CN103684918A - Method and device for detecting link failure - Google Patents

Abstract

The embodiment of the invention provides a method and device for detecting a link failure. The method comprises the steps that the detecting device collects the state information of corresponding ports of at least two nodes in an optical fiber channel network; the detecting device compares the state information of the corresponding ports of the at least two nodes, and whether the failure exists or not is determined according to a comparison result. According to the method and device for detecting the link failure, the problems that FC link detection in the prior art is not comprehensive, and the reliability of an FC network is low are solved.

Description

Link fault detection method and device

technical field

Embodiments of the present invention relate to communication technologies, and in particular to a link fault detection method and device.

Background technique

The Fiber Channel (FC for short) protocol is mainly used in the storage field and is a major way for servers to expand storage. The FC network can be specifically divided into storage area network (Storage Area Network, referred to as: SAN) and direct attached storage (Direct Attached Storage, referred to as: DAS). Among them, SAN is a high-speed dedicated subnet that connects disk arrays, tapes and other storage devices with related servers through fiber optic hubs, fiber optic routers, fiber optic switches and other connecting devices. In the DAS networking mode, the storage device is directly connected to the server through the cable, and the I/O (input/output) request is directly sent to the storage device. No matter what kind of networking, the entire link of FC includes multiple network nodes, such as host bus adapter (Host Bus Adapter, HBA for short), switch (Switch), disk array, etc. Any node failure on the link will cause the failure of the entire FC link.

Based on reliability considerations, FC storage usually adopts redundant networking, and multiple paths can be selected between the host and logical storage devices. When a path fails, the upper-layer multipath software automatically detects the failure and performs link switching to avoid service damage.

However, the existing technology is generally based on a single point detection of a node: for example, the status of the HBA card port, link status, link rate, optical module status, etc. are detected on the host side; the system temperature, voltage, optical module status, etc. are detected on the switch. Port changes, etc.; detect port status, optical modules, etc. on the storage array side. That is, the existing technology is performed on each node in the system independently, and each node can only perform the most basic detection. For some more complex errors, such as no fiber connection/fiber connection error, the peer device is not in place or Faults such as abnormalities cannot be detected, so the reliability of the FC network is still low.

Contents of the invention

Embodiments of the present invention provide a link fault detection method and device to overcome the problem of low reliability of the FC network due to incomplete FC link detection in the prior art.

In a first aspect, an embodiment of the present invention provides a link fault detection method, including:

The detection device collects state information of ports corresponding to each other of at least two nodes in the fiber channel network;

The detection device compares the state information of the ports corresponding to each other at least two nodes, and determines whether there is a fault according to the comparison result.

In a first possible implementation manner of the first aspect, the detection device collects state information corresponding to each other of at least two nodes in the fiber channel network, including:

The detection device collects state information of all ports of all nodes in the fiber channel network through the same interface.

In a second possible implementation manner of the first aspect, the state information of the port includes at least one of the following: port type, connection state, working mode, auto-negotiation result, and worldwide port name wwpn address.

According to the second possible implementation manner of the first aspect, in the third possible implementation manner, the node includes: a host bus adapter HBA, a switch Switch, and a storage device;

The detection device compares the status information of the ports corresponding to each other at least two nodes, and determines whether there is a fault according to the comparison result, including:

The detection device compares the wwpn address of the port of the HBA with the address of the device connected to the corresponding port on the Switch, if the wwpn address of the port of the HBA is inconsistent with the address of the device connected to the corresponding port on the Switch , it is determined that there is a fault between the HBA card and the Switch; or

The detection device compares the wwpn address of the port of the controller of the storage device with the address of the device connected to the corresponding port on the Switch, if the wwpn address of the port of the controller of the storage device is the same as that of the corresponding port on the Switch If the addresses of the connected devices are inconsistent, it is determined that there is a fault between the controller of the storage device and the Switch; or

The detection device judges whether the port types of the ports connected to different devices on the Switch are the same, and if they are the same, it is determined that there is a fault in the connection or configuration of the Switch.

According to the third possible implementation manner of the first aspect, in the fourth possible implementation manner, after the detection device determines that there is a fault between the HBA and the Switch, it further includes:

When the detection device determines that the wwpn address of the port of the HBA is not empty, and the wwpn address of the corresponding port on the Switch is empty, the detection device determines that the type of the fault is a link abnormality; or

When the detection device determines that the wwpn address of the port of the HBA and the wwpn of the corresponding port on the Switch are not empty, and the two wwpn addresses are inconsistent, the detection device determines that the type of the fault is the The above fault type is wrong connection.

