channel card. It is a 2nd flowchart which shows operation | movement of a fiber channel card.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
FIG. 1 is a schematic block diagram showing the configuration of a fiber channel card according to an embodiment of the present invention.
The fiber channel card 200 (communication control device) is mounted on the computer 100 and is connected to a CPU (Central Processing Unit) 110 via a bus 120 of the computer 100.
The fiber channel card 200 includes a light receiving unit 201 (receiving unit), a counting unit 202 (counting unit), a determining unit 203 (determining unit), a light emitting unit 204 (transmitting unit), a state transition unit 205 (standby state transition unit, disconnected state). Transition unit, connection state transition unit), state storage unit 206, reset unit 207 (reset unit), failure notification unit 208 (failure notification unit), and connection unit 209.
The light receiving unit 201 receives an optical signal from another device connected via a communication circuit.
The counting unit 202 counts the number of times the light receiving unit 201 has received a connection request signal for requesting connection with the fiber channel card 200 from another device.
The determination unit 203 determines whether or not the number of receptions of the connection request signal counted by the counting unit 202 is equal to or greater than a predetermined threshold (for example, 127 times).
The light emitting unit 204 transmits an optical signal to another device via a communication circuit.
The state transition unit 205 transitions the state of the Fiber Channel card 200 stored in the state storage unit 206 based on the determination result of the determination unit 203 and the optical signal received by the light receiving unit 201.
The state of the Fiber Channel card 200 stored in the state storage unit 206 is a standby state indicating that the connection with the other device is waiting, a disconnected state indicating that the connection with the other device is disconnected, or One of the connection states indicating connection with another device is shown. The state storage unit 206 stores a cutting state as an initial value of the state.
The reset unit 207 resets the number of receptions of the connection request signal counted by the counting unit 202.
The failure notification unit 208 notifies the CPU 110 of the computer 100 that a failure has occurred in the light emitting unit 204.
The connection unit 209 is connected to the bus 120 of the computer 100 and collects data with the computer 100.

In the fiber channel card 200, the light receiving unit 201 receives a connection request signal for requesting connection between the other device and the fiber channel card 200 from another device, and the counting unit 202 is received by the light receiving unit 201. The determination unit 203 determines whether or not the number of receptions counted by the counting unit 202 is equal to or greater than a predetermined threshold.
When the determination unit 203 determines that the number of receptions counted by the counting unit 202 is less than the threshold, the light emitting unit 204 transmits a response signal to the connection request signal to another device.
On the other hand, when the determination unit 203 determines that the number of receptions counted by the counting unit 202 is equal to or greater than the threshold, the failure notification unit 208 outputs a failure notification signal indicating the occurrence of a failure to the computer 100.
Thereby, the fiber channel card 200 can detect an abnormality of the light emitting unit 204 at an early stage.

Next, the operation of the fiber channel card 200 will be described.
FIG. 2 is a first flowchart showing the operation of the fiber channel card.
First, when another device transmits a connection request signal requesting connection between the own device and the Fiber Channel card 200 to the Fiber Channel card 200, the light receiving unit 201 receives the connection request signal from the other device (step S1). ). When the light receiving unit 201 receives the connection request signal, the state transition unit 205 acquires the state of the Fiber Channel card 200 stored in the state storage unit 206 and determines whether or not the state is a standby state (step S2). .

  When the state stored in the state storage unit 206 is not in the standby state, that is, in either the connected state or the disconnected state (step S2: NO), the state transition unit 205 stores the state stored in the state storage unit 206 in the standby state. (Step S3). When the state transition unit 205 rewrites the state stored in the state storage unit 206 to a standby state, the reset unit 207 counts the counting unit 202 and sets the number of receptions stored in a memory (not shown) to zero. Reset (step S4).

