CN103475695A - Interconnection method and device for storage system - Google Patents
Interconnection method and device for storage system Download PDFInfo
- Publication number
- CN103475695A CN103475695A CN2013103668424A CN201310366842A CN103475695A CN 103475695 A CN103475695 A CN 103475695A CN 2013103668424 A CN2013103668424 A CN 2013103668424A CN 201310366842 A CN201310366842 A CN 201310366842A CN 103475695 A CN103475695 A CN 103475695A
- Authority
- CN
- China
- Prior art keywords
- node
- hard disk
- processor
- disk unit
- sas
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000004044 response Effects 0.000 claims description 57
- 238000006243 chemical reaction Methods 0.000 claims description 48
- 238000012544 monitoring process Methods 0.000 claims description 14
- 238000010586 diagram Methods 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Images
Landscapes
- Debugging And Monitoring (AREA)
Abstract
The invention provides an interconnection method and device for a storage system. A first processor is connected with a second processor of a second node to obtain a heartbeat signal of the second processor of the second node and judge whether the second node fails or not according to the heartbeat signal; when the first processor judges that the second node fails according to the heartbeat signal, the first processor can access at least one second hard disk unit of the second node through a first interconnection hard disk channel between the first processor and the second node. The second hard disk unit of the second node can be taken over when the second node fails, so that the normal use of data in the second hard disk unit can be ensured on the premise of not wasting resources of the second node.
Description
Technical Field
The present invention relates to communications technologies, and in particular, to a storage system interconnection method and apparatus.
Background
In the current big data era, a distributed storage system presents a uniform access space to the outside by storing data on a plurality of nodes in a scattered manner. Each node is both a storage providing capacity and a head-end supporting front-end access. When the number of nodes reaches a certain number, the performance and capacity of the nodes far exceed those of the traditional storage system, and simultaneously higher reliability and expandability are provided.
In a distributed storage system, a single-control storage server is generally adopted, and if a single-node storage server fails, a hard disk in the node cannot be accessed, so that the availability of data is seriously reduced. Therefore, it will become very significant in a node having a large capacity to improve the usability of data by software or hardware. Fig. 1 is a schematic diagram of a distributed node in the prior art, and as shown in fig. 1, a standard x86 server is adopted for a node 1, which mainly includes a motherboard 10, a backplane 11, and a hard disk unit 12. The CPU101 of the motherboard 10 is connected to the SAS controller 102 through a PCIE Interface, and the Serial Attached Small Computer System Interface (SAS) controller 102 outputs the SAS Interface and is connected to the backplane 11 through a cable or a connector. The back board expands the number of SAS channels required by the system through the SAS Expander 110 (SAS Expander), and the hard disk unit 12 is connected to the back board 11 through a connector. In the prior art, nodes all adopt a node 1 structure, and hard disk access channels between the nodes are completely independent, so that when one node in a plurality of nodes fails, data of all hard disks in the node cannot be accessed. In order to solve the problem of node failure, in the prior art, higher availability of data is generally ensured in a distributed storage system through an upper layer software means. For example, when the service data is written, redundant data is generated by Erasure Codes (Erasure Codes) or Mirror algorithms (Mirror), and when the node fails, the data is recovered by reconstruction algorithms.
However, when the prior art is adopted, reconstruction overhead of a large-capacity node is often too large. At present, the capacity of a large-capacity node is about 100TB to 200TB, and the reconstruction time of 1TB data is usually 1 hour, so the data recovery time of one large-capacity node reaches more than 100 hours. And the effective utilization of the hard disk space is reduced. For example, in some application scenarios (such as data backup) where data mirroring between nodes is required, the effective utilization of space will be reduced by 50%, which indirectly results in an increase in the cost per capacity and a decrease in the capacity specification.
Disclosure of Invention
The invention provides a storage system interconnection method and device, which are used for ensuring that a hard disk unit of a node can still be accessed when the node fails on the premise of not reducing the utilization rate of node resources.
A first aspect of the present invention provides a node comprising: a first processor;
the first processor is connected with a second processor of a second node and used for acquiring a heartbeat signal of the second processor of the second node and judging whether the second node has a fault or not according to the heartbeat signal;
the first processor is further configured to access at least one second hard disk unit of the second node through a first interconnection hard disk channel between the first processor and the second node after the first processor determines that the second node has a fault according to the heartbeat signal.
In a first possible implementation manner of the first aspect, the first interconnected hard disk channel is a channel between a first serial small computer system interface SAS controller of the first node and a second SAS expander of the second node;
the first SAS controller of the first node is configured to perform protocol conversion on an access request sent by the first processor to at least one second hard disk unit of the second node, so that the at least one second hard disk unit of the second node can respond after receiving the access request, and perform protocol conversion on a response message sent by the second hard disk unit of the second node to the first processor, so that the first processor performs read-write operation on the at least one second hard disk unit of the second node according to the response message.
In a second possible implementation manner of the first aspect, the first interconnected hard disk channel is a channel between a first serial small computer system interface SAS controller of a first node, a first SAS expander of the first node, and a second SAS expander of the second node;
the first SAS controller of the first node is configured to perform protocol conversion on an access request sent by the first processor to the second hard disk unit of the second node, so that the second hard disk unit of the second node can respond after receiving the access request, and perform protocol conversion on a response message sent by the second hard disk unit of the second node to the first processor, so that the first processor performs read-write operation on the second hard disk unit of the second node according to the response message;
the first SAS expander of the first node is configured to interface with a second SAS expander of the second node.
In a third possible implementation manner of the first aspect, the first interconnected hard disk channel is a channel between a third serial small computer system interface SAS controller of the first node and a second SAS expander of the second node;
the third SAS controller of the first node is configured to perform protocol conversion on an access request sent by the first processor to the at least one second hard disk unit of the second node, so that the at least one second hard disk unit of the second node can respond after receiving the access request, and perform protocol conversion on a response message sent by the at least one second hard disk unit of the second node to the first processor, so that the first processor performs read-write operation on the at least one second hard disk unit of the second node according to the response message.
With reference to the foregoing possible implementation manners of the first aspect, in a fourth possible implementation manner of the first aspect, the first processor is further configured to, when a failure occurs in the first node, enable the second processor of the second node to know that the failure occurs in the first node through a heartbeat signal;
at least one first hard disk unit of a first node is connected with a second processor of a second node through a second interconnection hard disk channel, and the first processor enables the second processor of the second node to know that the first node is in fault through a heartbeat signal, so that the second processor of the second node accesses the at least one first hard disk unit of the first node through the second interconnection hard disk channel between the second processor of the second node and the first node;
and the at least one first hard disk unit of the first node is used for storing data.
With reference to the fourth possible implementation manner of the first aspect, in a fifth possible implementation manner of the first aspect, the second interconnected hard disk channel is a channel between a first SAS expander of the first node and a second SAS controller of the second node;
and the first SAS expander of the first node is used for expanding the second interconnected hard disk channel to at least one first hard disk unit of the first node.
With reference to the fourth possible implementation manner of the first aspect, in a sixth possible implementation manner of the first aspect, the second interconnected hard disk channel is a channel between a first SAS expander of the first node, a second SAS controller of the second node, and a second SAS expander of the second node;
and the first SAS expander of the first node is used for expanding the second interconnected hard disk channel to at least one first hard disk unit of the first node.