According to the third possible implementation manner of the first aspect, in the fifth possible implementation manner, after the detection device determines that there is a fault between the controller of the storage device and the Switch, it further includes:

When the detection device determines that the wwpn address of the port of the controller of the storage device is not empty, and the wwpn address of the corresponding port on the Switch is empty, the detection device determines that the connection between the storage device and the Switch The type of fault between is link abnormal; or

When the detection device determines that the wwpn address of the port of the controller of the storage device and the address of the device connected to the corresponding port on the Switch are not empty, and the two wwpn addresses are inconsistent, the detection device It is determined that the type of the fault between the controller of the storage device and the Switch is that no optical fiber is connected between the controller of the storage device and the Switch.

According to the second possible implementation manner of the first aspect, in a sixth possible implementation manner, the node includes: a host bus adapter HBA and a storage device;

The detection device compares the status information of the ports corresponding to each other at least two nodes, and determines whether there is a fault according to the comparison result, including:

The detection device compares the wwpn address of the port of the HBA with the wwpn address of the controller of the storage device, and if the wwpn address of the port of the HBA is inconsistent with the wwpn address of the controller of the storage device, it is determined that the HBA There is a failure with the controller of the storage device.

According to the sixth possible implementation manner of the first aspect, in the seventh possible implementation manner, after the detection device determines that there is a fault between the HBA and the controller of the storage device, it further includes:

When the detecting device determines that the wwpn address of the port of the HBA is not empty, and the wwpn address of the corresponding port on the Switch is empty, the detecting device determines the connection between the HBA and the controller of the storage device The type of fault is a link anomaly; or

When the detecting means determines that neither the wwpn address of the port of the HBA nor the wwpn address of the controller of the storage device is empty and the two wwpn addresses are inconsistent, the detecting means determines that the HBA and the The type of failure between the controllers of the storage device is misconnection.

According to the second possible implementation manner of the first aspect, in an eighth possible implementation manner, the node includes: a first controller and a second controller of the storage device, and the first controller and the second The controllers are respectively connected to the host bus adapter HBA to form the first link and the second link, or respectively connected to the switch Switch to form the first link and the second link, the first controller and the second controller The links of each other are backups;

The detection device compares the status information of the ports corresponding to each other at least two nodes, and determines whether there is a fault according to the comparison result, including:

The detection device compares the wwpn address of the port of the first controller corresponding to the first link with the wwpn address of the port of the second controller corresponding to the second link, if the If the two wwpn addresses are inconsistent, it is determined that there is a fault in the connection of the storage device.

In a second aspect, an embodiment of the present invention provides a link fault detection device, including:

A collecting module, configured to collect state information of ports corresponding to each other of at least two nodes in the fiber channel network;

The determination module is configured to compare the status information of the ports corresponding to each other at least two nodes, and determine whether there is a fault according to the comparison result.

In a first possible implementation manner of the second aspect, the collection module is specifically configured to:

Collect status information for all ports of all nodes in the Fiber Channel network through the same interface.

In a second possible implementation manner of the second aspect, the state information of the port includes at least one of the following: port type, connection state, working mode, auto-negotiation result, and worldwide port name wwpn address.

According to a second possible implementation of the second aspect, in a third possible implementation, the node includes: a host bus adapter HBA, a switch Switch, and a storage device;

The determination module is specifically used for:

Compare the wwpn address of the port of the HBA with the address of the device connected to the corresponding port on the Switch, if the wwpn address of the port of the HBA is inconsistent with the address of the device connected to the corresponding port on the Switch, then determine the There is a fault between the HBA card and the Switch; or

Comparing the wwpn address of the port of the controller of the storage device with the address of the device connected to the corresponding port on the Switch, if the wwpn address of the port of the controller of the storage device is the same as the address of the device connected to the corresponding port on the Switch If the addresses are inconsistent, it is determined that there is a fault between the controller of the storage device and the Switch; or

It is judged whether the port types of the ports connected to different devices on the Switch are the same, and if they are the same, it is determined that there is a fault in the connection or configuration of the Switch.

