CN107710165A - Method and apparatus for the request of memory node synchronous service - Google Patents
Method and apparatus for the request of memory node synchronous service Download PDFInfo
- Publication number
- CN107710165A CN107710165A CN201580002564.1A CN201580002564A CN107710165A CN 107710165 A CN107710165 A CN 107710165A CN 201580002564 A CN201580002564 A CN 201580002564A CN 107710165 A CN107710165 A CN 107710165A
- Authority
- CN
- China
- Prior art keywords
- service request
- memory node
- request set
- belonging
- service
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
Abstract
The present embodiments relate to the method and apparatus asked for memory node synchronous service.This method includes：When the first memory node is performing the t of multiple service requests1To t2When inside breaking down, determine to record in first daily record starts to perform the moment in t12dt to t2The collection of service request in+2dt is combined into the first service request set, and what is recorded in second daily record starts to perform the moment in t1Dt to t2The collection of service request in+dt is combined into the second service request set, and dt is the maximum time span for performing service request；It is determined that belong to second service request set and be not belonging to the service request that the service request of first service request set is lost for first memory node during breaking down, in order to which the first memory node performs the service request of the loss.The method and apparatus for being used for the request of memory node synchronous service of the embodiment of the present invention, the service request of loss can be accurately obtained, the service request of synchronous normal storage node and failed storage node, improves the handling capacity that storage system performs service request.
Description
The present invention relates to the communications fields, the more particularly, to method and apparatus of memory node synchronous service request.
Memory node failure is normality in fairly large storage system, need to guarantee that data are not lost in memory node failure, here it is high reliability, also to guarantee that system continues offer service, here it is high availability, store manufacturer and generally use more copies or correcting and eleting codes (Erasure code, EC) technology, such as replicate data more parts (more copies), more parts are stored to provide high reliability and high availability.
Assuming that now within the storage system, during memory node failure, storage system is still in normal issuing service, and failed storage node is just lost a part of service request at this time, needs failed storage node is synchronous with the service request of normal storage node.
In the storage of existing strong consistency storage system, general adoption status synchronous machine (Replication State Machine, referred to as " RSM ") mechanism provides simultaneous techniques.The basic thought of RSM mechanism is that each memory node is fully synchronized, such as assume there be put (key1), put (key2), del (key1), four service requests of put (key3), each memory node must all first carry out put (key1), put (key2) is executed again, del (key1) is executed again, put (key3) is executed again, and at the same time with same journal log, if being lost some service requests during memory node failure, what these service requests were necessarily located next in log (log), continuously, such as latter two service request del (key1), put (key3), after failed storage node is restarted, the business for being easy for finding loss by comparing log is asked It asks, the two service requests of polishing can be completed to synchronize.
But, in this way in order to efficiently identify failure restart memory node loss service request, service request must be that sequence executes, and needs to distribute the sequence number with maintenance service request, this largely limits the handling capacity that storage system executes service request.
Summary of the invention
The present invention provides a kind of method and apparatus for the request of memory node synchronous service, can be accurately obtained the service request of loss, and the service request of synchronous normal storage node and failed storage node improves the handling capacity that storage system executes service request.
First aspect, provide a kind of method for the request of memory node synchronous service, this method is applied in the storage system including the first memory node and the second memory node, first memory node is used to execute multiple service requests according to the first sequence and stores the first log, first log be used to record each service request that first memory node has executed in multiple service request and each service request that first memory node has executed start execute the moment, second memory node is used to execute multiple service request according to the second sequence and stores the second log, second log note for record each service request that second memory node has executed in multiple service request and each service request that second memory node has executed start execute the moment, this method comprises: when first memory node is executing The t of multiple service request1To t2When inside breaking down, service request synchronizing device determines the first service request set and the second service request set, which starts to execute the moment in t for what is recorded in first log1- 2dt to t2The set of service request in+2dt, second service request set start to execute the moment in t for what is recorded in second log1- dt to t2The set of service request in+dt, the dt is greater than or equal at the time of first memory node starts performance objective service request and second memory node starts to execute the difference between at the time of the target service is requested, and target service request is the service request in first service request set or second service request set；The service request synchronizing device determines that belonging to second service request set and being not belonging to the service request of first service request set is the service request of first memory node loss during breaking down；The service request synchronizing device indicates that second memory node sends the service request of the loss to first memory node.
Therefore, the method for the request of memory node synchronous service of the embodiment of the present invention, two memory nodes in storage system can not execute service request according to the sequence that service request issues, one when breaking down wherein, can by searching for be not belonging in different time sections the memory node to break down record service request but belong to normal storage nodes records service request be loss service request, to allow different memory nodes concurrently or out of sequence to execute service request, without the sequence number of special distribution and maintenance service request, and the service request that can also be accurately lost from normal memory node, finishing service request synchronizes, improve the handling capacity that storage system executes service request.
With reference to first aspect, in a kind of implementation of first aspect, the service request synchronizing device determines that belonging to second service request set and being not belonging to the service request of first service request set is the service request of first memory node loss during breaking down, comprising: the service request in first service request set and second service request set is ranked up by the service request synchronizing device according to the key of service request respectively；The service request synchronizing device compares the service request in first service request set and second service request set according to the result of sequence, obtains belonging to second service request set
And the service request for being not belonging to first service request set is the service request of the loss, this way it is possible to avoid traversal action, quickly searches the service request of loss.
With reference to first aspect and its above-mentioned implementation, in another implementation of first aspect, the service request synchronizing device determines that belonging to second service request set and being not belonging to the service request of first service request set is the service request of first memory node loss during breaking down, include: key of the service request synchronizing device according to each service request in first service request set, determines the mark bit map of first service request set；The service request synchronizing device determines the mark bit map of second service request set according to the key of each service request in second service request set；The service request synchronizing device compares the corresponding flag bit of the first service request set flag bit corresponding with second service request set, obtaining belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss, can more intuitively determine the service request lost in this way.
