JP3147049B2 - Fabric failure detection method - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to a control method for detecting a failure of a switch device (fabric device) in a fiber channel.

[0002]

2. Description of the Related Art FIG. 3 shows an example of a configuration in a case where a switch device (referred to as "fabric") used in a fiber channel is connected to a computer 105 in a multi-layer cascade (referred to as "meshing topology"). In the conventional fabric, when a multi-layer cascade connection is used, when a module of a certain fabric goes down due to a failure, no function means for early detection of the failed module is provided, so that early detection of the failed module is not performed. .

As a known document relating to the fabric, for example, Japanese Patent Application Laid-Open No. 7-321824 discloses various configurations of a cell switch fabric in which a cell (packet) main memory is interfaced with N input ports and N output ports. There has been proposed a configuration of an integrated circuit chip that meets the requirements.

[0004]

The above-mentioned conventional method has a problem that when a fabric has a meshing topology, even if one of the fabrics fails, it takes time to detect the failure. .

[0005] The reason for this is that no maintenance management means is provided in a complexly configured fabric system configuration.

SUMMARY OF THE INVENTION Accordingly, the present invention has been made in view of the above problems, and has as its object to solve the problem that when a fabric in a Fiber Channel is configured in a meshing topology in a system, a module of a certain fabric fails due to a failure. It is an object of the present invention to provide a fabric failure detection method that enables a failed fabric to be detected early when it goes down.

[0007]

In order to achieve the above-mentioned object, a fabric fault detecting method according to the present invention comprises a fiber
A failure detection method for a system in which switch devices (referred to as “fabrics”) in a channel are connected in a multi-tiered manner (referred to as a “messing topology”), wherein each of the fabrics includes a maintenance monitoring table, and each of the fabrics includes Storing the operation state of the module in the maintenance monitoring table, wherein the maintenance monitoring table is connected to a monitoring means of a maintenance management means via a maintenance interface, and the maintenance management means further comprises a timer means, a storage means, a comparison means, And reporting means, and when the timer reaches a preset time, from the monitoring means, collects information on the operating state of the module of the fabric stored in the maintenance monitoring table of each fabric. The generation is managed by the storage unit and stored. , If the information stored date information and the previous different, are reported to the maintenance personnel by said reporting means, characterized in that.

[0008]

Embodiments of the present invention will be described below. The fabric failure detection method of the present invention, in a preferred embodiment thereof, uses each fabric (FIG. 1).
The maintenance monitoring table (10 in FIG. 1) provided in
4) is compared with the previous state at predetermined time intervals to confirm the faulty fabric. More specifically, the timer means (FIG. 1) of the maintenance management means (107 in FIG. 1)
When 110) reaches a preset time,
The maintenance monitoring table (104 in FIG. 1) of each fabric is collected from the monitoring means (109 in FIG. 1) via the maintenance interface (106 in FIG. 1) and stored in the storage means (FIG. 1).
In (108), there is a comparison means (111 in FIG. 1) for performing generation management and comparing the latest information with the information stored before it.

Another feature of the embodiment of the present invention is that a maintenance person is notified of a fabric abnormality. More specifically, it includes a reporting unit (102 in FIG. 1) for notifying the maintenance staff of the abnormal fabric.

[0010] In the embodiment of the present invention, the provision of the above means for early notification of an abnormality of the fabric enables the abnormal fabric to be detected early and easily.

[0011]

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram showing an embodiment of the present invention;

FIG. 1 is a diagram showing a system configuration of a first embodiment of the present invention. Referring to FIG. 1, a first embodiment of the present invention is shown.
According to the embodiment, in the fabric 101 connected by the meshing topology, the module 103 built in the fabric 101 is connected to the maintenance monitoring table 104 via the internal bus 102, and the operation state of the module 103 is stored in the maintenance monitoring table 104. Store.

The maintenance monitoring table 104 of each fabric 101 is connected to the monitoring means 109 of the maintenance management means 107 via the maintenance interface 106. The maintenance management unit 107 includes a monitoring unit 109, a timer 110, a comparison unit 111, a storage unit 108, and a reporting unit 112.