With reference to the fourth possible implementation manner of the first aspect, in a seventh possible implementation manner of the first aspect, the second interconnected hard disk channel is a channel between a first SAS expander of the first node and a fourth SAS controller of the second node;
and the first SAS expander of the first node is used for expanding the second interconnected hard disk channel to at least one first hard disk unit of the first node.
With reference to the first aspect and the foregoing various possible implementation manners of the first aspect, in an eighth possible implementation manner of the first aspect, the first processor is connected to a local hard disk channel, and is configured to access the first hard disk unit through the local hard disk channel.
With reference to the eighth possible implementation manner of the first aspect, in a ninth possible implementation manner of the first aspect, the local hard disk channel is a channel between a first SAS controller of the first node and a first SAS expander of the first node;
the first SAS controller of the first node is configured to perform protocol conversion on an access request sent by the first processor to the first hard disk unit of the first node, so that the first hard disk unit of the first node can respond after receiving the access request, and perform protocol conversion on a response message sent by the first hard disk unit of the first node to the first processor, so that the first processor performs read-write operation on the first hard disk unit of the first node according to the response message;
and the first SAS expander of the first node is used for expanding the local hard disk channel to at least one first hard disk unit.
With reference to the first aspect and the foregoing various possible implementation manners of the first aspect, in a tenth possible implementation manner of the first aspect, the first processor is further configured to perform a hard disk discovery operation to discover a second hard disk unit of the second node;
the first processor is further configured to establish an SAS topological structure, where the SAS topological structure includes the first interconnected hard disk channel and the local hard disk channel.
With reference to the first aspect and the foregoing possible implementation manners of the first aspect, in an eleventh possible implementation manner of the first aspect, the first processor is further configured to, after it is determined that the second node has a fault according to the heartbeat signal, wait for at least one second hard disk unit of the second node to complete a current command, and then access the at least one second hard disk unit of the second node through the first interconnection hard disk channel;
or, after judging that the second node has a fault according to the heartbeat signal, clearing the association relationship between the second SAS controller of the second node and the at least one second hard disk node of the second node, which is included in the STP connection, establishing the association relationship between the first SAS controller of the first node and the at least one second hard disk node of the second node, and accessing the at least one second hard disk unit of the second node through the first interconnected hard disk channel.
With reference to the first aspect and the foregoing various possible implementation manners of the first aspect, in a twelfth possible implementation manner of the first aspect, the first SAS controller and the first processor of the first node are disposed on a motherboard of the first node; the first SAS expander of the first node is arranged on the back plate of the first node; or,
the first SAS controller of the first node, the third SAS controller of the first node, and the first processor are disposed on a motherboard of the first node, and the first SAS expander of the first node is disposed on a SAS expansion board of the first node;
the system power supply of the first node, the fan controller of the first node and the monitoring module of the first node are arranged on the back plate of the first node; or,
the system power supply of the first node, the fan controller of the first node and the monitoring module of the first node are disposed on the SAS expander of the first node;
the system power supply of the first node is used for providing power for a first SAS controller of the first node, the first processor, a first SAS expander of the first node, a third SAS controller of the first node and a first hard disk unit of the first node;
the fan controller of the first node is configured to control a fan to dissipate heat of a first SAS controller of the first node, the first processor, a first SAS expander of the first node, a third SAS controller of the first node, and a first hard disk unit of the first node;
and the monitoring module of the first node is used for controlling the system power supply of the first node, the fan controller of the first node and monitoring the temperature.
The second aspect of the present invention provides a storage system interconnection method, including:
acquiring a heartbeat signal of a second processor of the second node, and judging whether the second node has a fault according to the heartbeat signal;
and if the second node fails, accessing at least one second hard disk unit of the second node through the first interconnection hard disk channel.
In a first possible implementation manner of the second aspect, the accessing, by the first interconnection hard disk channel, the at least one second hard disk unit of the second node includes:
sending an access request to at least one second hard disk unit of the second node;
performing protocol conversion on the access request so that at least one second hard disk unit of the second node can respond after receiving the access request;
receiving a response message sent by a second hard disk unit of the second node;
carrying out protocol conversion on the response message;
and performing read-write operation on at least one second hard disk unit of the second node according to the response message.
With reference to the second aspect and the first possible implementation manner of the second aspect, in a second possible implementation manner of the second aspect, the method further includes:
when a first node fails, a second processor of a second node learns that the first node fails through a heartbeat signal;
and when the second processor of the second node receives the heartbeat signal and learns that the first node is in fault, allowing the second processor of the second node to access at least one first hard disk unit of the first node through the second interconnection hard disk channel.
With reference to the second possible implementation manner of the second aspect, in a third possible implementation manner of the second aspect, the allowing the second processor of the second node to access the at least one first hard disk unit of the first node through the second interconnection hard disk channel includes:
receiving an access request sent by a second processor of the second node to at least one first hard disk unit of the first node;
performing protocol conversion on the access request so that at least one first hard disk unit of the first node can respond after receiving the access request;
receiving a response message sent by at least one first hard disk unit of the first node to a second processor of the second node;
and performing protocol conversion on the response message so that the second processor of the second node performs read-write operation on at least one first hard disk unit of the first node according to the response message.
With reference to the second aspect and the foregoing various possible implementation manners of the second aspect, in a fourth possible implementation manner of the second aspect, the method further includes: and accessing the first hard disk unit through the local hard disk channel.
With reference to the fourth possible implementation manner of the second aspect, in a fifth possible implementation manner of the second aspect, the accessing the first hard disk unit through the local hard disk channel includes:
sending an access request to a first hard disk unit of the first node;
performing protocol conversion on the access request so that a first hard disk unit of the first node can respond after receiving the access request;
receiving a response message sent by a first hard disk unit of the first node;
and performing protocol conversion on the response message so that the first processor performs read-write operation on the first hard disk unit of the first node according to the response message.
With reference to the second aspect and the foregoing various possible implementation manners of the second aspect, in a sixth possible implementation manner of the second aspect, a hard disk discovery operation is performed to discover a second hard disk unit of the second node;
and establishing a serial small computer system interface (SAS) topological structure, wherein the SAS topological structure comprises the first interconnected hard disk channel and the local hard disk channel.
With reference to the second aspect and the foregoing various possible implementation manners of the second aspect, in a seventh possible implementation manner of the second aspect, if it is determined that the second node fails according to the heartbeat signal, accessing at least one second hard disk unit of the second node through the first interconnection hard disk channel includes accessing the at least one second hard disk unit of the second node through the first interconnection hard disk channel
After judging that the second node has a fault according to the heartbeat signal, waiting for a second hard disk unit of the second node to complete a current command, and accessing the second hard disk unit of the second node through the first interconnection hard disk channel;
or, after judging that the second node has a fault according to the heartbeat signal, clearing the incidence relation between the second SAS controller of the second node and the second hard disk node of the second node included in the STP connection, establishing the incidence relation between the first SAS controller of the first node and the second hard disk node of the second node, and accessing the second hard disk unit of the second node through the first interconnected hard disk channel.