According to a third possible implementation of the second aspect, in a fourth possible implementation, the determining module is further configured to:

When it is determined that the wwpn address of the port of the HBA is not empty, and the wwpn address of the corresponding port on the Switch is empty, it is determined that the type of the fault is a link exception; or

When it is determined that the wwpn address of the port of the HBA and the wwpn of the corresponding port on the Switch are not empty, and the two wwpn addresses are inconsistent, it is determined that the type of the fault is that the type of the fault is a misconnection.

According to a third possible implementation of the second aspect, in a fifth possible implementation, the determining module is further configured to:

When it is determined that the wwpn address of the port of the controller of the storage device is not empty, and the wwpn address of the corresponding port on the Switch is empty, determine that the type of failure between the storage device and the Switch is a link abnormal; or

When it is determined that the wwpn address of the port of the controller of the storage device and the address of the device connected to the corresponding port on the Switch are not empty, and the two wwpn addresses are inconsistent, then determine the controller of the storage device The type of the fault with the Switch is that the optical fiber is not connected between the controller of the storage device and the Switch.

According to a second possible implementation manner of the second aspect, in a sixth possible implementation manner, the node includes: a host bus adapter HBA and a storage device;

The determination module is specifically used for:

Comparing the wwpn address of the port of the HBA with the wwpn address of the controller of the storage device, if the wwpn address of the port of the HBA is inconsistent with the wwpn address of the controller of the storage device, it is determined that the HBA and the storage device There is a fault between the controllers of the device.

According to the sixth possible implementation manner of the second aspect, in a seventh possible implementation manner, the determining module is further configured to:

When it is determined that the wwpn address of the port of the HBA is not empty, and the wwpn address of the corresponding port on the Switch is empty, then the detection device determines that the type of fault between the HBA and the controller of the storage device is link abnormality; or

When it is determined that the wwpn address of the port of the HBA and the wwpn address of the controller of the storage device are not empty and the two wwpn addresses are inconsistent, determine the connection between the HBA and the controller of the storage device The type of failure is misconnection.

According to the second possible implementation manner of the second aspect, in an eighth possible implementation manner, the node includes: a first controller and a second controller of the storage device, and the first controller and the second The controllers are respectively connected to the host bus adapter HBA to form the first link and the second link, or respectively connected to the switch Switch to form the first link and the second link, the first controller and the second controller The links of each other are backups;

The determination module is specifically used for:

Comparing the wwpn address of the port of the first controller corresponding to the first link with the wwpn address of the port of the second controller corresponding to the second link, if the two wwpn addresses If they are inconsistent, it is determined that there is a fault in the connection of the storage device.

The link fault detection method and device provided by the embodiments of the present invention collect the state information of each port in the entire link uniformly, and compare the state information of the ports corresponding to each other at least two nodes to check the Whether the comparison result meets expectations, thereby judging whether there is a fault, compared with the detection method in the prior art, can detect more complex and hidden faults, thereby improving the reliability of the FC network.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained according to these drawings without any creative effort.

Fig. 1 is a schematic structural diagram of a typical SAN network;

Fig. 2 is a schematic structural diagram of a typical DAS network;

Fig. 3 is the flow chart of the embodiment of link fault detection method of the present invention;

FIG. 4 is a schematic structural diagram of an embodiment of a link fault detection device according to the present invention.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

FIG. 1 is a schematic structural diagram of a typical SAN network. As shown in FIG. 1 , the SAN network includes HBAs, switches, and disk arrays, wherein the disk array includes a controller and storage. In the SAN network shown in Figure 1, the primary link is the first switch (for example, Slot7FC Switch) with one end connected to the first controller (Controller A) of the disk array, and the other end connected to the zero port (port0 port) of the HBA. The backup link is that one end of the second switch (for example, Slot8FC Switch) is connected to the second controller (Controller B) of the disk array, and the other end is connected to port 1 (port1) of the HBA. If the optical fiber cable between the Slot8FC Switch and Controller B is not connected or damaged. Once the active link fails, the backup link is also unavailable, and the upper-layer services will be interrupted at this time.

Figure 2 is a schematic diagram of a typical DAS network structure. As shown in Figure 2, the FC network includes HBAs and disk arrays. A common connection method is: all HBA port zero (port0) connects to the first port of the disk array. One controller, Controller A; the first port (port1) of all HBA cards is connected to the second controller Controller B of the disk array. When port1 of an HBA fails, the port cannot be connected, and the upper-layer business will be interrupted.