With reference to first aspect and its above-mentioned implementation, in another implementation of first aspect, the service request synchronizing device determines that belonging to second service request set and being not belonging to the service request of first service request set is the service request of first memory node loss during breaking down, include: key of the service request synchronizing device according to each service request in Bloom Filter bloom filter algorithm and first service request set, determines the bitmap of first service request set；The service request synchronizing device determines the bitmap of second service request set according to the key of each service request in the bloom filter algorithm and second service request set；The service request synchronizing device compares the bitmap of first service request set and the bitmap of second service request set, determines that belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
With reference to first aspect and its above-mentioned implementation, in another implementation of first aspect, first sequence is different from second sequence.
With reference to first aspect and its above-mentioned implementation, in another implementation of first aspect, the service request synchronizing device indicates that second memory node sends the service request of the loss to first memory node, comprising: the service request synchronizing device receives the service request of the loss of second memory node transmission；The service request synchronizing device sends the service request of the loss to first memory node.
Second aspect provides a kind of device for the request of memory node synchronous service, the method in any possible implementation for executing above-mentioned first aspect or first aspect.Specifically, which includes the unit for executing the method in any possible implementation of above-mentioned first aspect or first aspect.
The third aspect provides a kind of device for the request of memory node synchronous service, comprising: storage
Unit and processor, the storage unit is for storing instruction, the processor is used to execute the instruction of memory storage, and when the processor executes the instruction of memory storage, the execution is so that the processor executes the method in any possible implementation of first aspect or first aspect.
Fourth aspect provides a kind of computer-readable medium, and for storing computer program, which includes the instruction for executing the method in any possible implementation of first aspect or first aspect.
In order to illustrate the technical solution of the embodiments of the present invention more clearly, will be briefly described below to attached drawing needed in the embodiment of the present invention.
Fig. 1 is the schematic diagram of storage cluster according to an embodiment of the present invention.
Fig. 2 is the schematic flow chart of the method according to an embodiment of the present invention for the request of memory node synchronous service.
Fig. 3 is the schematic diagram of the method for determining service request set according to an embodiment of the present invention.
Fig. 4 is another schematic diagram of the method for determining service request set according to an embodiment of the present invention.
Fig. 5 is another schematic diagram of the method for determining service request set according to an embodiment of the present invention.
Fig. 6 is the schematic block diagram of the device according to an embodiment of the present invention for the request of memory node synchronous service.
Fig. 7 is the schematic block diagram of the device according to another embodiment of the present invention for the request of memory node synchronous service.
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention is explicitly described, it is clear that described embodiment is a part of the embodiments of the present invention, rather than whole embodiments.
As shown in Figure 1, Fig. 1 is the physical structure of a storage cluster, and key-value memory node as shown in Figure 1 can provide the storage cluster of key-value interface for one, the storage cluster may include multiple ether (Ethernet) protocol interface hard disk, also known as IP disk, such as storage cluster shown in FIG. 1 includes two IP disks, or also may include more than two IP disk.
In addition, key-value memory node is also possible to the disk of the IP of single offer key-value interface；The key-value memory node is also possible to the offer key-value interface being deployed in cluster or single-deck
Virtual unit.
And the embodiment of the present invention describes a kind of method of memory node synchronous service request, this method is applied in storage system, which may include two key-value memory nodes as described above.In the storage system, service request can be concurrent, out-of-order execution, each key-value memory node can save the key-value data and the corresponding log of respective memory node of respective memory node respectively, two parts of key-value data can be namely saved in the storage system, while saving the corresponding log of two memory nodes.After 1 failure of memory node in storage system is restarted, since service request can be out-of-order in the memory node, concurrent execution, therefore the service request that memory node 1 is lost is not to be located next in the corresponding log of the memory node (log) 1, continuously, need efficiently to search the service request of these loss, therefore, the embodiment of the present invention describes a kind of method of memory node synchronous service request, the service request that the memory node of failure is lost can be accurately obtained, finishing service request synchronizes, improve the handling capacity that storage system executes service request.
Fig. 2 shows the schematic flow charts of the method 100 according to an embodiment of the present invention for the request of memory node synchronous service, this method 100 is applied in the storage system including the first memory node and the second memory node, first memory node is used to execute multiple service requests according to the first sequence, first memory node stores the first log, first log be used to be recorded in first memory node has executed in multiple service request each service request and each service request start execute the moment, second memory node is used to execute multiple service request according to the second sequence, second memory node stores the first log, second log be used to be recorded in second memory node has executed in multiple service request each service request and each service request start execute the moment, this method 1 00 can be executed by service request synchronizing device, the device can be a virtual module, which is located in any one memory node in the storage system, such as the first memory node or the second memory node, or other memory nodes, the embodiment of the present invention are not limited to this.As shown in Fig. 2, this method 100 includes:
S110, when first memory node is in the t for executing multiple service request1To t2When inside breaking down, service request synchronizing device determines the first service request set and the second service request set, which starts to execute the moment in t for what is recorded in first log1- 2dt to t2The set of service request in+2dt, second service request set start to execute the moment in t for what is recorded in second log1- dt to t2The set of service request in+dt, the dt is greater than or equal at the time of first memory node starts performance objective service request and second memory node starts to execute the difference between at the time of the target service is requested, and target service request is the service request in first service request set or second service request set；
S120, the service request synchronizing device determine that belonging to second service request set and being not belonging to the service request of first service request set is the service request of first memory node loss during breaking down；
S130, the service request synchronizing device indicate that second memory node sends the service request of the loss to first memory node.
Specifically, first memory node execute multiple service requests according to the first sequence and each service request for having been executed by the first log recording and it is corresponding execute the moment, second memory node according to each service request that the second sequence also executes multiple service request and has been executed by the second log recording and it is corresponding execute the moment, when in t1To t2In moment, the first memory node breaks down, then the first service request set is determined in the first log, which includes being recorded in the first log in t1- 2dt to t2The service request executed in+2dt the moment；The second service request set is determined also in the second log, which includes being recorded in the second log in t1- dt to t2The service request executed in+dt the moment, wherein, the dt is properly termed as maximum time span, dt is greater than or equal at the time of the first memory node starts performance objective service request and second memory node starts to execute the difference between at the time of the target service is requested, target service request is any one service request in multiple service requests that system issues, optionally, it can choose one in the whole service requests for belonging to the first service request set or the second service request set for the target service, the whole service requests for including for first service request set and the second service request set can satisfy the range of maximum time span dt.The service request that the second service request set will be belonged to again but be not belonging to the first service request set is determined as the service request that the first memory node is lost during failure, i.e. the service request of the loss is the service request that the first memory node is not carried out due to failure, in order to which the first memory node executes the service request of the loss.