The storage system interconnection method and device provided by the embodiment of the invention have the advantages that the first processor of the node is connected with the second processor of the second node, the first processor acquires a heartbeat signal of the second processor of the second node and judges whether the second node fails according to the heartbeat signal, the first processor is connected with at least one second hard disk unit of the second node through the first interconnection hard disk channel, and when the first processor judges that the second node fails according to the heartbeat signal, the first processor accesses the at least one second hard disk unit of the second node through the first interconnection hard disk channel, so that the second hard disk unit of the second node is taken over when the second node fails, and the normal use of data in the second hard disk unit is ensured on the premise of not wasting resources of the second node.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic diagram of a distributed node in the prior art;
fig. 2 is a schematic diagram of connection between nodes according to an embodiment of the present invention;
fig. 3 is a schematic diagram illustrating connection between nodes according to a second embodiment of the present invention;
fig. 4 is a schematic diagram of connection between nodes according to a third embodiment of the present invention;
fig. 5 is a schematic diagram illustrating connection between nodes according to a fourth embodiment of the present invention;
fig. 6 is a schematic flowchart of a storage system interconnection method according to a ninth embodiment of the present invention;
fig. 7 is a schematic flowchart of a storage system interconnection method according to a tenth embodiment of the present invention;
fig. 8 is a schematic flowchart of a storage system interconnection method according to an eleventh embodiment of the present invention.
Detailed Description
In order to make the objects, 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 with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In each embodiment of the invention, a hard disk SAS interconnection channel and a heartbeat detection channel between nodes are provided through bottom hardware. When the system works normally, the processor of one node only accesses the hard disk in the node, and simultaneously detects the health state of the opposite node through the heartbeat signal. When the failure of the opposite end node is found, the local node takes over the hard disk of the failed node through a Serial Attached Small Computer system interface (SAS for short) interconnection channel, so that the hard disk data of the failed node can be continuously accessed. In this way, the adjacent nodes have a mutual aid relationship at the bottom hardware level, which avoids huge computation overhead and space overhead of data recovery through upper software. The embodiments of the present invention will be described in detail with reference to specific examples.
Fig. 2 is a schematic diagram of connection between nodes according to a first embodiment of the present invention, and it should be noted that the first node 20 shown in fig. 2 is an execution subject according to the first embodiment of the present invention. The first node 20 is described in detail with reference to fig. 2, wherein the first node 20 includes: a first processor 200. A second node 21 comprising: a second processor 210 and at least one second hard disk unit 211.
The first processor 200 is connected to the second processor 210 of the second node 21, and the first processor 200 is configured to obtain a heartbeat signal of the second processor 210 of the second node 21, and determine whether the second node 21 fails according to the heartbeat signal.
The first processor 200 is further configured to, when the first processor 200 determines that the second node 21 fails according to the heartbeat signal, access at least one second hard disk unit 211 of the second node 21 through a first interconnection hard disk channel between the first processor 200 and the second node 21.
Specifically, in fig. 2, the second node 21 is illustrated by taking one second hard disk unit 211 as an example, obviously, the second node 21 may include a plurality of second hard disk units 211, and the first processor 200 may be connected to the second hard disk units 211 through a first interconnection hard disk channel.
At least one second hard disk unit 211 of the second node 21 for storing data.
The node provided by this embodiment is connected to the second processor of the second node through the first processor of the node, the first processor obtains a heartbeat signal of the second processor of the second node, and determines whether the second node fails according to the heartbeat signal, after the first processor determines that the second node fails according to the heartbeat signal, the first processor accesses at least one second hard disk unit of the second node through the first interconnection hard disk channel between the first processor and the second node, so that the second hard disk unit of the second node is taken over when the second node fails, and normal use of data in the second hard disk unit is ensured on the premise that resources of the second node are not wasted.
Further, with respect to the first interconnected hard disk channel in fig. 2, a possible implementation manner of the first interconnected hard disk channel is described below by giving specific embodiments.
Example two
Based on fig. 2, fig. 3 is a schematic diagram of the connection between the nodes according to the second embodiment of the present invention, in which both the first node 20 and the second node 21 are based on a conventional x86 server architecture, and specifically, taking the first node 20 as an example, a SAS channel (cable adapter plug) is respectively branched from the first SAS controller 203 of the motherboard and the first SAS expander 202 of the backplane to the chassis panel of the first node 20. Two adjacent nodes (the first node 20 and the second node 21 in fig. 3) are cross-interconnected through SAS cables, while retaining the heartbeat signal, for example, the processors of the two nodes may obtain the heartbeat signal through a Gigabit Ethernet (GE) channel. Referring to fig. 2, a first interconnected hard disk channel is a channel between a first serial small computer system interface SAS controller 203 of the first node 20 and a second SAS expander 212 of the second node 21.
The first SAS controller 203 of the first node 20 is coupled to the second SAS expander 212 of the second node 21.
Referring to fig. 2, the first processor 200 is further configured to access at least one second hard disk unit 211 of the second node 21 through the first SAS controller 203 of the first node 20 and the second SAS expander 212 of the second node 21 after determining that the second node 21 has a failure according to the heartbeat signal.
Further, the first SAS controller 203 of the first node 20 is configured to perform protocol conversion on the access request sent by the first processor 200 to the at least one second hard disk unit 211 of the second node 21, so that the at least one second hard disk unit 211 of the second node 21 can respond after receiving the access request,
the first SAS controller 203 of the first node 20 is further configured to perform protocol conversion on a response message sent by the second hard disk unit 211 of the second node 21 to the first processor 200, so that the first processor 200 performs read-write operation on at least one second hard disk unit 211 of the second node 21 according to the response message.
It should be noted that the second SAS expander 212 of the second node 21 is configured to expand the first interconnected hard disk channel to at least one second hard disk unit 211 of the second node 21.
Specifically, referring to fig. 2, taking one second hard disk unit 211 as an example in fig. 2, it is obvious that a plurality of second hard disk units 211 may be included in the second node 21, and at this time, the second SAS expander 212 of the second node 21 is required to expand the first interconnected hard disk channel to the plurality of second hard disk units 211.
EXAMPLE III
Based on fig. 1, fig. 4 is a schematic diagram of connection between nodes according to a third embodiment of the present invention, and referring to fig. 4, in the third embodiment, a first node 20 and a second node 21 are both based on a conventional x86 server architecture, and taking the first node 20 as an example, a SAS channel (cable patch plug) is divided from each first SAS expander 202 of a backplane to a chassis panel of the first node 20. Two adjacent nodes (i.e., the first node 20 and the second node 21) are directly interconnected via the SAS cable while retaining the heartbeat signal, for example, the heartbeat signal may be obtained by the processors of the two nodes via the GE channel. The first interconnected hard disk channel is a channel between the first SAS controller 203 of the first node 20, the first SAS expander 203 of the first node 20, and the second SAS expander 212 of the second node 21.
The first processor 200 is further configured to, when the first processor 200 determines that the second node 21 fails according to the heartbeat signal, the first processor 200 accesses at least one second hard disk unit 211 of the second node 21 through the first SAS controller 203 of the first node 20, the first SAS expander 202 of the first node 20, and the second SAS expander 212 of the second node 21.