FIG. 3 is a flow chart of an embodiment of a link fault detection method according to the present invention. The method of this embodiment can be applied to the FC network shown in FIG. 1 and FIG. 2 , and can also be applied to other FC networks. In this embodiment, the detection device may be a network management software process. As shown in Figure 3, the method of this embodiment may include:

Step 301, the detection device collects state information of ports corresponding to each other at least two nodes in the fiber channel network.

Wherein, the status information of the port includes at least one of the following: port type, connection status, working mode, auto-negotiation result and World Wide Port Name (WWPN) address. The status information may also include other parameters, such as whether the speeds of the ports at both ends of the link are the same, whether the WWPN number of the opposite end can be correctly obtained from one port, etc., which is not limited in this embodiment of the present invention.

Further, during specific implementation, it may be set that the detection device collects status information of all ports of all nodes in the fiber channel network through the same interface.

Compared with the detection method in the prior art, in this embodiment, the status information of the ports is collected in a unified manner: instead of being performed by each node separately.

Step 302, the detecting device compares the state information of the ports corresponding to each other at least two nodes, and determines whether there is a fault according to the comparison result.

Specifically, the detection device can verify whether the state information of all ports in the FC network meets expectations, and if the detected actual results do not meet expectations, it can be determined that there is a fault and an alarm can be reported.

In actual implementation, you can compare the wwpn address of the HBA card with the address of the device connected to the corresponding port on the Switch. If the corresponding port does not find the wwpn address, it means that the link between the HBA card and the Switch is abnormal. If the wwpn address is wrong, it means that there is an error. connect;

You can also compare the wwpn address of the storage device controller with the address of the device connected to the corresponding port on the Switch. If the wwpn address is not found on the corresponding port, it means that the link between the storage device and the Switch is abnormal. No fiber is connected between the switches.

In addition, the port types of ports connected to different devices on the switch should be different. Therefore, by judging the port type, it can also be determined whether there is a configuration error or a connection error.

In this embodiment, by uniformly collecting the state information of each port in the entire link, and comparing the state information of at least two corresponding ports of the nodes, checking whether the comparison result meets expectations, thereby judging whether there is The fault, compared with the detection method in the prior art, can detect more complex and hidden faults, thereby improving the reliability of the FC network.

Optionally, in a scenario, when the method of the foregoing embodiment is applied to a SAN network, the nodes include: a host bus adapter HBA, a switch Switch, and a storage device, and step 302 is specifically:

The detection device compares the wwpn address of the port of the HBA with the address of the device connected to the corresponding port on the Switch, if the wwpn address of the port of the HBA is inconsistent with the address of the device connected to the corresponding port on the Switch , it is determined that there is a fault between the HBA card and the Switch; or

The detection device compares the wwpn address of the port of the controller of the storage device with the address of the device connected to the corresponding port on the Switch, if the wwpn address of the port of the controller of the storage device is the same as that of the corresponding port on the Switch If the addresses of the connected devices are inconsistent, it is determined that there is a fault between the controller of the storage device and the Switch; or

The detection device judges whether the port types of the ports connected to different devices on the Switch are the same, and if they are the same, it is determined that there is a fault in the connection or configuration of the Switch.

Further optionally, if the detection device determines that there is a fault between the HBA and the Switch, after step 302, it may further include:

When the detection device determines that the wwpn address of the port of the HBA is not empty, and the wwpn address of the corresponding port on the Switch is empty, the detection device determines that the type of the fault is a link abnormality; or

When the detection device determines that the wwpn address of the port of the HBA and the wwpn of the corresponding port on the Switch are not empty, and the two wwpn addresses are inconsistent, the detection device determines that the type of the fault is the The above fault type is wrong connection.

Further optionally, if the detecting device determines that there is a fault between the controller of the storage device and the Switch, after step 302, it may further include:

When the detection device determines that the wwpn address of the port of the controller of the storage device is not empty, and the wwpn address of the corresponding port on the Switch is empty, the detection device determines that the connection between the storage device and the Switch The type of fault between is link abnormal; or

When the detection device determines that the wwpn address of the port of the controller of the storage device and the address of the device connected to the corresponding port on the Switch are not empty, and the two wwpn addresses are inconsistent, the detection device It is determined that the type of the fault between the controller of the storage device and the Switch is that no optical fiber is connected between the controller of the storage device and the Switch.