Therefore, the method for the request of memory node synchronous service in the embodiment of the present invention, two memory nodes in storage system can not execute service request according to the sequence that service request issues, one when breaking down wherein, can by searching for be not belonging in different time sections the memory node to break down record service request but belong to normal storage nodes records service request be loss service request, to allow different memory nodes concurrently or out of sequence to execute service request, without the sequence number of special distribution and maintenance service request, and the service request that can also be accurately lost from normal memory node, finishing service request synchronizes, improve the handling capacity that storage system executes service request.
In embodiments of the present invention, the multiple service requests issued for storage system, the first memory node can execute multiple service request according to the first sequence, and the second memory node is executed according to the second sequence should
Multiple service requests, first sequence and the second sequence can be identical, it can also be different, the sequence for executing multiple service requests can be inconsistent with transmitting sequence, it can the concurrent or multiple service requests of Out-of-order execution, can avoid the need in this way specific assigned and maintenance service request sequence number, so as to cause limit service request handling capacity.Furthermore, the service request executed for each memory node record, can by first log recording the first memory node carried traffic request and the service request start execute the moment, by second log recording the second memory node carried traffic request and the service request start execute the moment.
In embodiments of the present invention, no matter the first memory node or the second memory node, all the execution sequence of service request is not limited, but it can limit the execution time to service request, if it exceeds preset time memory node is not carried out service request, i.e., within a certain period of time, storage system does not receive the response message that the memory node returns after having executed the service request, then system can re-issue the service request, which should re-execute the service request.Optionally, here preset time can be configured according to practical application, after presetting a time, if system is more than the response message that the preset time does not receive the memory node, then system can re-issue the service request, which can re-execute the service request.
In embodiments of the present invention, maximum time span can be defined, i.e. when any one service request, such as target service request is performed in t moment, is appeared in a log, that is, execute by a memory node, so in t-dt to t+dt this period at moment, the target service request also centainly appear in another log, by another memory node also execute, dt here is maximum time span.Such as, in t moment, target service request appears in the first log, namely executed by the first memory node, so in t-dt to t+dt this period at moment, which is centainly appeared in second day will, is executed by the second memory node, it is, the dt meets at the time of starting to execute target service request more than or equal to first memory node and second memory node starts to execute the difference between at the time of the target service is requested.Optionally, maximum time span dt can be preset according to the actual situation, and each service request that each memory node executes all meets the requirement of the maximum time span.Optionally, maximum time span dt can also be calculated after breaking down, and calculate the maximum time span of the service request in a period of time, and the embodiment of the present invention is not limited to this.
In S110, when first memory node is during executing multiple service request, in t1To t2When breaking down in the moment, then the first service request set is determined according to the first log, the second service request set is determined according to the second log, which is that this aims at t on 1st1- 2dt to t2The set of the service request executed recorded in+2dt the moment, which is should
Second day aims at t1- dt to t2The set of the service request executed recorded in+dt the moment, wherein the dt is maximum time span, which can carry out calculating acquisition according to the service request for including in the first service request set and the second service request set；In S120, determine that belonging to second service request set and being not belonging to the service request of first service request set is the service request of first memory node loss during breaking down, the service request lost during failure can be re-executed in order to restore normal first memory node, to realize that service request is synchronous, the handling capacity that storage system executes service request is improved.
In embodiments of the present invention, the first memory node and the second memory node meet the requirement of maximum time span when executing service request, when any memory node breaks down, for example, as shown in figure 3, the first memory node is in t1To t2Moment internal fault, i.e. the first storage is broken down in A times in Fig. 3, then the service request that the first memory node is lost in this period centainly belongs to the service request in the B section time in Fig. 3, that is, the second memory node is in t1- dt to t2The service request executed in+dt the moment, that is, appear in second day and aim at t1- dt to t2In the service request recorded in+dt the moment, the service request that these this time records is determined as the second service request set；Also, the service request lost is not belonging to C times, that is, the first memory node in t1- 2dt to t2The service request executed in+2dt the moment, that is, do not appear in the t in the first log1- 2dt to t2In the service request recorded in+2dt the moment, the service request that these this time records is determined as the first service request set.Therefore, the service request lost during determining the first memory node failure, it namely determines the service request for belonging to A time, that is, determines that belonging to the second service request set but being not belonging to the service request of the first service request set is the service request of the first memory node loss.
Optionally, as one embodiment, when the first memory node is in t1To t2When breaking down in the moment, determine that the service request that the first memory node defective device is lost, that is, determination belong to the second service request set, but be not belonging to the service request of the first service request set, the first service request set is the first memory node in t1- 2dt to t2The service request executed in+2dt the moment, the t being recorded in the first log1- 2dt to t2In+2dt the moment；Second service request is combined into the second memory node in t1- dt to t2The service request executed in+dt the moment, the t being recorded in the second log1- dt to t2In+dt the moment.Specifically, it can be ranked up by the service request in combining the first service request set and the second service request according to key, so that it is determined that going out the service request lost.For example, as shown in figure 4, A, multiple service requests are respectively included in B and C, here service request is by taking enter key (key) as an example, for example, put (key1), the key of the corresponding service request of serial number 1, in addition, the corresponding service request to lose of A, corresponding second service request set of B, C corresponds to the first service request set, determines that belonging to the second business asks
It seeks set but is not belonging to the service request of the first service request set, determine the service request for belonging to B but being not belonging to C, first the service request in B and C can be ranked up according to key, ranking results are as shown in Figure 4, it compares and knows according to the sequence of key, belong to B but be not belonging to C service request be respectively it is consistent in key2, key4, key6 and key7, with A, illustrate can accurately to judge in this way the service request lost.It is compared by the way of this sequence, it can be to avoid each service request recorded in traversal log, such as the key6 in B, it is key8 later it can be found that only including key5 in C when in lookup, whether it belongs to C, it then can not only determine that key6 is to lose data, can also determine key7 also must lose data, without judging key7 again, avoid the operation of each service request in traversal B.