If the state transition unit 205 determines in step S2 that the state stored in the state storage unit 206 is a standby state (step S2: YES), or the number of receptions that the reset unit 207 counts in the counting unit 202 in step S4 Is reset, the counting unit 202 updates the number of receptions stored in the memory to a value obtained by adding 1 to the number of receptions (step S5).
When the counting unit 202 adds the number of receptions, the determination unit 203 determines whether or not the number of receptions counted by the counting unit is equal to or greater than a predetermined threshold (for example, 127 times) (step S6).

  When the determination unit 203 determines that the number of receptions counted by the counting unit is less than a predetermined threshold (step S6: NO), the light emitting unit 204 transmits a response signal to the connection request signal to another device (step S6). S7). When the light emitting unit 204 transmits a response signal, the light receiving unit 201 receives a connection establishment signal indicating that the other device has received the response signal and has established a connection from another device (step S8).

When the light receiving unit 201 receives the connection establishment signal (step S8: YES), the state transition unit 205 rewrites the state stored in the state storage unit 206 into the connection state (step S9). Thereafter, the light receiving unit 201 and the light emitting unit 204 of the fiber channel card transmit signals in accordance with commands output from the CPU 110 of the computer 100 via the connection unit 209. Thus, the Fiber Channel card 200 can mediate communication between the computer 100 and other devices.
On the other hand, when the light receiving unit 201 has not received the connection establishment signal (step S8: NO), the process returns to step S1 to accept the reception of the connection request signal from another device again.

  When the determination unit 203 determines in step S6 that the number of receptions counted by the counting unit is equal to or greater than a predetermined threshold (step S6: YES), the failure notification unit 208 is connected to the computer 100 via the connection unit 209. An interrupt signal for notifying the CPU 110 of the occurrence of a failure in the light emitting unit is output (step S10). When the failure notification unit 208 notifies the occurrence of a failure, the state transition unit 205 rewrites the state stored in the state storage unit 206 into a disconnected state (step S11).

  Thus, according to the present embodiment, the counting unit 202 counts the number of receptions of the connection request signal, and when the number of receptions counted by the counting unit 202 is equal to or greater than a predetermined threshold, the connection establishment signal is transmitted from another device. Is not received, the failure notification unit 208 outputs a failure notification signal indicating the occurrence of the failure to the computer. As a result, the failure of the transmission unit can be detected by the function of the communication control device regardless of the I / O timeout of the computer, so that the failure can be detected early.

  Further, according to the present embodiment, when the state transition unit 205 rewrites the state stored in the state storage unit 206 from the connected state or the disconnected state to the standby state, the reset unit 207 determines the number of receptions counted by the counting unit 202. Reset to 0 times. Accordingly, the counting unit 202 receives the connection request signal when the receiving unit 201 receives the connection request signal after the output of the failure notification signal by the failure notification unit 208 or the reception of the connection establishment signal by the receiving unit 201. The number of times is counted as the first time. Therefore, since the counting unit 202 can count the number of times of reception only when the light receiving unit 201 continuously receives the connection establishment signal, the connection request signal is discontinuously due to a temporary response decrease or the like. Can be prevented from being output when the failure notification unit 208 receives a failure notification.

As described above, the embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to the above, and various design changes and the like can be made without departing from the scope of the present invention. It is possible to
For example, in the present embodiment, the case where the fiber channel card 200 is used as an example of the communication control apparatus has been described. However, the present invention is not limited to this, and another communication control apparatus may be used.

  In this embodiment, when the receiving unit 201 receives a connection request signal following the output of the failure notification signal by the failure notification unit 208 or the reception of the connection establishment signal by the receiving unit 201, the connection request is sent to the counting unit 202. As a method of counting the number of signal receptions as the first time, when the state transition unit 205 transitions the state stored in the state storage unit 206 from the connected state or the disconnected state to the standby state, the reset unit 207 includes the counting unit 202. However, the present invention is not limited to this. For example, a method that does not use the state stored in the state storage unit 206 as described below may be used.

FIG. 3 is a second flowchart showing the operation of the fiber channel card.
First, when another device transmits a connection request signal to the fiber channel card 200, the light receiving unit 201 receives the connection request signal from the other device (step S21). When the light receiving unit 201 receives the connection request signal, the counting unit 202 adds 1 to the number of receptions stored in the memory (step S22). When the counting unit 202 adds the number of receptions, the determination unit 203 determines whether or not the number of receptions counted by the counting unit is equal to or greater than a predetermined threshold (step S23).

  When the determination unit 203 determines that the number of receptions counted by the counting unit is less than a predetermined threshold (step S23: NO), the light emitting unit 204 transmits a response signal to another device (step S24). When the light emitting unit 204 transmits a response signal, the light receiving unit 201 receives a connection establishment signal from another device (step S25).

  When the light receiving unit 201 receives the connection establishment signal (step S25: YES), the reset unit 207 resets the number of receptions stored in the memory to 0 (step S26). Thereby, when the receiving unit 201 receives a connection request signal following the reception of the connection establishment signal by the receiving unit 201, the counting unit 202 can count the number of times the connection request signal is received as the first time.

  On the other hand, when the light receiving unit 201 has not received the connection establishment signal (step S25: NO), the process returns to step S21 and receives the connection request signal from another device again.

  When the determination unit 203 determines in step S23 that the number of receptions counted by the counting unit is equal to or greater than a predetermined threshold (step S23: YES), the failure notification unit 208 is connected to the computer 100 via the connection unit 209. An interrupt signal for notifying the CPU 110 of the occurrence of a failure in the light emitting unit is output (step S27). When the failure notification unit 208 notifies the occurrence of a failure, the reset unit 207 resets the number of receptions stored in the memory to 0 (step S28). As a result, when the receiving unit 201 receives a connection request signal following the output of the failure notification signal by the failure notification unit 208, the counting unit 202 can count the number of receptions of the connection request signal as the first time.

  In this embodiment, when the receiving unit 201 receives a connection request signal following the output of the failure notification signal by the failure notification unit 208 or the reception of the connection establishment signal by the receiving unit 201, the connection request is sent to the counting unit 202. Although the case where the number of signal receptions is counted as the first time has been described, the present invention is not limited to this. For example, the light reception unit 201 includes a time measuring unit (not shown) for measuring the elapsed time from the time when the connection request signal is received. The reset unit 207 may reset the number of receptions stored in the memory when the elapsed time measured by the time measuring unit at the time when the receiving unit 201 receives the connection request signal is equal to or longer than a predetermined time. At this time, the same effect as that of the above-described embodiment can be obtained by making the predetermined time longer than the time until the connection request signal is transmitted again when another device cannot receive the response signal. it can.

  The above-mentioned fiber channel card has a computer system inside. The operation of each processing unit described above is stored in a computer-readable recording medium in the form of a program, and the above processing is performed by the computer reading and executing this program. Here, the computer-readable recording medium means a magnetic disk, a magneto-optical disk, a CD-ROM, a DVD-ROM, a semiconductor memory, or the like. Alternatively, the computer program may be distributed to the computer via a communication line, and the computer that has received the distribution may execute the program.

  The program may be for realizing a part of the functions described above. Furthermore, what can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, what is called a difference file (difference program) may be sufficient.

  DESCRIPTION OF SYMBOLS 100 ... Computer 110 ... CPU 120 ... Bus 200 ... Fiber channel card 201 ... Light receiving part 202 ... Counting part 203 ... Determination part 204 ... Light emission part 205 ... State transition part 206 ... State storage part 207 ... Reset part 208 ... Fault notification part 209 ... Connection

Claims (8)

A communication control device that mediates communication with other devices mounted on a computer and connected to the computer via a communication line,
Receiving means for receiving a connection request signal for requesting connection from the other device to the own device;
Counting means for counting the number of times of reception of the connection request signal received by the receiving means;
Determination means for determining whether or not the number of receptions counted by the counting means is equal to or greater than a predetermined threshold;
A transmission unit that transmits a response signal to the connection request signal to the other device when the determination unit determines that the number of receptions counted by the counting unit is less than the threshold;
A failure notification means for outputting a failure notification signal indicating a failure occurrence of the transmission means to the computer when the determination means determines that the number of receptions counted by the counting means is equal to or greater than the threshold;
A communication control apparatus comprising: The receiving means receives a connection establishment signal indicating that a connection between the other device and the communication control device is established from the other device in addition to the connection request signal,
The counting means receives the connection request signal when the receiving means receives the connection request signal following the output of the failure notification signal by the failure notifying means or when the receiving means receives the connection establishment signal by the receiving means. When received, count the number of times the connection request signal is received as the first time.
The communication control apparatus according to claim 1. State storage means for storing the state of the communication control device;
When the receiving unit receives the connection request signal, a standby state transition unit that rewrites the state stored by the state storage unit into a standby state indicating that the connection with the other device is waiting;
A disconnection state transition means for rewriting the state stored in the state storage means to a disconnection state indicating that the connection with the other device is disconnected when the failure notification means outputs a failure notification signal;
A connection state transition means for rewriting the state stored in the state storage means to a connection state indicating that it is connected to the other device when the reception means receives the connection establishment signal;
A reset unit that resets the number of receptions counted by the counting unit when the standby state transition unit transitions the state stored in the state storage unit from a disconnected state or a connected state to a standby state;
The communication control apparatus according to claim 2, further comprising: A reset means for resetting the number of receptions counted by the counting means when the failure notification means outputs a failure notification signal or when the receiving means receives a connection establishment signal;
The communication control apparatus according to claim 2, further comprising: Time measuring means for measuring the elapsed time from the time when the receiving means received the connection request signal;
Resetting means for resetting the number of receptions counted by the counting means when the elapsed time measured by the timing means at a time when the receiving means receives the connection request signal is a predetermined time or more;
The communication control device according to claim 1, further comprising: A failure detection method using a communication control device that mediates communication with another device mounted on a computer and connected to the computer via a communication line,
The receiving means receives a connection request signal for requesting connection from the other device to the own device,
The counting means counts the number of receptions of the connection request signal received by the receiving means,
The determining means determines whether or not the number of receptions counted by the counting means is a predetermined threshold value or more,
The transmission unit transmits a response signal to the connection request signal to the other device when the determination unit determines that the number of receptions counted by the counting unit is less than the threshold.
The failure notification unit outputs a failure notification signal indicating the occurrence of a failure of the transmission unit to the computer when the determination unit determines that the number of receptions counted by the counting unit is equal to or greater than the threshold.
The fault detection method characterized by the above-mentioned. A communication control circuit that mediates communication with other devices mounted on a computer and connected to the computer via a communication line,
A receiving circuit for receiving a connection request signal for requesting connection from the other device to the own device;
A counting circuit for counting the number of receptions of the connection request signal received by the receiving means;
A determination circuit for determining whether or not the number of receptions counted by the counting means is equal to or greater than a predetermined threshold;
A transmission circuit that transmits a response signal to the connection request signal to the other device when the determination unit determines that the number of receptions counted by the counting unit is less than the threshold;
A failure notification circuit that outputs a failure notification signal indicating the occurrence of a failure of the transmission circuit to the computer when the determination unit determines that the number of receptions counted by the counting unit is equal to or greater than the threshold;
A communication control circuit comprising: A communication control device that mediates communication with other devices mounted on a computer and connected to the computer via a communication line;
Receiving means for receiving a connection request signal for requesting connection from the other device to the own device;
Counting means for counting the number of times of reception of the connection request signal received by the receiving means;
Determination means for determining whether the number of receptions counted by the counting means is equal to or greater than a predetermined threshold;
A transmission unit that transmits a response signal to the connection request signal to the other device when the determination unit determines that the number of receptions counted by the counting unit is less than the threshold;
A failure notification means for outputting a failure notification signal indicating a failure occurrence of the transmission means to the computer when the determination means determines that the number of receptions counted by the counting means is equal to or greater than the threshold;
Program to operate as.

Images