Taking the main link of the SAN network shown in Figure 1 as an example, step 302 can specifically be: the detection device compares the wwpn address of the port0 port of the HBA with the address of the connected device on the corresponding port on the Slot7FC Switch, if the If the wwpn address of the port0 port of the HBA is inconsistent with the address of the connected device on the corresponding port on the Slot7FCSwitch, then it is determined that there is a fault between the HBA and the Slot7FCSwitch; The wwpn address of the corresponding port on the Slot7FC Switch is compared with the address of the device connected to the corresponding port. If the wwpn address of the port of Controller A of the disk array is inconsistent with the address of the device connected to the corresponding port on the Slot7FC Switch, determine the address of the device connected to the corresponding port of the disk array. There is a fault between the controller and Controller A; and/or, the detection device judges whether the port types of ports connected to different devices on Controller A are the same, and if they are the same, it is determined that there is a fault in the connection or configuration of the Switch.

The detection of the standby link is similar to the above detection of the primary link, as long as the corresponding equipment and ports are replaced with the equipment and ports in the standby link. If the detection result of the standby link is: the wwpn address of port1 port of all connected HABs can be queried on the Slot8FC Switch, but the wwpn address of the disk array controller Controller B cannot be queried on the port connected to the disk array, then you can If it is determined that there is a wrong connection or an abnormal connection in the backup link, an alarm can be generated at this time to prompt the user to check the status of the backup link.

Optionally, in another scenario, when the method in the foregoing embodiment is applied to a DSA network, the nodes include: a host bus adapter HBA and a storage device;

Step 302 is specifically:

The detection device compares the wwpn address of the port of the HBA with the wwpn address of the controller of the storage device, and if the wwpn address of the port of the HBA is inconsistent with the wwpn address of the controller of the storage device, it is determined that the HBA There is a failure with the controller of the storage device.

Further, if the detecting device determines that there is a fault between the HBA and the controller of the storage device, after step 302, it may further include:

When the detecting device determines that the wwpn address of the port of the HBA is not empty, and the wwpn address of the corresponding port on the Switch is empty, the detecting device determines the connection between the HBA and the controller of the storage device The type of failure is a link anomaly; or

When the detecting means determines that neither the wwpn address of the port of the HBA nor the wwpn address of the controller of the storage device is empty and the two wwpn addresses are inconsistent, the detecting means determines that the HBA and the The type of failure between the controllers of the storage device is misconnection.

Taking the main link of the DAS network shown in FIG. 2 as an example, step 302 may specifically be:

The detection device compares the wwpn address of the port0 port of the HBA with the wwpn address of the ControllerA of the disk array, if the wwpn address of the port0 port of the HBA is inconsistent with the wwpn address of the Controller A of the disk array, it can be determined that the There is a fault between the HBA and the controller of the storage device.

In another application scenario of the link fault detection method of the present invention, the node includes: a first controller and a second controller of the storage device, and the first controller and the second controller are respectively connected to the host bus adapter The HBA is connected to form a first link and a second link, or is respectively connected to a switch Switch to form a first link and a second link, and the links of the first controller and the second controller are mutually backed up;

Step 302 may include:

The detection device compares the wwpn address of the port of the first controller corresponding to the first link with the wwpn address of the port of the second controller corresponding to the second link, if the If the two wwpn addresses are inconsistent, it is determined that there is a fault in the connection of the storage device.

For example, for the FC network in Figure 1 or Figure 2, the wwpn addresses of the corresponding ports of Controller A and Controller B can be compared, if the wwpn addresses of the two corresponding ports are inconsistent, it can be determined that the connection of the storage device is faulty. For example, if it is detected that Controller A has the wwpn address of the connected device on a certain port, but the corresponding port on Controller B does not find the wwpn address of the connected device, it can be determined that there is a failure in the connection of the storage device, and an alarm can be generated at this time , prompting the user to troubleshoot.