It optionally, can also be by flag bit, to determine the service request of loss as one embodiment.Specifically, such as, as shown in Figure 5, each service request in second service request set is indicated with flag bit, that is the corresponding flag bit of a service request, determines the mark bit map of the second service request set, as a result as shown in the B in Fig. 5, black square expression performs the corresponding service request of the flag bit, and white square expression is not carried out the corresponding service request of the flag bit；Similarly each service request in the first service request set is also indicated with flag bit, as a result as shown in the C in Fig. 5, and B and the key for the service request that flag bit identical in C indicates are also identical, such as, for the first flag bit in B, assuming that the key of the corresponding service request of the flag bit is key1, then the key of the corresponding service request of the first flag bit in C is also key1, and the first flag bit in B is white piece, expression is not carried out the key1, the first flag bit in C is black patch, and expression has executed the key1.After the mark bit map for determining the corresponding B of the second service request set C corresponding with the first service request set respectively, service request synchronizing device can be according to the service request A of the determining loss for belonging to B but being not belonging to C of the mark bit map, specifically, formula being passed through: A=B-B ∩ C=B^ (B&C) is calculated, wherein, & indicate with, ^ indicates exclusive or, i.e. first by B, C step-by-step with, again by result and B exclusive or, the corresponding flag bit of service request A of loss can be found, as shown in Figure 5, the service request A of determining loss is respectively the 4th flag bit and the 6th flag bit, it is reversed again to search the service request that can be obtained by loss specifically, determine the 4th flag bit and the corresponding service request of the 6th flag bit.
It optionally, can also be by Bloom Filter (bloom filter) algorithm, to determine the service request of loss as one embodiment.Specifically, it is determined that the service request in the first service request set and the second service request set is then input with key, such as first service request set includes input key3, then is input with key3 so that service request is bloom filter as an example；The corresponding output numerical value of input value is calculated by a function, such as by any one Hash (hash) function h (x), with
Key3 is input, calculates the value of output valve h (key3)；Any several bit values of the output valve are taken again, such as take latter two of output valve h (key3), are determined the position for belonging to the key3 in the bitmap of the first service request set according to the double figures, are set 1 for the bit at the position.The rest may be inferred, it is respectively input by each service request in the first service request set and the second service request set, calculate position of each service request in respective bitmap, and each service request is represented in corresponding bitmap, in this way, the bitmap of the first service request set and the bitmap of the second service request set can be determined respectively, two bitmaps are compared, indicate to need to acquire the service request of the first memory node loss with A, the service request of the second service request set is indicated with B, the service request of the first service request set is indicated with C, : A=B-B ∩ C=B^ (B&C) is searched and belongs to B but be not belonging to the service request A of loss of C and can pass through formula to calculate, wherein, & indicate with, ^ indicates exclusive or, i.e. first by B, C step-by-step with, again by result and B exclusive or, in this way The position of the corresponding bitmap of service request A of loss can be found.Can be obtained by the corresponding service request in the position by function retrospectively calculate again is the service request lost；Or when generating bitmap, while each corresponding service request of bit for 1 is recorded, then the service request A lost can be directly determined out by the relationship of the record.
In S130, which indicates that second memory node sends the service request of the loss to first memory node.Specifically, the service request synchronizing device is according to the first service request set and the second service request set, it can determine in the second log of the second memory node, which service request belongs to the service request that the first memory node is not carried out during the first memory node failure, these service requests are the service request that the first memory node is lost.The service request synchronizing device can indicate that the service request of the loss is sent to the first memory node by the second memory node, then the service request of the loss is executed by the first memory node, to which synchronous service is requested, the handling capacity that storage system executes service request is improved.
In embodiments of the present invention, which directly can be sent to the first memory node for the service request of the loss for belonging to the first memory node recorded in the second log including the second memory node according to the instruction of service request synchronizing device；Or second memory node the service request of the loss is sent to the service request synchronizing device, the service request of loss is sent to the first memory node by the service request synchronizing device.Or, first memory node is after fault recovery, solicited message can be sent to service request synchronizing device, which is used for the service request for requesting to lose, which indicates that the second memory node sends the service request lost to the first memory node according to the solicited message.Alternatively, the service request synchronizing device indicates that second memory node to the service request that first memory node sends the loss includes that the service request synchronizing device indicates that the first memory node is sent out to the second memory node
Solicited message is sent, which is used for the service request for requesting to lose, and the second memory node sends the service request lost according to solicited message to the first memory node.Or, first memory node sends solicited message to the second memory node, the solicited message be used for request loss service request, the service request synchronizing device indicate second memory node according to solicited message to the service request that first memory node sends the loss include that the embodiment of the present invention is not limited to this.
It should be understood that, in various embodiments of the present invention, magnitude of the sequence numbers of the above procedures are not meant that the order of the execution order, and the execution sequence of each process should be determined by its function and internal logic, and the implementation process of the embodiments of the invention shall not be constituted with any limitation.
Therefore, the method for the request of memory node synchronous service in the embodiment of the present invention, two memory nodes in storage system can not execute service request according to the sequence that service request issues, when a memory node breaks down wherein, can by searching for be not belonging in different time sections the memory node to break down record service request but belong to normal storage nodes records service request be loss service request, to allow different memory nodes concurrently or out of sequence to execute service request, without the sequence number of special distribution and maintenance service request, and the service request that can also be accurately lost from normal memory node, finishing service request synchronizes, improve the handling capacity that storage system executes service request.
Above in conjunction with Fig. 1 to Fig. 5, the method according to an embodiment of the present invention for the request of memory node synchronous service is described in detail, below in conjunction with Fig. 6 to Fig. 7, describes the device according to an embodiment of the present invention for the request of memory node synchronous service.