The first SAS controller 203 of the first node 20 is configured to perform protocol conversion on an access request sent by the first processor 200 to the second hard disk unit 211 of the second node 21, so that the second hard disk unit 211 of the second node 21 can respond after receiving the access request, and perform protocol conversion on a response message sent by the second hard disk unit 211 of the second node 21 to the first processor 200, so that the first processor 200 performs a read-write operation on the second hard disk unit 211 of the second node 21 according to the response message.
The first SAS expander 202 of the first node 20 is adapted for connection with the second SAS expander 212 of the second node 21.
It should be noted that the second SAS expander 212 of the second node 21 is configured to expand the first interconnected hard disk channel to at least one second hard disk unit 211 of the second node 21.
Example four
On the basis of fig. 1, fig. 5 is a schematic diagram of connection between nodes according to a fourth embodiment of the present invention, in which a control motherboard in a node is implemented in the form of an insertion frame, and an SAS expansion board is added, and both of them are connected to a backplane in the form of a Field Replacement Unit (FRU) module. A first SAS controller 203 (local SAS controller) on the first node 20, which controls the main board, is first connected to a first SAS expander 202 of the SAS expansion board through the backplane, and then the first SAS expander 202 expands a required number of SAS channels to connect to the first hard disk unit 201 of the first node 20. Meanwhile, a third SAS controller (node interconnection SAS controller) is added on the control main board, and a standard SAS interface (downlink channel) is output on a panel of the case; the SAS expansion board also outputs a standard SAS interface (upstream channel) at the chassis panel. Two adjacent nodes (the first node 20 and the second node 21) cross-connect the third SAS controller 204 (interconnected SAS controller) of the first node 20 and the interface of the second SAS expander 212 (SAS expander board) of the second node 21 through the external cable of the enclosure, and simultaneously a heartbeat signal, such as a GE channel, is reserved between the nodes.
Specifically, referring to fig. 5, the first interconnected hard disk channel is a channel between the third SAS controller 204 of the first node 20 and the second SAS expander 212 of the second node 21.
The third SAS controller 204 of the first node 20 is coupled to the second SAS expander 212 of the second node 21.
The first processor 200 is further configured to, after the first processor 200 determines that the second node 21 fails according to the heartbeat signal, access at least one second hard disk unit 211 of the second node 21 through the third SAS controller 204 of the first node 20 and the second SAS expander 212 of the second node 21.
The third SAS controller 204 of the first node 20 is configured to perform protocol conversion on an access request sent by the first processor 200 to the at least one second hard disk unit 211 of the second node 21, so that the at least one second hard disk unit 211 of the second node 21 can respond after receiving the access request, and perform protocol conversion on a response message sent by the at least one second hard disk unit 211 of the second node 21 to the first processor 200, so that the first processor 200 performs a read-write operation on the at least one second hard disk unit 211 of the second node 21 according to the response message.
It should be noted that the second SAS expander 212 of the second node 21 is configured to expand the first interconnected hard disk channel to at least one second hard disk unit 211 of the second node 21.
Further, with respect to the solutions provided in the first to fourth embodiments, except that the first node 20 may take over the second hard disk unit 211 of the second node 21 to implement the read/write operation on the second hard disk unit 211 when the second node 21 fails, referring to the solutions provided in the first to fourth embodiments when the first node 20 fails, similarly, the second node 21 may also access the first hard disk unit 201 of the first node 20 in the same manner, and a specific embodiment is given below to describe a possible implementation manner thereof.
Obviously, since the second node 21 has exactly the same function as the first node 20, when the first node 20 fails, the second node 21 may also take over the first hard disk unit 201 of the first node 20, which will be described below by way of specific embodiments.
EXAMPLE five
Referring to fig. 2, the first processor 200 is connected to the second processor 210 of the second node 21, and is further configured to make the second processor 210 of the second node 21 know that the first node 20 fails through a heartbeat signal when the first node 20 fails.
At least one first hard disk unit 201 of the first node 20 is connected to the second processor 210 of the second node 21 through a second interconnection hard disk channel, and the first processor 200 makes the second processor 210 of the second node 21 know that the first node 20 has a fault through a heartbeat signal, so that the second processor 210 of the second node 21 accesses the at least one first hard disk unit 201 of the first node 20 through the second interconnection hard disk channel with the first node 20.
At least one first hard disk unit 201 of the first node 20 for storing data.
EXAMPLE six
Referring to fig. 3, the second interconnected hard disk path is a path between the first SAS expander 202 of the first node 20.
The first SAS expander 202 of the first node 20 is coupled to the second SAS controller 213 of the second node 21.
The first processor 200 makes the second processor 210 of the second node 21 aware of the failure of the first node 20 through the heartbeat signal, so that the second processor 210 of the second node 21 accesses at least one first hard disk unit 201 of the first node 20 through the second SAS controller 213 of the second node 21 and the first SAS expander 202 of the first node 20.
The first SAS expander 202 of the first node 20 is configured to expand the second interconnected hard disk channel to at least one first hard disk unit 201 of the first node 20.
It should be noted that the second SAS controller 213 of the second node 21 is configured to perform protocol conversion on an access request sent by the second processor 210 of the second node 21 to the at least one first hard disk unit 201 of the first node 20, so as to enable the at least one first hard disk unit 201 of the first node 20 to respond after receiving the access request, and perform protocol conversion on a response message sent by the at least one first hard disk unit 201 of the first node 20 to the second processor 210 of the second node 21, so that the second processor 210 of the second node 21 performs read/write operations on the at least one first hard disk unit 201 of the first node 20 according to the response message.
EXAMPLE seven
Referring to fig. 4, the second interconnected hard disk path is a path between the first SAS expander 202 of the first node 20 and the second SAS controller 213 of the second node 21 and the second SAS expander 212 of the second node 21.
The first SAS expander 202 of the first node 20, the second SAS controller 213 of the second node 21, and the second SAS expander 212 of the second node 21 are connected in this order.
After the first processor 200 makes the second processor 210 of the second node 21 know that the first node 20 has a failure through the heartbeat signal, the second processor 210 of the second node 21 accesses at least one first hard disk unit 201 of the first node 20 through the first SAS expander 202 of the first node 20, the second SAS controller 213 of the second node 21, and the second SAS expander 212 of the second node 21.
The first SAS expander 202 of the first node 20 is configured to expand the second interconnected hard disk channel to at least one first hard disk unit 201 of the first node 20.
It should be noted that the second SAS controller 213 of the second node 21 is configured to perform protocol conversion on an access request sent by the second processor 210 of the second node 21 to the at least one first hard disk unit 201 of the first node 20, so as to enable the at least one first hard disk unit 201 of the first node 20 to respond after receiving the access request, and perform protocol conversion on a response message sent by the at least one first hard disk unit 201 of the first node 20 to the second processor 210 of the second node 21, so that the second processor 210 of the second node 21 performs read/write operations on the at least one first hard disk unit 201 of the first node 20 according to the response message.
Example eight
Referring to fig. 5, the second interconnected hard disk channel is a channel between the first SAS expander 202 of the first node 20 and the fourth SAS controller 214 of the second node 21.
The first SAS expander 202 of the first node 20 is coupled to the fourth SAS controller 214 of the second node 21.
The first processor 200 makes the second processor 210 of the second node 21 aware of the failure of the first node 20 through the heartbeat signal, so that the second processor 210 of the second node 21 accesses the at least one first hard disk unit 201 of the first node 20 through the fourth SAS controller 214 of the second node 21 and the first SAS expander 202 of the first node 20.
The first SAS expander 202 of the first node 20 is configured to expand the second interconnected hard disk channel to at least one first hard disk unit 201 of the first node 20.
It should be noted that the fourth SAS controller of the second node 21 is configured to perform protocol conversion on an access request sent by the second processor 210 to the at least one first hard disk unit 201 of the first node 20, so that the at least one first hard disk unit 201 of the first node 20 can respond after receiving the access request, and perform protocol conversion on a response message sent by the at least one first hard disk unit 201 of the first node 20 to the second processor 210, so that the second processor 210 performs read-write operation on the at least one first hard disk unit 201 of the first node 20 according to the response message.
Further, taking the first node 20 in fig. 1 to fig. 4 as an example, the first processor 200 of the first node 20 is connected to the local hard disk channel of the first node 20, and is configured to access the first hard disk unit 201 through the local hard disk channel.
Similarly, the second processor 210 of the second node 21 may also be connected to the local hard disk channel of the second node 21, for accessing the second hard disk unit 211 through the local hard disk channel of the second node 21.
Further, referring to fig. 2 to 4, for the first node 20, the local hard disk channel of the first node 20 is a channel between the first SAS controller 203 of the first node 20 and the first SAS expander 202 of the first node 20.
The first SAS controller 203 of the first node 20 is coupled to the first SAS expander 202 of the first node 20.
The first processor 200 is also configured to access at least one first hard disk unit 201 via a first SAS controller 203 of the first node 20 and a first SAS expander 202 of the first node 20.
The first SAS controller 203 of the first node 20 is configured to perform protocol conversion on an access request sent by the first processor 200 to the first hard disk unit 201 of the first node 20, so that the first hard disk unit 201 of the first node 20 can respond after receiving the access request, and perform protocol conversion on a response message sent by the first hard disk unit 201 of the first node 20 to the first processor 200, so that the first processor 200 performs read-write operation on the first hard disk unit 201 of the first node 20 according to the response message.
The first SAS expander 202 of the first node 20 is configured to expand the local hard disk channel to at least one first hard disk unit 201.
Similarly, the second node 21 may also access the second hard disk unit 211 through a local hard disk channel of the second node 21, and similarly, the local hard disk channel of the second node 21 is a channel between the second SAS controller 213 of the second node 21 and the second SAS expander 212 of the second node 21, and the principle thereof is similar to that of the first node 20, and is not described herein again.
For the above embodiments, the first processor 200 of the first node 20 is further configured to perform a hard disk discovery operation to discover the second hard disk unit 211 of the second node 21.
The first processor 200 is further configured to establish an SAS topology, where the SAS topology includes a first interconnected hard disk channel and a local hard disk channel.
For the first node 20, after the first processor 200 determines that the second node 21 has a fault according to the heartbeat signal, it may specifically implement a scheme of taking over the second node 21 through two feasible implementation manners:
the first method is as follows: the first processor 200 is further configured to, after determining that the second node 21 fails according to the heartbeat signal, wait for the at least one second hard disk unit 211 of the second node 21 to complete the current command, and then access the at least one second hard disk unit 211 of the second node 21 through the first interconnection hard disk channel.
Alternatively, the second mode: the first processor 200 is further configured to, after determining that the second node 21 fails according to the heartbeat signal, clear an association relationship between the second SAS controller 213 of the second node 21 and at least one second hard disk node of the second node 21, which is included in the STP connection, establish an association relationship between the first SAS controller 203 of the first node 20 and at least one second hard disk node of the second node 21, and access at least one second hard disk unit 211 of the second node 21 through the first interconnection hard disk channel.
Obviously, the second processor 210 of the second node 21 also has similar functions as the first processor 200, and will not be described herein again.
Further, for the above embodiments and possible implementations, the following two connection manners may be available for the respective components of the first node 20.
The first method is as follows: the first SAS controller 203 and the first processor 200 of the first node 20 are disposed on a motherboard of the first node 20; first SAS expander 202 of first node 20 is disposed on a backplane of first node 20.
Alternatively, the second mode: the first SAS controller 203 of the first node 20, the third SAS controller of the first node 20, and the first processor 200 are provided on a motherboard of the first node 20, and the first SAS expander 202 of the first node 20 is provided on a SAS expansion board of the first node 20.
Further, in the first or second mode, the system power supply of the first node 20, the fan controller of the first node 20, and the monitoring module of the first node 20 are disposed on a back board of the first node 20.
Alternatively, the system power of first node 20, the fan controller of first node 20, and the monitoring module of first node 20 are located on the SAS expander of first node 20.
The system power supply, the fan controller and the monitoring module are stripped from the main board and are realized on the SAS expander. When the mainboard has a fault, the power supply and the fan still work normally. In addition, the power control signal outputted from the motherboard is sent in the form of a command packet (e.g., an Inter-Integrated Circuit (I2C) command) to avoid an indeterminate state of the level signal when the motherboard fails. And the power supply still works normally when the main board fails. Furthermore, the power supply of the mainboard is isolated from the system power supply, so that the power supply still normally works under the condition of short circuit of the mainboard power supply. Preferably, the mainboard is designed in a hot plug mode, so that the hard disk still can be normally accessed after the mainboard is controlled to be pulled out of the case, and online maintenance is supported.
Through the optimization, the main board is controlled to have any fault (including software running away, chip failure and power supply short circuit) and even be pulled out of the chassis, and as long as the system power supply and the SAS expansion board work normally, the hard disk can be taken over by the adjacent nodes. Since the SAS protocol supports simultaneous discovery and access of a hard disk by multiple hosts, while the Serial Advanced Technology Attachment (SATA) protocol supports only a single host, the specific hard disk takeover procedure depends on the type of hard disk interface.
The system power supply of the first node 20 is configured to provide power to a first SAS controller 203 of the first node 20, the first processor 200, a first SAS expander 202 of the first node 20, a third SAS controller of the first node 20, and a first hard disk unit 201 of the first node 20.
The fan controller of the first node 20 is configured to control a fan to dissipate heat of the first SAS controller 203, the first processor 200, the first SAS expander 202 of the first node 20, the third SAS controller of the first node 20, and the first hard disk unit 201 of the first node 20.
The monitoring module of the first node 20 is configured to control a system power of the first node 20, a fan controller of the first node 20, and perform temperature monitoring.
It should be noted that the specific connection manner of the system power supply, the fan controller and the monitoring module of the second node 21 may also be similar to that of the first node 20, and is not described herein again. For each of the above embodiments and possible implementations, two nodes, that is, a first node and a second node, are used for description, and it is obvious that, for a network having a plurality of nodes, the above series connection may be performed between adjacent nodes having a takeover function, and when one node fails, according to the solutions of the above embodiments and possible implementations, the hard disk unit of the failed node may be taken over by another node. Similarly, the above embodiments of the present invention are not only applied to a distributed storage system, but also applied to independent storage devices configured in multiple nodes, such as interconnection among multiple video monitoring devices and multiple IPTV devices.
Fig. 6 is a schematic flowchart of a storage system interconnection method provided in the ninth embodiment of the present invention, which includes the specific steps of:
In the storage system interconnection method provided by this embodiment, the heartbeat signal of the second processor of the second node is obtained, whether the second node fails is determined according to the heartbeat signal, and then the second node fails is determined according to the heartbeat signal, so that at least one second hard disk unit of the second node is accessed through the first interconnection hard disk channel, and the second hard disk unit of the second node is taken over when the second node fails, so that normal use of data in the second hard disk unit is ensured on the premise of not wasting resources of the second node.
Further, in step 101, at least one second hard disk unit of the second node is accessed through the first interconnection hard disk channel, and one possible implementation manner of the second hard disk unit is as follows:
an access request is sent to at least one second hard disk unit of the second node.
And carrying out protocol conversion on the access request so that at least one second hard disk unit of the second node can respond after receiving the access request.
And receiving a response message sent by the second hard disk unit of the second node.
And carrying out protocol conversion on the response message.
And performing read-write operation on at least one second hard disk unit of the second node according to the response message.
Similarly, fig. 7 is a flowchart illustrating a storage system interconnection method provided in a tenth embodiment of the present invention, and a description is given with reference to fig. 7 for a scenario where a first node fails and a second node needs to take over a first hard disk unit of the first node, where the method includes the specific steps of:
Further, for the step 201, allowing the second processor of the second node to access the at least one first hard disk unit of the first node through the second interconnection hard disk channel, one possible implementation manner of the method is as follows:
and receiving an access request sent by a second processor of the second node to at least one first hard disk unit of the first node.
And carrying out protocol conversion on the access request so as to enable at least one first hard disk unit of the first node to respond after receiving the access request.
And receiving a response message sent by at least one first hard disk unit of the first node to a second processor of the second node.
And performing protocol conversion on the response message so that the second processor of the second node performs read-write operation on at least one first hard disk unit of the first node according to the response message.
Further, for the first node, in addition to taking over the second hard disk unit of the second node when the second node fails, the first node also accesses the first hard disk unit through the local hard disk channel.
Specifically, a feasible implementation manner for the first node to access the first hard disk unit through the local hard disk channel is as follows:
an access request is sent to a first hard disk unit of a first node.
And carrying out protocol conversion on the access request so that the first hard disk unit of the first node can respond after receiving the access request.
And receiving a response message sent by the first hard disk unit of the first node.
And performing protocol conversion on the response message, so that the first processor performs read-write operation on the first hard disk unit of the first node 20 according to the response message.
For a scenario where a second node fails, fig. 8 is a schematic flow diagram of a storage system interconnection method provided in an eleventh embodiment of the present invention, where an execution main body of the eleventh embodiment is a first node, and the following describes the eleventh embodiment with reference to fig. 8, where the method specifically includes the following steps:
and step 300, performing a hard disk discovery operation to discover a second hard disk unit of the second node.
Specifically, the SAS topology includes a first interconnected hard disk channel and a local hard disk channel.
And step 303, acquiring a heartbeat signal of the second processor of the second node, and judging whether the second node has a fault according to the heartbeat signal.
And step 304, judging the second hard disk unit interface type of the second node.
Specifically, if the second hard disk unit interface type of the second node is SAS, step 305 is executed; if the second hard disk unit interface type of the second node is SATA, step 306 is executed.
And 305, after judging that the second node has a fault according to the heartbeat signal, waiting for the second hard disk unit of the second node to complete the current command.
Specifically, when the second hard disk unit of the second node completes the current command, step 307 is executed.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (21)
1. A node, comprising: a first processor;
the first processor is connected with a second processor of a second node and used for acquiring a heartbeat signal of the second processor of the second node and judging whether the second node has a fault or not according to the heartbeat signal;
the first processor is further configured to access at least one second hard disk unit of the second node through a first interconnection hard disk channel between the first processor and the second node after the first processor determines that the second node has a fault according to the heartbeat signal.
2. The node of claim 1, wherein the first interconnecting hard disk channel is a channel between a first serial small computer system interface (SAS) controller of the first node and a second SAS expander of the second node;
the first SAS controller of the first node is configured to perform protocol conversion on an access request sent by the first processor to at least one second hard disk unit of the second node, so that the at least one second hard disk unit of the second node can respond after receiving the access request, and perform protocol conversion on a response message sent by the second hard disk unit of the second node to the first processor, so that the first processor performs read-write operation on the at least one second hard disk unit of the second node according to the response message.
3. The node of claim 1, wherein the first interconnecting hard disk tunnel is a tunnel between a first serial small computer system interface (SAS) controller of a first node, a first SAS expander of the first node, and a second SAS expander of a second node;
the first SAS controller of the first node is configured to perform protocol conversion on an access request sent by the first processor to the second hard disk unit of the second node, so that the second hard disk unit of the second node can respond after receiving the access request, and perform protocol conversion on a response message sent by the second hard disk unit of the second node to the first processor, so that the first processor performs read-write operation on the second hard disk unit of the second node according to the response message;
the first SAS expander of the first node is configured to interface with a second SAS expander of the second node.
4. The node of claim 1, wherein the first interconnecting hard disk channel is a channel between a third serial small computer system interface (SAS) controller of the first node and a second SAS expander of the second node;
the third SAS controller of the first node is configured to perform protocol conversion on an access request sent by the first processor to the at least one second hard disk unit of the second node, so that the at least one second hard disk unit of the second node can respond after receiving the access request, and perform protocol conversion on a response message sent by the at least one second hard disk unit of the second node to the first processor, so that the first processor performs read-write operation on the at least one second hard disk unit of the second node according to the response message.
5. The node according to any one of claims 2 to 4, wherein the first processor is further configured to, when a failure occurs in a first node, make the second processor of the second node know that the failure occurs in the first node through a heartbeat signal;
at least one first hard disk unit of a first node is connected with a second processor of a second node through a second interconnection hard disk channel, and the first processor enables the second processor of the second node to know that the first node is in fault through a heartbeat signal, so that the second processor of the second node accesses the at least one first hard disk unit of the first node through the second interconnection hard disk channel between the second processor of the second node and the first node;
and the at least one first hard disk unit of the first node is used for storing data.
6. The node of claim 5, wherein the second interconnecting hard disk tunnel is a tunnel between a first SAS expander of the first node and a second SAS controller of the second node;
and the first SAS expander of the first node is used for expanding the second interconnected hard disk channel to at least one first hard disk unit of the first node.
7. The node of claim 5, wherein the second interconnecting hard disk tunnel is a tunnel between a first SAS expander of the first node, a second SAS controller of the second node, and a second SAS expander of the second node;
and the first SAS expander of the first node is used for expanding the second interconnected hard disk channel to at least one first hard disk unit of the first node.
8. The node of claim 5, wherein the second interconnecting hard disk tunnel is a tunnel between a first SAS expander of the first node and a fourth SAS controller of the second node;
and the first SAS expander of the first node is used for expanding the second interconnected hard disk channel to at least one first hard disk unit of the first node.
9. The node according to any one of claims 1 to 8, wherein the first processor is connected to a local hard disk channel for accessing the first hard disk unit through the local hard disk channel.
10. The node of claim 9, wherein the local hard disk tunnel is a tunnel between a first SAS controller of the first node and a first SAS expander of the first node;
the first SAS controller of the first node is configured to perform protocol conversion on an access request sent by the first processor to the first hard disk unit of the first node, so that the first hard disk unit of the first node can respond after receiving the access request, and perform protocol conversion on a response message sent by the first hard disk unit of the first node to the first processor, so that the first processor performs read-write operation on the first hard disk unit of the first node according to the response message;
and the first SAS expander of the first node is used for expanding the local hard disk channel to at least one first hard disk unit.
11. The node according to any one of claims 1 to 10, wherein the first processor is further configured to perform a hard disk discovery operation to discover a second hard disk unit of the second node;
the first processor is further configured to establish an SAS topological structure, where the SAS topological structure includes the first interconnected hard disk channel and the local hard disk channel.
12. The node according to any one of claims 1 to 11, wherein the first processor is further configured to, after determining that the second node has a fault according to the heartbeat signal, wait for at least one second hard disk unit of the second node to complete a current command, and then access the at least one second hard disk unit of the second node through the first interconnection hard disk channel;
or, after judging that the second node has a fault according to the heartbeat signal, clearing the association relationship between the second SAS controller of the second node and the at least one second hard disk node of the second node, which is included in the STP connection, establishing the association relationship between the first SAS controller of the first node and the at least one second hard disk node of the second node, and accessing the at least one second hard disk unit of the second node through the first interconnected hard disk channel.
13. The node according to any of claims 1-12, wherein the first SAS controller and the first processor of the first node are disposed on a motherboard of the first node; the first SAS expander of the first node is arranged on the back plate of the first node; or,
the first SAS controller of the first node, the third SAS controller of the first node, and the first processor are disposed on a motherboard of the first node, and the first SAS expander of the first node is disposed on a SAS expansion board of the first node;
the system power supply of the first node, the fan controller of the first node and the monitoring module of the first node are arranged on the back plate of the first node; or,
the system power supply of the first node, the fan controller of the first node and the monitoring module of the first node are disposed on the SAS expander of the first node;
the system power supply of the first node is used for providing power for a first SAS controller of the first node, the first processor, a first SAS expander of the first node, a third SAS controller of the first node and a first hard disk unit of the first node;
the fan controller of the first node is configured to control a fan to dissipate heat of a first SAS controller of the first node, the first processor, a first SAS expander of the first node, a third SAS controller of the first node, and a first hard disk unit of the first node;
and the monitoring module of the first node is used for controlling the system power supply of the first node, the fan controller of the first node and monitoring the temperature.
14. A storage system interconnection method is characterized by comprising the following steps:
acquiring a heartbeat signal of a second processor of the second node, and judging whether the second node has a fault according to the heartbeat signal;
and if the second node fails, accessing at least one second hard disk unit of the second node through the first interconnection hard disk channel.
15. The method of claim 14, wherein accessing the at least one second hard disk unit of the second node through the first interconnect hard disk channel comprises:
sending an access request to at least one second hard disk unit of the second node;
performing protocol conversion on the access request so that at least one second hard disk unit of the second node can respond after receiving the access request;
receiving a response message sent by a second hard disk unit of the second node;
carrying out protocol conversion on the response message;
and performing read-write operation on at least one second hard disk unit of the second node according to the response message.
16. The method of any one of claims 14 to 15, further comprising:
when a first node fails, a second processor of a second node learns that the first node fails through a heartbeat signal;
and when the second processor of the second node receives the heartbeat signal and learns that the first node is in fault, allowing the second processor of the second node to access at least one first hard disk unit of the first node through the second interconnection hard disk channel.
17. The method of claim 16, wherein allowing the second processor of the second node to access the at least one first hard disk unit of the first node through the second interconnect hard disk channel comprises:
receiving an access request sent by a second processor of the second node to at least one first hard disk unit of the first node;
performing protocol conversion on the access request so that at least one first hard disk unit of the first node can respond after receiving the access request;
receiving a response message sent by at least one first hard disk unit of the first node to a second processor of the second node;
and performing protocol conversion on the response message so that the second processor of the second node performs read-write operation on at least one first hard disk unit of the first node according to the response message.
18. The method of any one of claims 14 to 17, further comprising: and accessing the first hard disk unit through the local hard disk channel.
19. The method of claim 18, wherein accessing the first hard disk unit through the local hard disk channel comprises:
sending an access request to a first hard disk unit of the first node;
performing protocol conversion on the access request so that a first hard disk unit of the first node can respond after receiving the access request;
receiving a response message sent by a first hard disk unit of the first node;
and performing protocol conversion on the response message so that the first processor performs read-write operation on the first hard disk unit of the first node according to the response message.
20. The method according to any one of claims 14 to 19, wherein a hard disk discovery operation is performed to discover a second hard disk unit of the second node;
and establishing a serial small computer system interface (SAS) topological structure, wherein the SAS topological structure comprises the first interconnected hard disk channel and the local hard disk channel.
21. The method according to any one of claims 14 to 20, wherein the step of accessing at least one second hard disk unit of the second node through the first interconnected hard disk channel when the second node is judged to be faulty according to the heartbeat signal comprises
After judging that the second node has a fault according to the heartbeat signal, waiting for a second hard disk unit of the second node to complete a current command, and accessing the second hard disk unit of the second node through the first interconnection hard disk channel;
or, after judging that the second node has a fault according to the heartbeat signal, clearing the incidence relation between the second SAS controller of the second node and the second hard disk node of the second node included in the STP connection, establishing the incidence relation between the first SAS controller of the first node and the second hard disk node of the second node, and accessing the second hard disk unit of the second node through the first interconnected hard disk channel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013103668424A CN103475695A (en) | 2013-08-21 | 2013-08-21 | Interconnection method and device for storage system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013103668424A CN103475695A (en) | 2013-08-21 | 2013-08-21 | Interconnection method and device for storage system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103475695A true CN103475695A (en) | 2013-12-25 |