FIG. 4 is a schematic structural diagram of an embodiment of a link fault detection device according to the present invention. As shown in FIG. 4 , the device 400 of this embodiment may include: a collection module 11 and a determination module 12, wherein,

The collection module 11 can be used to collect state information of ports corresponding to each other of at least two nodes in the fiber channel network;

The determination module 12 may be configured to compare the status information of the ports corresponding to each other at least two nodes, and determine whether there is a fault according to the comparison result.

The device of this embodiment can be used to implement the technical solution of the method embodiment shown in FIG. 3 , and its implementation principles are similar, so details are not repeated here.

In the embodiment of the link fault detection device in this embodiment, the state information of each port in the entire link is uniformly collected, and the state information of at least two corresponding ports of the nodes is compared to check the comparison result Whether it meets expectations, so as to determine whether there is a fault. Compared with the detection method in the prior art, it can detect more complex and hidden faults, thereby improving the reliability of the FC network.

Further optionally, the collection module 11 can specifically be used for:

Collect status information for all ports of all nodes in the Fiber Channel network through the same interface.

Further optionally, the state information of the port includes at least one of the following: port type, connection state, working mode, auto-negotiation result and worldwide port name wwpn address.

Further optionally, the node includes: a host bus adapter HBA, a switch Switch, and a storage device;

The determination module 12 can specifically be used for:

Compare the wwpn address of the port of the HBA with the address of the device connected to the corresponding port on the Switch, if the wwpn address of the port of the HBA is inconsistent with the address of the device connected to the corresponding port on the Switch, then determine the There is a fault between the HBA card and the Switch; or

Comparing the wwpn address of the port of the controller of the storage device with the address of the device connected to the corresponding port on the Switch, if the wwpn address of the port of the controller of the storage device is the same as the address of the device connected to the corresponding port on the Switch If the addresses are inconsistent, it is determined that there is a fault between the controller of the storage device and the Switch; or

It is judged whether the port types of ports connected to different devices on the Switch are the same, and if they are the same, it is determined that there is a fault in the connection or configuration of the Switch.

Further optionally, the determining module 12 may also be used for:

When it is determined that the wwpn address of the port of the HBA is not empty, and the wwpn address of the corresponding port on the Switch is empty, it is determined that the type of the fault is a link exception; or

When it is determined that the wwpn address of the port of the HBA and the wwpn of the corresponding port on the Switch are not empty, and the two wwpn addresses are inconsistent, it is determined that the type of the fault is that the type of the fault is a misconnection.

Further optionally, the determining module 12 may also be used for:

When it is determined that the wwpn address of the port of the controller of the storage device is not empty, and the wwpn address of the corresponding port on the Switch is empty, determine that the type of failure between the storage device and the Switch is a link abnormal; or

When it is determined that the wwpn address of the port of the controller of the storage device and the address of the device connected to the corresponding port on the Switch are not empty, and the two wwpn addresses are inconsistent, then determine the controller of the storage device The type of the fault with the Switch is that the optical fiber is not connected between the controller of the storage device and the Switch.

Further optionally, the node may include: a host bus adapter HBA and a storage device;

The determination module 12 can specifically be used for:

Comparing the wwpn address of the port of the HBA with the wwpn address of the controller of the storage device, if the wwpn address of the port of the HBA is inconsistent with the wwpn address of the controller of the storage device, it is determined that the HBA and the storage device There is a fault between the controllers of the device.

Further optionally, the determining module 12 may also be used for:

When it is determined that the wwpn address of the port of the HBA is not empty, and the wwpn address of the corresponding port on the Switch is empty, then the detection device determines that the type of fault between the HBA and the controller of the storage device is link abnormality; or

When it is determined that the wwpn address of the port of the HBA and the wwpn address of the controller of the storage device are not empty and the two wwpn addresses are inconsistent, determine the connection between the HBA and the controller of the storage device The type of failure is misconnection.

Further optionally, the node may include: a first controller and a second controller of the storage device, the first controller and the second controller are respectively connected to the host bus adapter HBA to form the first link and the second link. Two links, or respectively connected to the switch Switch to form a first link and a second link, and the links of the first controller and the second controller are mutually backup;

The determination module 12 can specifically be used for:

Comparing the wwpn address of the port of the first controller corresponding to the first link with the wwpn address of the port of the second controller corresponding to the second link, if the two wwpn addresses If they are inconsistent, it is determined that there is a fault in the connection of the storage device.

Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by program instructions and related hardware. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above-mentioned method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other various media that can store program codes.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the various embodiments of the present invention. scope.

Claims (18)

1. a link failure detection method, is characterized in that, comprising:

Checkout gear is collected the state information of the port in correspondence with each other of at least two nodes in fibre channel networks;

Described checkout gear compares the state information of the port in correspondence with each other of at least two described nodes, according to comparative result, determines whether to exist fault.

2. method according to claim 1, is characterized in that, described checkout gear is collected the state information in correspondence with each other of at least two nodes in fibre channel networks, comprising:

Described checkout gear is collected the state information of all of the port of all nodes in fibre channel networks by same interface.

3. method according to claim 1, is characterized in that, the state information of described port comprise following at least one: port type, connection status, mode of operation, auto-negotiation result and worldwide port name claim wwpn address.

4. method according to claim 3, is characterized in that, described node comprises: host bus adaptor HBA, switch Switch and memory device;

Described checkout gear compares the state information of the port in correspondence with each other of at least two described nodes, according to comparative result, determines whether to exist fault, comprising:

Described checkout gear compares the address of the wwpn address of the port of described HBA and the upper corresponding ports connected device of described Switch, if the address of the upper corresponding ports connected device of the wwpn address of the port of described HBA and described Switch is inconsistent, determines between described HBA card and described Switch and have fault; Or

Described checkout gear compares the address of the wwpn address of the port of the controller of described memory device and the upper corresponding ports connected device of Switch, if the address of the upper corresponding ports connected device of the wwpn address of the port of the controller of described memory device and described Switch is inconsistent, between the controller of definite described memory device and described Switch, there is fault; Or

Described checkout gear judges that whether the port type of the port that connects distinct device on described Switch is identical, if identical, determines that connection or the configuration of described Switch exists fault.

5. method according to claim 4, is characterized in that, after described checkout gear determines there is fault between described HBA and described Switch, also comprises:

When the wwpn address of port that described checkout gear is determined described HBA is for empty, and the wwpn address of the upper corresponding ports of described Switch is while be sky, and described checkout gear determines that the type of described fault is that link is abnormal; Or

When described checkout gear determines that the wwpn address of port of described HBA and the wwpn of the upper corresponding ports of described Switch are not all sky, and when described two wwpn addresses are inconsistent, described checkout gear determines that the type that the type of described fault is described fault is mistake connection.

6. method according to claim 4, is characterized in that, after described checkout gear determines there is fault between the controller of described memory device and described Switch, also comprises:

When the wwpn address of port of controller that described checkout gear is determined described memory device is for empty, and the wwpn address of the upper corresponding ports of described Switch is while be sky, described checkout gear determines that the type of the fault between described memory device and described Switch is that link is abnormal; Or

The wwpn address of port and the address of the upper corresponding ports connected device of described Switch of when described checkout gear, determining the controller of described memory device are not all sky, and when described two wwpn addresses are inconsistent, between the controller that the type of the fault between the controller that described checkout gear is determined described memory device and described Switch is described memory device and described Switch, be not connected optical fiber.

7. method according to claim 3, is characterized in that, described node comprises: host bus adaptor HBA and memory device;

Described checkout gear compares the state information of the port in correspondence with each other of at least two described nodes, according to comparative result, determines whether to exist fault, comprising:

Described checkout gear compares the wwpn address of the controller of the wwpn address of the port of HBA and memory device, if the wwpn address of the controller of the wwpn address of the port of described HBA and described memory device is inconsistent, determines between described HBA and the controller of described memory device and have fault.

8. method according to claim 7, is characterized in that, after described checkout gear determines there is fault between described HBA and the controller of described memory device, also comprises:

When the wwpn address of port that described checkout gear is determined described HBA is for empty, and the wwpn address of the upper corresponding ports of described Switch is while be sky, and checkout gear determines that the type of the fault between described HBA and the controller of described memory device is that link is abnormal; Or

When described checkout gear determines that the wwpn address of port of described HBA and the wwpn address of the controller of described memory device are all for empty and described two wwpn addresses are when inconsistent, described checkout gear determines that the type of the fault between the controller of described HBA and described memory device is connected for missing.

9. method according to claim 3, it is characterized in that, described node comprises: the first controller and the second controller of memory device, described the first controller is connected with host bus adaptor HBA respectively with second controller, form the first link and the second link, or be connected with switch Switch respectively, forming the first link and the second link, the link of described the first controller and second controller backups each other;

Described checkout gear compares the state information of the port in correspondence with each other of at least two described nodes, according to comparative result, determines whether to exist fault, comprising:

Described checkout gear compares the wwpn address of the port of the wwpn address of the port of described the first controller corresponding to described the first link described second controller corresponding with described the second link, if described two wwpn addresses are inconsistent, determine that the connection of described memory device exists fault.

10. a link failure detection device, is characterized in that, comprising:

Collection module, for collecting the state information of the port in correspondence with each other of at least two nodes of fibre channel networks;

Determination module, for the state information of the port in correspondence with each other of at least two described nodes is compared, determines whether to exist fault according to comparative result.

11. devices according to claim 10, is characterized in that, described collection module specifically for:

By same interface, collect the state information of all of the port of all nodes in fibre channel networks.

12. devices according to claim 10, is characterized in that, the state information of described port comprise following at least one: port type, connection status, mode of operation, auto-negotiation result and worldwide port name claim wwpn address.

13. devices according to claim 12, is characterized in that, described node comprises: host bus adaptor HBA, switch Switch and memory device;

Described determination module specifically for:

The address of the wwpn address of the port of described HBA and the upper corresponding ports connected device of described Switch is compared, if the address of the upper corresponding ports connected device of the wwpn address of the port of described HBA and described Switch is inconsistent, determines between described HBA card and described Switch and have fault; Or

The address of the wwpn address of the port of the controller of described memory device and the upper corresponding ports connected device of Switch is compared, if the address of the upper corresponding ports connected device of the wwpn address of the port of the controller of described memory device and described Switch is inconsistent, between the controller of definite described memory device and described Switch, there is fault; Or

Whether the port type that judges the port that connects distinct device on described Switch is identical, if identical, determines that connection or the configuration of described Switch exists fault.

14. devices according to claim 13, is characterized in that, described determination module also for:

When determining that the wwpn address of the port of described HBA be empty, and the wwpn address of the upper corresponding ports of described Switch is while being sky, and the type of determining described fault is that link is abnormal; Or

When determining that the wwpn address of port and the wwpn of the upper corresponding ports of described Switch of described HBA be all empty, and described two wwpn addresses are when inconsistent, and the type that the type of determining described fault is described fault is connection by mistake.

15. devices according to claim 13, is characterized in that, described determination module also for:

When determining that the wwpn address of port of the controller of described memory device be empty, and the wwpn address of the upper corresponding ports of described Switch is while being sky, and the type of determining the fault between described memory device and described Switch is that link is abnormal; Or

When determining that the wwpn address of port and the address of the upper corresponding ports connected device of described Switch of the controller of described memory device is not all empty, and when described two wwpn addresses are inconsistent, between the controller that the type of the fault between the controller of determining described memory device and described Switch is described memory device and described Switch, be not connected optical fiber.

16. devices according to claim 12, is characterized in that, described node comprises: host bus adaptor HBA and memory device;

Described determination module specifically for:

The wwpn address of the controller of the wwpn address of the port of HBA and memory device is compared, if the wwpn address of the controller of the wwpn address of the port of described HBA and described memory device is inconsistent, determines between described HBA and the controller of described memory device and have fault.

17. devices according to claim 16, is characterized in that, described determination module also for:

When determining that the wwpn address of the port of described HBA be empty, and the wwpn address of the upper corresponding ports of described Switch is while being sky, and checkout gear determines that the type of the fault between described HBA and the controller of described memory device is that link is abnormal; Or

When definite wwpn address of port of described HBA and the wwpn address of the controller of described memory device are not all empty and when described two wwpn addresses are inconsistent, determine that the type of the fault between the controller of described HBA and described memory device is connected for missing.

18. devices according to claim 12, it is characterized in that, described node comprises: the first controller and the second controller of memory device, described the first controller is connected with host bus adaptor HBA respectively with second controller, form the first link and the second link, or be connected with switch Switch respectively, forming the first link and the second link, the link of described the first controller and second controller backups each other;

Described determination module specifically for:

The wwpn address of the port of the wwpn address of the port of described the first controller corresponding to described the first link described second controller corresponding with described the second link is compared, if described two wwpn addresses are inconsistent, determine that the connection of described memory device exists fault.

Images