Fig. 6 shows the schematic block diagram of the device 200 according to an embodiment of the present invention for the request of memory node synchronous service, the device 200 can be located in the storage system including the first memory node and the second memory node, first memory node is used to execute multiple service requests according to the first sequence and stores the first log, first log be used to record each service request executed in multiple service request and each service request executed start execute the moment, second memory node be used to execute multiple service request according to the second sequence and store the second log second log be used to record each service request executed in multiple service request and each service request executed start execute the moment, the device 200 includes:
First determination unit 210, for when first memory node is in the t for executing multiple service request1To t2When inside breaking down, the first service request set and the second service request set are determined, which starts to execute the moment in t for what is recorded in first log1- 2dt to t2The set of service request in+2dt, second service request set start to execute the moment in t for what is recorded in second log1- dt to t2The set of service request in+dt, the dt are greater than or equal to first memory node and start
At the time of performance objective service request and second memory node starts to execute the difference between at the time of the target service is requested, and target service request is the service request in first service request set or second service request set；
Second determination unit 220, for determining that belonging to second service request set and being not belonging to the service request of first service request set is the service request of first memory node loss during breaking down；
Processing unit 230 is used to indicate the service request that second memory node sends the loss to first memory node.
Therefore, the device for the request of memory node synchronous service in the embodiment of the present invention, it can be in the case that two memory nodes within the storage system can not execute service request according to the sequence that service request issues, one when breaking down wherein, by searching for be not belonging in different time sections the memory node to break down record service request but belong to normal storage nodes records service request be loss service request, to allow different memory nodes concurrently or out of sequence to execute service request, without the sequence number of special distribution and maintenance service request, and the service request that can also be accurately lost from normal memory node, finishing service request synchronizes, improve the handling capacity that storage system executes service request.
Optionally, which is specifically used for: being respectively ranked up the service request in first service request set and second service request set according to the key of service request；The service request in first service request set and second service request set is compared according to the result of sequence, obtaining belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
Optionally, which is specifically used for: according to the key of each service request in first service request set, determining the mark bit map of first service request set；The service request synchronizing device determines the mark bit map of second service request set according to the key of each service request in second service request set；The corresponding mark bit map of the first service request set mark bit map corresponding with second service request set is compared, obtaining belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
Optionally, which is specifically used for: according to the key of each service request in Bloom Filter bloom filter algorithm and first service request set, determining the bitmap of first service request set；The service request synchronizing device determines the bitmap of second service request set according to the key of each service request in the bloom filter algorithm and second service request set；The synchronous dress of the service request
The bitmap for setting the bitmap and second service request set that compare first service request set determines that belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
Optionally, which can be different from second sequence, can also be identical.
It should be understood that, device 200 according to an embodiment of the present invention for the request of memory node synchronous service can correspond to execute the method 100 in the embodiment of the present invention, and above and other operation and/or function for the modules in the device 200 of memory node synchronous service request is respectively in order to realize the corresponding process of each method in Fig. 2, for sake of simplicity, details are not described herein.
Therefore, the device for the request of memory node synchronous service in the embodiment of the present invention, it can be in the case that two memory nodes within the storage system can not execute service request according to the sequence that service request issues, one when breaking down wherein, by searching for be not belonging in different time sections the memory node to break down record service request but belong to normal storage nodes records service request be loss service request, to allow different memory nodes concurrently or out of sequence to execute service request, without the sequence number of special distribution and maintenance service request, and the service request that can also be accurately lost from normal memory node, finishing service request synchronizes, improve the handling capacity that storage system executes service request.
As shown in Figure 7, the embodiment of the invention also provides a kind of devices 300 for the request of memory node synchronous service, including processor 310, memory 320 and bus system 330, the device 300 is located in the storage system including the first memory node and the second memory node, first memory node is used to execute multiple service requests according to the first sequence and stores the first log, first log be used to record each service request executed in multiple service request and each service request executed start execute the moment, second memory node is used to execute multiple service request according to the second sequence and stores the second log, second log be used to record each service request executed in multiple service request and each service request executed start execute the moment.
Wherein, processor 310 is connected with memory 320 by bus system 330, which for storing instruction, and stores the first log and the second log, which is used to execute the instruction of the memory 320 storage.The memory 320 stores program code, and processor 310 can call the program code stored in memory 320 to execute following operation: when first memory node is in the t for executing multiple service request1To t2When inside breaking down, the first service request set and the second service request set are determined, which starts to execute the moment in t for what is recorded in first log1- 2dt to t2The set of service request in+2dt, second service request set are opened for what is recorded in second log
Begin to execute the moment in t1- dt to t2The set of service request in+dt, the dt is greater than or equal at the time of first memory node starts performance objective service request and second memory node starts to execute the difference between at the time of the target service is requested, and target service request is the service request in first service request set or second service request set；Determine that belonging to second service request set and being not belonging to the service request of first service request set is the service request of first memory node loss during breaking down；Indicate that second memory node sends the service request of the loss to first memory node.
Therefore, the device for the request of memory node synchronous service in the embodiment of the present invention, it can be in the case that two memory nodes within the storage system can not execute service request according to the sequence that service request issues, one when breaking down wherein, by searching for be not belonging in different time sections the memory node to break down record service request but belong to normal storage nodes records service request be loss service request, to allow different memory nodes concurrently or out of sequence to execute service request, without the sequence number of special distribution and maintenance service request, and the service request that can also be accurately lost from normal memory node, finishing service request synchronizes, improve the handling capacity that storage system executes service request.
It should be understood that, in embodiments of the present invention, the processor 310 can be central processing unit (Central Processing Unit, referred to as " CPU "), which can also be other general processors, digital signal processor (DSP), specific integrated circuit (ASIC), ready-made programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor etc..
The memory 320 may include read-only memory and random access memory, and provide instruction and data to processor 310.The a part of of memory 320 can also include nonvolatile RAM.For example, memory 320 can be with the information of storage device type.