Family
ID=49800388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013103668424A Pending CN103475695A (en) | 2013-08-21 | 2013-08-21 | Interconnection method and device for storage system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103475695A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104052642A (en) * | 2014-06-11 | 2014-09-17 | 华为技术有限公司 | Communication system and method |
| CN105159605A (en) * | 2015-08-24 | 2015-12-16 | 浪潮(北京)电子信息产业有限公司 | Storage server architecture |
| CN105573895A (en) * | 2015-12-18 | 2016-05-11 | 山东海量信息技术研究院 | Double-control storage based HDD (hard disk drive) indicating light design method and module |
| CN105912278A (en) * | 2016-04-29 | 2016-08-31 | 浪潮(北京)电子信息产业有限公司 | Converge infrastructure based memory module frame system used for eight-path server |
| CN106250284A (en) * | 2015-06-08 | 2016-12-21 | 群晖科技股份有限公司 | Method and apparatus for managing a storage system |
| CN106294077A (en) * | 2016-08-31 | 2017-01-04 | 浪潮(北京)电子信息产业有限公司 | Link expander instrument operating condition monitoring method, system and server |
| CN107391037A (en) * | 2017-07-25 | 2017-11-24 | 郑州云海信息技术有限公司 | A kind of method and device of memory system data |
| US10049068B2 (en) | 2014-11-11 | 2018-08-14 | Huawei Technologies Co., Ltd. | SAS system, SAS system traversal method, and apparatus |
| CN112579384A (en) * | 2019-09-27 | 2021-03-30 | 杭州海康威视数字技术股份有限公司 | Method, device and system for monitoring nodes of SAS domain and nodes |
| WO2021238579A1 (en) * | 2020-05-27 | 2021-12-02 | 华为技术有限公司 | Method for managing sata hard disk by means of storage system, and storage system |
| TWI830097B (en) * | 2021-12-08 | 2024-01-21 | 神雲科技股份有限公司 | Clustered storage system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101382872A (en) * | 2008-10-21 | 2009-03-11 | 浪潮电子信息产业股份有限公司 | Double-control storage and switch control method for SAS and SATA signal by detecting heartbeat |
| CN101546601A (en) * | 2009-05-13 | 2009-09-30 | 杭州华三通信技术有限公司 | Solid state disk and memory system |
| US20110169254A1 (en) * | 2007-07-16 | 2011-07-14 | Lsi Corporation | Active-active failover for a direct-attached storage system |
| CN102387184A (en) * | 2010-08-25 | 2012-03-21 | Lsi公司 | Methods and apparatus for improved host/initiator utilization in serial advanced technology attachment communication |
| CN103049225A (en) * | 2013-01-05 | 2013-04-17 | 浪潮电子信息产业股份有限公司 | Double-controller active-active storage system |
-
2013
- 2013-08-21 CN CN2013103668424A patent/CN103475695A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110169254A1 (en) * | 2007-07-16 | 2011-07-14 | Lsi Corporation | Active-active failover for a direct-attached storage system |
| CN101382872A (en) * | 2008-10-21 | 2009-03-11 | 浪潮电子信息产业股份有限公司 | Double-control storage and switch control method for SAS and SATA signal by detecting heartbeat |
| CN102187324A (en) * | 2008-11-13 | 2011-09-14 | Lsi公司 | Active-active failover for a direct-attached storage system |
| CN101546601A (en) * | 2009-05-13 | 2009-09-30 | 杭州华三通信技术有限公司 | Solid state disk and memory system |
| CN102387184A (en) * | 2010-08-25 | 2012-03-21 | Lsi公司 | Methods and apparatus for improved host/initiator utilization in serial advanced technology attachment communication |
| CN103049225A (en) * | 2013-01-05 | 2013-04-17 | 浪潮电子信息产业股份有限公司 | Double-controller active-active storage system |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104052642B (en) * | 2014-06-11 | 2017-11-24 | 华为技术有限公司 | A kind of communication system and communication means |
| CN104052642A (en) * | 2014-06-11 | 2014-09-17 | 华为技术有限公司 | Communication system and method |
| US10049068B2 (en) | 2014-11-11 | 2018-08-14 | Huawei Technologies Co., Ltd. | SAS system, SAS system traversal method, and apparatus |
| CN106250284B (en) * | 2015-06-08 | 2019-03-15 | 群晖科技股份有限公司 | Method and apparatus for managing a storage system |
| CN106250284A (en) * | 2015-06-08 | 2016-12-21 | 群晖科技股份有限公司 | Method and apparatus for managing a storage system |
| CN105159605A (en) * | 2015-08-24 | 2015-12-16 | 浪潮(北京)电子信息产业有限公司 | Storage server architecture |
| CN105573895B (en) * | 2015-12-18 | 2018-06-19 | 山东海量信息技术研究院 | A kind of hard disk indication lamp design method based on dual control storage |
| CN105573895A (en) * | 2015-12-18 | 2016-05-11 | 山东海量信息技术研究院 | Double-control storage based HDD (hard disk drive) indicating light design method and module |
| CN105912278A (en) * | 2016-04-29 | 2016-08-31 | 浪潮(北京)电子信息产业有限公司 | Converge infrastructure based memory module frame system used for eight-path server |
| CN105912278B (en) * | 2016-04-29 | 2018-11-23 | 浪潮(北京)电子信息产业有限公司 | The memory module architecture system of 8 road servers is used for based on fusion architecture |
| CN106294077A (en) * | 2016-08-31 | 2017-01-04 | 浪潮(北京)电子信息产业有限公司 | Link expander instrument operating condition monitoring method, system and server |
| CN106294077B (en) * | 2016-08-31 | 2019-01-29 | 浪潮(北京)电子信息产业有限公司 | Link expander instrument operating condition monitoring method, system and server |
| CN107391037A (en) * | 2017-07-25 | 2017-11-24 | 郑州云海信息技术有限公司 | A kind of method and device of memory system data |
| CN112579384A (en) * | 2019-09-27 | 2021-03-30 | 杭州海康威视数字技术股份有限公司 | Method, device and system for monitoring nodes of SAS domain and nodes |
| WO2021238579A1 (en) * | 2020-05-27 | 2021-12-02 | 华为技术有限公司 | Method for managing sata hard disk by means of storage system, and storage system |
| CN113742142A (en) * | 2020-05-27 | 2021-12-03 | 华为技术有限公司 | Method for managing SATA hard disk by storage system and storage system |
| CN113742142B (en) * | 2020-05-27 | 2024-03-26 | 华为技术有限公司 | Method for managing SATA hard disk by storage system and storage system |
| TWI830097B (en) * | 2021-12-08 | 2024-01-21 | 神雲科技股份有限公司 | Clustered storage system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103475695A (en) | Interconnection method and device for storage system | |
| US9137148B2 (en) | Information processing system and information processing apparatus | |
| JP4723290B2 (en) | Disk array device and control method thereof | |
| TWI403891B (en) | Active-active failover for a direct-attached storage system | |
| US20110145452A1 (en) | Methods and apparatus for distribution of raid storage management over a sas domain | |
| JP5561622B2 (en) | Multiplexing system, data communication card, state abnormality detection method, and program | |
| US20120233399A1 (en) | Storage apparatus and method of controlling the same | |
| CN101651559A (en) | Failover method of storage service in double controller storage system | |
| US9329653B2 (en) | Server systems having segregated power circuits for high availability applications | |
| TW201319824A (en) | Server direct attached storage shared through virtual SAS expanders | |
| CN112667066B (en) | Method, system and medium for expanding hard disk storage capacity | |
| CN109783280A (en) | Shared memory systems and shared storage method | |
| CN105045336A (en) | JBOD (Just Bunch of Disks) | |
| TWI773152B (en) | Server and control method of server | |
| JP2006293863A (en) | Disk array device and control method thereof | |
| TWI612429B (en) | Server system and data access method using the same | |
| US20130111094A1 (en) | Management of target devices | |
| WO2021012169A1 (en) | Method of improving reliability of storage system, and related apparatus | |
| US9507677B2 (en) | Storage control device, storage apparatus, and computer-readable recording medium having storage control program stored therein | |
| US20070002847A1 (en) | Storage control device and storage control device path switching method | |
| CN116661688B (en) | Service response method and device of SAS storage system | |
| CN117041184B (en) | IO expansion device and IO switch | |
| JP2007334764A (en) | Nas system and information processing method of nas system | |
| TW202020607A (en) | Hard disk module and server system | |
| EP2307969B1 (en) | Connecting a storage subsystem and an electronic device with a control device that hides details of the storage subsystem |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20131225 |