In the maintenance management means 107, the timer 11
When 0 reaches a preset time, the monitoring means 1
Information of the maintenance monitoring table 104 (operation state of the module) is collected from 09 and stored in the storage unit 108 by generation management. Then, the latest information and the information collected before that are compared by the comparing means 111, and the result of the comparison is reported to the maintenance person via the reporting means 112.

FIG. 2 is a flowchart for explaining the operation of one embodiment of the present invention. The operation of the embodiment of the present invention will be described in detail with reference to FIGS.

The operating state of the module 103 built in each fabric 101 is stored in the maintenance monitoring table 104 (step A1).

It is determined whether the timer 110 of the maintenance management means 107 has reached a preset time (step A2).

If the preset time has been reached, the operating status information of the maintenance monitoring table 104 of each fabric is collected from the monitoring means 109 (step A).
3).

The generation management of information is performed from the monitoring means 109 to the storage means 108 (step A4).

The comparing means 111 compares the latest information with the preceding information (step A5), judges the difference (step A6), and notifies the maintenance person via the reporting means 112 when there is a difference. (Step A7). On the other hand, if there is no difference, no report is made to the maintenance personnel (step A
8).

[0021]

As described above, according to the present invention,
If multiple fabrics connected in a meshing topology configuration become unusable due to an abnormality such as a failure, it is possible to detect the abnormal fabric before using it,
This has the effect of improving reliability and maintainability.

The reason for this is that, in the present invention, the maintenance management means is configured so that the maintenance monitoring table of each fabric is generation-managed and the comparing means can report an abnormal fabric such as a fault to a maintenance person.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of an embodiment of a fabric failure detection method according to the present invention.

FIG. 2 is a flowchart for explaining the operation of one embodiment of the fabric failure detection method according to the present invention.

FIG. 3 is a block diagram showing a conventional configuration.

[Explanation of symbols]

 101 Fabric 102 Internal Bus 103 Module 104 Maintenance Monitoring Table 105 Computer 106 Maintenance Interface 107 Maintenance Management Means 108 Storage Means 109 Monitoring Means 110 Timer 111 Comparison Means 112 Reporting Means 113 Fiber Channel

Continuation of front page (56) References JP-A-7-57175 (JP, A) JP-A-7-321786 (JP, A) JP-A-8-36415 (JP, A) JP-A-9-153394 (JP, A) JP-A-10-51447 (JP, A) Fiber Channel; Connection to the Future, (August 1995), by the Fiber Channel Association, pages. 25-35 NEC Technical Report, Vol. 50 No. 8, 1997, Takashi Iida et al., “Super Server Fiber Channel Fabric Switch for NX7000 Series”, pp. 31-34 (58) Fields investigated (Int. Cl. ⁷ , DB name) H04L 12/24 H04L 12/26 H04L 12 / 28 G06F 11/30

Claims (2)

(57) [Claims] 1. A failure detection method in a system in which switch devices (referred to as “fabrics”) in a fiber channel are connected in a multi-layered cascade (referred to as a “messing topology”), wherein each of the fabrics comprises: A maintenance monitoring table that stores an operation state of the provided module; and a maintenance management unit that connects to each of the fabrics via a predetermined maintenance interface.The maintenance management unit is provided at every predetermined time. Means for acquiring operation status information of the module of each fabric stored in the maintenance monitoring table of each fabric, and performing generation management and storage management of the acquired information; information of the latest generation and information of the previous generation When an abnormality is detected for a module of a certain fabric, Means for notifying, and a fabric failure detection method. 2. A failure detection method for a system in which switch devices (referred to as "fabrics") in a fiber channel are connected in a multi-tiered manner (referred to as a "messing topology"). Storing the operation state of the module of each fabric in the maintenance monitoring table via an internal bus, wherein the maintenance monitoring table is connected to a monitoring unit of a maintenance management unit via a maintenance interface; Further, timer means, storage means,
Comparing means, and reporting means, When the timer means has reached a preset time, from the monitoring means, information on the operating status of the module of the fabric stored in the maintenance monitoring table of each fabric Is collected by the storage unit and the information is generation-managed and stored by the storage unit. The comparison unit compares the information of the latest generation with the information of the previous generation stored before it, and as a result of the comparison, In this case, the fault is reported to a maintenance person via the reporting means.