The bus system 330 can also include power bus, control bus and status signal bus in addition etc. in addition to including data/address bus.But for the sake of clear explanation, various buses are all designated as bus system 330 in figure.
During realization, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 310 or the instruction of software form.The step of method in conjunction with disclosed in the embodiment of the present invention, can be embodied directly in hardware processor and execute completion, or in processor hardware and software module combination execute completion.Software module can be located at random access memory, flash memory, read-only memory, in the storage medium of this fields such as programmable read only memory or electrically erasable programmable memory, register maturation.The storage medium is located at memory 320, and processor 310 reads the information in memory 320, in conjunction with it
Hardware completes the step of above method.To avoid repeating, it is not detailed herein.
Optionally, as one embodiment, processor 310 can call the program code stored in memory 320 to execute following operation: respectively be ranked up the service request in first service request set and second service request set according to the key of service request；The service request in first service request set and second service request set is compared according to the result of sequence, obtaining belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
Optionally, as one embodiment, processor 310 can call the program code stored in memory 320 to execute following operation: according to the key of each service request in first service request set, determine the mark bit map of first service request set；According to the key of each service request in second service request set, the mark bit map of second service request set is determined；The corresponding flag bit of the first service request set flag bit corresponding with second service request set is compared, obtaining belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
Optionally, as one embodiment, processor 310 can call the program code stored in memory 320 to execute following operation: according to the key of each service request in Bloom Filter bloom filter algorithm and first service request set, determine the bitmap of first service request set；According to the key of each service request in the bloom filter algorithm and second service request set, the bitmap of second service request set is determined；The bitmap of first service request set and the bitmap of second service request set are compared, determines that belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
Optionally, which can be different from second sequence, can also be identical.
It should be understood that, device 300 according to an embodiment of the present invention for the request of memory node synchronous service can correspond to the device 200 for the request of memory node synchronous service in the embodiment of the present invention, and it can correspond to execute the corresponding main body in 100 according to the method for the embodiment of the present invention, and above and other operation and/or function for the modules in the device 300 of memory node synchronous service request is respectively in order to realize the corresponding process of each method in Fig. 2, for sake of simplicity, details are not described herein.
Therefore, the device for the request of memory node synchronous service in the embodiment of the present invention, it can be in the case that two memory nodes within the storage system can not execute service request according to the sequence that service request issues, one when breaking down wherein, by searching for be not belonging in different time sections the memory node to break down record service request but belong to normal storage nodes records service request be loss service request, to allow different memory nodes concurrently or out of sequence to execute service request, without the sequence number of special distribution and maintenance service request, and it can also accurately be obtained from normal memory node
To the service request of loss, finishing service request is synchronized, and improves the handling capacity that storage system executes service request.
Those of ordinary skill in the art may be aware that unit described in conjunction with the examples disclosed in the embodiments of the present disclosure and algorithm steps, can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Professional technician can use different methods to achieve the described function each specific application, but such implementation should not be considered as beyond the scope of the present invention.
It is apparent to those skilled in the art that for convenience and simplicity of description, system, the specific work process of device and unit of foregoing description can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods may be implemented in other ways.Such as, the apparatus embodiments described above are merely exemplary, such as, the division of the unit, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed mutual coupling, direct-coupling or communication connection can be through some interfaces, the indirect coupling or communication connection of device or unit, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, and component shown as a unit may or may not be physical unit, it can and it is in one place, or may be distributed over multiple network units.It can some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
In addition, the functional units in various embodiments of the present invention may be integrated into one processing unit, it is also possible to each unit and physically exists alone, can also be integrated in one unit with two or more units.
If the function is realized in the form of SFU software functional unit and when sold or used as an independent product, can store in a computer readable storage medium.Based on this understanding, substantially the part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products technical solution of the present invention in other words, the computer software product is stored in a storage medium, it uses including some instructions so that a computer equipment (can be personal computer, server or the network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory),
The various media that can store program code such as random access memory (RAM, Random Access Memory), magnetic or disk.
It is described above; only a specific embodiment of the invention, but scope of protection of the present invention is not limited thereto, and anyone skilled in the art is in the technical scope disclosed by the present invention; it can easily think of the change or the replacement, should be covered by the protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (15)
- A method of it is requested for memory node synchronous service, it is characterized in that, the method is applied in the storage system including the first memory node and the second memory node, first memory node is used to execute multiple service requests according to the first sequence and stores the first log, first log be used to record each service request that the first memory node described in the multiple service request has executed and each service request that first memory node has executed start execute the moment, second memory node is used to execute the multiple service request according to the second sequence and stores the second log, second log be used to record each service request that the second memory node described in the multiple service request has executed and each service request that second memory node has executed start execute the moment, the described method includes:When first memory node is in the t for executing the multiple service request1To t2When inside breaking down, service request synchronizing device determines that the first service request set and the second service request set, first service request set start to execute the moment in t for what is recorded in first log1- 2dt to t2The set of service request in+2dt, second service request set start to execute the moment in t for what is recorded in second log1- dt to t2The set of service request in+dt, the dt is greater than or equal at the time of first memory node starts performance objective service request and second memory node starts to execute the difference between at the time of the target service is requested, and the target service request is the service request in first service request set or second service request set；The service request synchronizing device determines that belonging to second service request set and being not belonging to the service request of first service request set is the service request of first memory node loss during breaking down；The service request synchronizing device indicates that second memory node sends the service request of the loss to first memory node.
- According to the method for claim 1, it is characterized in that, the service request synchronizing device determines that belonging to second service request set and being not belonging to the service request of first service request set is the service request of first memory node loss during breaking down, comprising:Service request in first service request set and second service request set is ranked up by the service request synchronizing device according to the key of service request respectively；The service request synchronizing device compares the service request in first service request set and second service request set according to the result of sequence, and obtaining belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
- The method according to claim 1, wherein the service request synchronizing device Determine that belonging to second service request set and being not belonging to the service request of first service request set is the service request of first memory node loss during breaking down, comprising:The service request synchronizing device determines the mark bit map of first service request set according to the key of each service request in first service request set；The service request synchronizing device determines the mark bit map of second service request set according to the key of each service request in second service request set；The service request synchronizing device compares the mark bit map of first service request set and the mark bit map of second service request set, and obtaining belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
- According to the method for claim 1, it is characterized in that, the service request synchronizing device determines that belonging to second service request set and being not belonging to the service request of first service request set is the service request of first memory node loss during breaking down, comprising:The service request synchronizing device determines the bitmap of first service request set according to the key of each service request in Bloom Filter bloom filter algorithm and first service request set；The service request synchronizing device determines the bitmap of second service request set according to the key of each service request in the bloom filter algorithm and second service request set；The service request synchronizing device compares the bitmap of first service request set and the bitmap of second service request set, determines that belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
- Method according to claim 1 to 4, which is characterized in that first sequence is different from second sequence.
- A kind of device for the request of memory node synchronous service, it is characterized in that, described device is located in the storage system including the first memory node and the second memory node, first memory node is used to execute multiple service requests according to the first sequence and stores the first log, described first day for will record each service request that the first memory node described in the multiple service request has executed and each service request that first memory node has executed start execute the moment, second memory node is used to execute the multiple service request according to the second sequence and stores the second constitution, second log be used to record each service request that the second memory node described in the multiple service request has executed and each service request that second memory node has executed start execute the moment, described device includes:First determination unit, for when first memory node is in the t for executing the multiple service request1To t2When inside breaking down, the first service request set and the second service request set are determined, described first Service request set starts to execute the moment in t for what is recorded in first log1- 2dt to t2The set of service request in+2dt, second service request set start to execute the moment in t for what is recorded in second log1- dt to t2The set of service request in+dt, the dt is greater than or equal at the time of first memory node starts performance objective service request and second memory node starts to execute the difference between at the time of the target service is requested, and the target service request is the service request in first service request set or second service request set；Second determination unit, for determining that belonging to second service request set and being not belonging to the service request of first service request set is the service request of first memory node loss during breaking down；Processing unit is used to indicate the service request that second memory node sends the loss to first memory node.
- Device according to claim 6, which is characterized in that first determination unit is specifically used for:The service request in first service request set and second service request set is ranked up according to the key of service request respectively；The service request in first service request set and second service request set is compared according to the result of sequence, obtaining belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
- Device according to claim 6, which is characterized in that first determination unit is specifically used for:According to the key of each service request in first service request set, the mark bit map of first service request set is determined；According to the key of each service request in second service request set, the mark bit map of second service request set is determined；The corresponding flag bit of first service request set and the corresponding flag bit of second service request set are compared, obtaining belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
- Device according to claim 6, which is characterized in that first determination unit is specifically used for:According to the key of each service request in Bloom Filter bloom filter algorithm and first service request set, the bitmap of first service request set is determined；According to the key of each service request in the bloom filter algorithm and second service request set, the bitmap of second service request set is determined；The bitmap of first service request set and the bitmap of second service request set are compared, determines that belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
- Device according to any one of claims 6 to 9, which is characterized in that first sequence is different from second sequence.
- A kind of device for the request of memory node synchronous service, it is characterized in that, described device is located in the storage system including the first memory node and the second memory node, first memory node is used to execute multiple service requests according to the first sequence and stores the first log, first log be used to record each service request that the first memory node described in the multiple service request has executed and each service request that first memory node has executed start execute the moment, second memory node is used to execute the multiple service request according to the second sequence and stores the second log, second log be used to record each service request that the second memory node described in the multiple service request has executed and each service request that second memory node has executed start execute the moment, described device includes: to deposit Reservoir and processor,The memory is used to store first log and second log,The processor is used for:When first memory node is in the t for executing the multiple service request1To t2When inside breaking down, determine that the first service request set and the second service request set, first service request set start to execute the moment in t for what is recorded in first log1- 2dt to t2The set of service request in+2dt, second service request set start to execute the moment in t for what is recorded in second log1- dt to t2The set of service request in+dt, the dt is greater than or equal at the time of first memory node starts performance objective service request and second memory node starts to execute the difference between at the time of the target service is requested, and the target service request is the service request in first service request set or second service request set；Determine that belonging to second service request set and being not belonging to the service request of first service request set is the service request of first memory node loss during breaking down；Indicate that second memory node sends the service request of the loss to first memory node.
- Device according to claim 11, which is characterized in that the processor is specifically used for:Respectively by the service request in first service request set and second service request set It is ranked up according to the key of service request；The service request in first service request set and second service request set is compared according to the result of sequence, obtaining belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
- Device according to claim 11, which is characterized in that the processor is specifically used for:According to the key of each service request in first service request set, the mark bit map of first service request set is determined；According to the key of each service request in second service request set, the mark bit map of second service request set is determined；The corresponding mark bit map of first service request set and the corresponding mark bit map of second service request set are compared, obtaining belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
- Device according to claim 11, which is characterized in that the processor is specifically used for:According to the key of each service request in Bloom Filter bloom filter algorithm and first service request set, the bitmap of first service request set is determined；According to the key of each service request in the bloom filter algorithm and second service request set, the bitmap of second service request set is determined；The bitmap of first service request set and the bitmap of second service request set are compared, determines that belonging to second service request set and being not belonging to the service request of first service request set is the service request of the loss.
- Device described in any one of 1 to 14 according to claim 1, which is characterized in that first sequence is different from second sequence.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2015/097431 WO2017101016A1 (en) | 2015-12-15 | 2015-12-15 | Method and apparatus for synchronizing service request of storage node |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107710165A true CN107710165A (en) | 2018-02-16 |
| CN107710165B CN107710165B (en) | 2020-01-03 |
Family
ID=59055361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201580002564.1A Active CN107710165B (en) | 2015-12-15 | 2015-12-15 | Method and device for storage node synchronization service request |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107710165B (en) |
| WO (1) | WO2017101016A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111352763A (en) * | 2020-03-11 | 2020-06-30 | Oppo（重庆）智能科技有限公司 | Information processing method and related product |
| CN112181701A (en) * | 2020-09-23 | 2021-01-05 | 中国建设银行股份有限公司 | Method and device for positioning abnormal service request |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1728099A (en) * | 2004-06-18 | 2006-02-01 | 微软公司 | Efficient changing of replica sets in distributed fault-tolerant computing system |
| CN101079896A (en) * | 2007-06-22 | 2007-11-28 | 西安交通大学 | A multi-availability mechanism coexistence framework of concurrent storage system |
| CN102693324A (en) * | 2012-01-09 | 2012-09-26 | 西安电子科技大学 | Distributed database synchronization system, synchronization method and node management method |
| CN102882699A (en) * | 2011-07-14 | 2013-01-16 | 华为技术有限公司 | Method and device for distributing edge nodes, edge node controller |
| CN103064759A (en) * | 2012-12-18 | 2013-04-24 | 华为技术有限公司 | Data recovery method and device |
| CN103198159A (en) * | 2013-04-27 | 2013-07-10 | 国家计算机网络与信息安全管理中心 | Transaction-redo-based multi-copy consistency maintaining method for heterogeneous clusters |
| US20140325256A1 (en) * | 2013-04-25 | 2014-10-30 | Netapp, Inc. | Systems and methods for managing disaster recovery in a storage system |
| CN105095013A (en) * | 2015-06-04 | 2015-11-25 | 华为技术有限公司 | Data storage method, data recovery method, and relevant device and system |
| US20150347250A1 (en) * | 2014-05-30 | 2015-12-03 | Altibase Corp. | Database management system for providing partial re-synchronization and partial re-synchronization method of using the same |
-
2015
- 2015-12-15 WO PCT/CN2015/097431 patent/WO2017101016A1/en active Application Filing
- 2015-12-15 CN CN201580002564.1A patent/CN107710165B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1728099A (en) * | 2004-06-18 | 2006-02-01 | 微软公司 | Efficient changing of replica sets in distributed fault-tolerant computing system |
| CN101079896A (en) * | 2007-06-22 | 2007-11-28 | 西安交通大学 | A multi-availability mechanism coexistence framework of concurrent storage system |
| CN102882699A (en) * | 2011-07-14 | 2013-01-16 | 华为技术有限公司 | Method and device for distributing edge nodes, edge node controller |
| CN102693324A (en) * | 2012-01-09 | 2012-09-26 | 西安电子科技大学 | Distributed database synchronization system, synchronization method and node management method |
| CN103064759A (en) * | 2012-12-18 | 2013-04-24 | 华为技术有限公司 | Data recovery method and device |
| US20140325256A1 (en) * | 2013-04-25 | 2014-10-30 | Netapp, Inc. | Systems and methods for managing disaster recovery in a storage system |
| CN103198159A (en) * | 2013-04-27 | 2013-07-10 | 国家计算机网络与信息安全管理中心 | Transaction-redo-based multi-copy consistency maintaining method for heterogeneous clusters |
| US20150347250A1 (en) * | 2014-05-30 | 2015-12-03 | Altibase Corp. | Database management system for providing partial re-synchronization and partial re-synchronization method of using the same |
| CN105095013A (en) * | 2015-06-04 | 2015-11-25 | 华为技术有限公司 | Data storage method, data recovery method, and relevant device and system |
Non-Patent Citations (2)
| Title |
|---|
| 柴梦竹: "基于分布式***的锁服务器的容错机制的设计与实现", 《南昌教育学院学报》 * |
| 范捷: "拜占庭***技术研究综述", 《软件学报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111352763A (en) * | 2020-03-11 | 2020-06-30 | Oppo（重庆）智能科技有限公司 | Information processing method and related product |
| CN111352763B (en) * | 2020-03-11 | 2023-10-31 | Oppo（重庆）智能科技有限公司 | Information processing method and related product |
| CN112181701A (en) * | 2020-09-23 | 2021-01-05 | 中国建设银行股份有限公司 | Method and device for positioning abnormal service request |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107710165B (en) | 2020-01-03 |
| WO2017101016A1 (en) | 2017-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11320991B2 (en) | Identifying sub-health object storage devices in a data storage system | |
| US11360854B2 (en) | Storage cluster configuration change method, storage cluster, and computer system | |
| US10560315B2 (en) | Method and device for processing failure in at least one distributed cluster, and system | |
| US10915412B2 (en) | System and method for live migration of a virtual machine | |
| CN106331098B (en) | Server cluster system | |
| CN110071821B (en) | Method, node and storage medium for determining the status of a transaction log | |
| JP6382454B2 (en) | Distributed storage and replication system and method | |
| CN105426439B (en) | Metadata processing method and device | |
| US11271814B2 (en) | Online capacity-expanding and online capacity-reducing methods and apparatuses for distributed consensus system | |
| US9152491B2 (en) | Job continuation management apparatus, job continuation management method and job continuation management program | |
| WO2017152860A1 (en) | Heartbeat information sending method and device, and heartbeat sending node | |
| CN111049928B (en) | Data synchronization method, system, electronic device and computer readable storage medium | |
| CN107656705B (en) | Computer storage medium and data migration method, device and system | |
| CN111404730B (en) | State synchronization method and device of virtual router, electronic equipment and storage medium | |
| CN106331081B (en) | Information synchronization method and device | |
| CN105323271B (en) | Cloud computing system and processing method and device thereof | |
| CN107710165A (en) | Method and apparatus for the request of memory node synchronous service | |
| CN107943615B (en) | Data processing method and system based on distributed cluster | |
| CN111404737B (en) | Disaster recovery processing method and related device | |
| CN108984602B (en) | Database control method and database system | |
| CN116795601A (en) | Dual-computer hot backup method, system, device, computer equipment and storage medium | |
| WO2014094296A1 (en) | Distributed storage control method, device, and system | |
| JP2014016953A (en) | Unshared type database system, synchronizing device, database server, its synchronizing method, and synchronizing program | |
| US20220166829A1 (en) | Data Synchronization Method and Apparatus | |
| JP5685213B2 (en) | Differential replication system, master database device, and slave database device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |