CN103365741A - Method and equipment for snapshot and recovery of virtual machine cluster - Google Patents
Method and equipment for snapshot and recovery of virtual machine cluster Download PDFInfo
- Publication number
- CN103365741A CN103365741A CN2012101031205A CN201210103120A CN103365741A CN 103365741 A CN103365741 A CN 103365741A CN 2012101031205 A CN2012101031205 A CN 2012101031205A CN 201210103120 A CN201210103120 A CN 201210103120A CN 103365741 A CN103365741 A CN 103365741A
- Authority
- CN
- China
- Prior art keywords
- virtual machine
- message
- snapshot
- cluster
- dye marker
- 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
Images
Abstract
The embodiment of the invention relates to a method and equipment for snapshot and recovery of a virtual machine cluster. The embodiment of the invention provides a method for generating a snapshot relevant to one virtual machine in the virtual machine cluster to generate a snapshot of the cluster, a method for generating the snapshot of the virtual machine cluster, and a method for recovering the virtual machine cluster and corresponding equipment. The embodiment of the invention provides a novel message dyeing mechanism to ensure that not only can the local snapshots of the individual virtual machines be recorded, but also a state of a communication channel for supporting communication of the virtual machines can be recorded effectively when the snapshot of the virtual machine cluster is created. The embodiment of the invention further discloses corresponding equipment. With the adoption of the method and the equipment, the snapshot of the virtual machine cluster can be generated more effectively, and the virtual machine cluster can be recovered to a specified snapshot moment correspondingly.
Description
Technical field
Embodiments of the invention relate generally to virtual machine, more specifically, relate to for the snapshot of cluster virtual machine and the method and apparatus of recovery.
Background technology
Virtual machine (Virtual Machine, VM) refers to specifically be applied in the application execution environment that creates on the hardware platform of physical machine by a class, and the user can move to use also by this environment and occur with it alternately, just as using physical machine.The software application that creates VM is commonly referred to virtual machine manager (hypervisor).Manager can be disposed and operate on the physical machine, and the VM manager can create and move one or more virtual machines.Along with increasing Distributed Application is deployed in cloud (cloud) environment, cluster virtual machine (cluster) has obtained increasingly extensive use.Term " cluster virtual machine " refers to utilize each other communication port to intercom mutually and the logic packaging body of a plurality of virtual machines of swap data as used herein.A cluster virtual machine is usually served one and is used or system.Virtual machine in the cluster can be deployed on the same VM manager, also can stride different VM managers and distribute.
Know that for the single virtual machine, snapshot (snapshot) is an important operation.The purpose of snapshot operation is to preserve virtual machine at all states, data and the context (context) of given time.Snapshot operation is most important for the fault recovery of virtual machine.For example, when a virtual machine in operation gross error occurs, can virtual machine be returned to residing state of the moment and the context that creates this snapshot according to snapshot.Equally, in cluster virtual machine, also be absolutely necessary for the snapshot operation of whole cluster.
For a cluster virtual machine that is comprised of a plurality of virtual machines, snapshot operation should be preserved in the cluster all virtual machines at given time state and context separately.Moreover, owing to may communicate by communication port between the different virtual machine in the cluster, so the cluster snapshot also should be preserved communication port between the virtual machine at snapshot state constantly.
Known cluster virtual machine snapshot operation often can't be preserved a plurality of virtual machines at the context of strict synchronization by degree of preservation.The more important thing is that communication port in the cluster can't be caught and preserve to known cluster virtual machine snapshot effectively at snapshot state constantly, and these passages may be at snapshot constantly just at the transmission of data.Like this, the cluster snapshot becomes imperfect because having lost the information of communication port, and may destroy the data consistency in the cluster.In addition, a lot of cluster virtual machine snapshots of the prior art depend on VME operating system (OS) or use, so that these schemes can't be applicable to the environment of system virtualization and cloud computing.
Therefore, this area needs a kind of more efficiently snapshot mechanism of the cluster virtual machine for comprising a plurality of virtual machines.
Summary of the invention
In view of the above-mentioned problems in the prior art, the present invention proposes a kind of method and apparatus that is used for the generating virtual machines cluster of novelty.
In a first aspect of the present invention, provide a kind of snapshot of being associated with a virtual machine in the cluster virtual machine of generating to be used for the method for generation cluster snapshot, described virtual machine is communicated by letter with other virtual machines in the described cluster by communication port.Described method comprises: in response to the snapshot indication, the local express that creates described virtual machine shines; In response to the startup of described establishment, make each that will send to other virtual machines the described cluster from described virtual machine spread out of message and be added dye marker, the described local express that described dye marker indication is creating described virtual machine shines; And receive the message of importing into described dye marker in response to other virtual machines from described cluster, store the described relevant information of message of importing into as the part of the snapshot of described communication port.
In a second aspect of the present invention, a kind of method of the snapshot for the generating virtual machines cluster is provided, described cluster comprises a plurality of virtual machines that utilize communication port to communicate with one another.Described method comprises: send the snapshot indication by the first virtual machine that is chosen as the coordinator in described a plurality of virtual machines to other virtual machines; In response to the indication of described snapshot, generate the snapshot that is associated with each virtual machine in described a plurality of virtual machines according to the described method of paragraph above; And the snapshot that is associated with each virtual machine in described a plurality of virtual machines of collection, to be used for generating the snapshot of described cluster.
In a third aspect of the present invention, provide a kind of cluster virtual machine is returned to given snapshot method constantly, described cluster comprises a plurality of virtual machines, and described cluster uses the method that paragraph above describes and generates at described snapshot snapshot constantly.Described method comprises: sent to other virtual machines by the first virtual machine that is chosen as the coordinator in described a plurality of virtual machines and recover indication; In response to described recovery indication, each virtual machine that makes described a plurality of virtual machines according to the local express of this virtual machine according to returning to described snapshot state constantly; And load the message of having stored according to the snapshot of described communication port, so that each described message is sent to the destination virtual machine.
In a fourth aspect of the present invention, provide a kind of snapshot of being associated with a virtual machine in the cluster virtual machine of generating to be used for the equipment of generation cluster snapshot, described virtual machine is communicated by letter with other virtual machines in the described cluster by communication port.Described equipment comprises: local fast photographing device, configuration are used for creating in response to the snapshot indication local express photograph of described virtual machine; The message dyeing apparatus, configuration is used for making in response to the startup of described establishment and will spreads out of message from each of other virtual machines that described virtual machine sends to described cluster and be added dye marker, and the described local express that described dye marker indication is creating described virtual machine shines; And the passage fast photographing device, configuration is used for receiving in response to other virtual machines from described cluster and does not have the importing message into of described dye marker and store the described relevant information of message of importing into as the part of the snapshot of described communication port.
As mentioned summary and hereinafter detailed description according to the embodiment of the present invention, have proposed a kind of message dyeing mechanism for when generating each virtual machine local express photograph, generate the snapshot of the communication port between these virtual machines.For any individual virtual machine in the cluster, when this virtual machine begins to create the local express photograph, it utilizes dyeing mechanism that all that will send at communication port are spread out of message and dyes, and shines in order to indicate this virtual machine creating local express to other virtual machines.When the predetermined condition such as finishing such as local snapshot creation and be satisfied, virtual machine finishes spreading out of the dyeing of message.
On the other hand, import message into for each that receives, whether the destination virtual machine detects this source virtual machine that imports message into and this message is dyeed.If this message is not colored, illustrate that then this message just sent by source virtual machine constantly at snapshot, therefore should be saved with the part as the communication port snapshot.On the other hand, be colored if import message into, illustrate that this message is that source virtual machine just is issued constantly at snapshot, so need not to comprise the information of this message in the cluster snapshot.
In this way, embodiments of the present invention can generate snapshot for cluster virtual machine with a kind of more effectively, reliably and flexibly method.
Description of drawings
By reading with reference to the accompanying drawings detailed description hereinafter, above-mentioned and other purposes of the embodiment of the invention, the feature and advantage easy to understand that will become.In the accompanying drawings, show some embodiment of the present invention in exemplary and nonrestrictive mode, wherein:
Fig. 1 shows a plurality of mutually schematic block diagrams of the cluster 100 of the virtual machine of intercommunication that comprise according to an illustrative embodiment of the invention;
Fig. 2 show according to an illustrative embodiment of the invention be used for to generate the snapshot that is associated with a virtual machine of cluster virtual machine with the indicative flowchart of the method 200 that is used for generation cluster snapshot;
What Fig. 3 showed according to the present invention another exemplary embodiment is used for generating the snapshot that is associated with a virtual machine of cluster virtual machine with the indicative flowchart of the method 300 that is used for generation cluster snapshot;
Fig. 4 shows the indicative flowchart of the method 400 of the snapshot that is used for the generating virtual machines cluster according to an illustrative embodiment of the invention;
Fig. 5 shows the indicative flowchart that is used for cluster virtual machine is returned to the method 500 of given time according to an illustrative embodiment of the invention;
Fig. 6 show according to an illustrative embodiment of the invention be used for to generate the snapshot that is associated with a virtual machine of cluster virtual machine with the schematic block diagram of the equipment 600 that is used for generation cluster snapshot; And
Fig. 7 shows the schematic block diagram of the computer system 700 that is fit to put into practice the embodiment of the invention.
In each accompanying drawing, identical or corresponding label represents identical or corresponding part.
Embodiment
Some exemplary embodiments are below with reference to the accompanying drawings described principle of the present invention and spirit.Should be appreciated that providing these embodiment only is for those skilled in the art can being understood better and then realize the present invention, and be not to limit the scope of the invention by any way.
In general, according to embodiments of the invention, the snapshot of a cluster virtual machine in the given moment (being called " snapshot constantly ") comprises two parts: the snapshot of the individual virtual machine of each in the cluster, and the snapshot of the communication port of communicating by letter between the virtual support machine.More particularly, the snapshot of communication port mainly refers to those message of constantly having transmitted at communication port at snapshot, or claims message in transit.
For this reason, embodiments of the invention based on thinking be: when each virtual machine in the cluster snapshot constantly create separately local express according to during, the message of sending by communication port is labelled.Be the purpose of explanation and description, add tagged this process and can exemplarily be called " dyeing " to spreading out of message.Dyeing in order to indicate this message to the destination virtual machine to message is just to be issued constantly at snapshot.Thus, the destination virtual machine only those no dyeings of memory channel import message into as the part of communication port snapshot because the message of no dyeing constantly is transmitted at communication port at snapshot.
At first with reference to figure 1, it shows the schematic block diagram of cluster virtual machine 100 according to an illustrative embodiment of the invention.In cluster 100, there be n manager (hypervisor), namely manager 1 to manager n.These managers are the application for establishment, operation and management virtual machine, and operate on the corresponding physical machine (not shown).Each manager can dispose for establishment, the one or more virtual machines of operation and management.For example, as shown in Figure 1, manager 1 is in charge of virtual machine VM
1-1, VM
1-2To VM
1-i, manager n is in charge of virtual machine VM
N-1, VM
N-2To VM
N-j
Especially, in cluster virtual machine shown in Figure 1, can utilize the communication port (not shown) to communicate with one another between the different virtual machines.Communication port between the virtual machine for example can be network, for example the Internet or Intranet.Alternatively or additionally, communication port also can be inter-process communication mechanisms etc.Scope of the present invention is unrestricted in this regard.Notice that it only is exemplary describing cluster 100 with reference to figure 1, the number shown in the figure and configuration only are illustrative rather than restrictive.N, the i, the j that above describe with reference to figure 1 are natural number.
Below with reference to Fig. 2, its show according to an illustrative embodiment of the invention be used for to generate with cluster virtual machine (for example, the cluster among Fig. 1 100) in the snapshot that is associated of a virtual machine with the indicative flowchart of the method 200 that is used for generating the cluster snapshot.According to embodiments of the invention, method 200 can be performed for each virtual machine in the cluster.For example, the main body of manner of execution 200 can be associated with virtual machine be called " snapshot agent " application of being responsible for snapshot operation specially or process (agent).This also will be explained below.
After method 200 beginnings, at step S202, the local express that creates described virtual machine in response to the snapshot indication shines.As mentioned below, according to embodiments of the invention, a virtual machine manager can be selected as snapshot promoter or coordinator in the cluster.This virtual machine manager can send here said " snapshot indication " to all virtual machines in the cluster.For example, can specify snapshot constantly in the snapshot indication, so that all virtual machines in the cluster generate the snapshot that this snapshot is located constantly.
In response to receiving such indication, each the virtual machine creating local express in the cluster shines.The local express photograph of virtual machine is the record to the local state of virtual machine, comprises data, mode of operation, context, storer operating position, processor operating position, disk operating position, the network connection state of this virtual machine, etc.These are known to those skilled in the art, do not repeat them here.
Continuation is with reference to figure 2, next at step S204, in response to the startup of the establishment of local express photograph, make each that will send to other virtual machines the cluster from this virtual machine spread out of message and be added dye marker, the local express that the dye marker indication is creating this virtual machine shines.
The performed operation of step S204 can be regarded as " dyeing " operation, that is, and and to adding mark (be called " dye marker) from the message that this virtual machine sends to other virtual machines the cluster.This dye marker indicates to other virtual machines: the source virtual machine of message is creating local express and is shining when sending this message.In other words, by means of dye marker, the destination virtual machine of receipt message can be known: the message that is colored is just sent by source virtual machine constantly at snapshot, does not belong to the part of communication port state, thereby need not to be saved and record.
According to some embodiment, at step S204 place, that can utilize the package that spreads out of message does not arrange described dye marker with the position.As indicated above, the communication port between the virtual machine can be network, for example based on the network of ICP/IP protocol or udp protocol.In such embodiments, common existence is not used in the message package position or spare bits.These do not have clear and definite fixing in procotol, can be by customization to be used for carry information.Therefore, can be with the position dye marker not being set in the message package.In other words, if the specific position of not using in the package is set to the first predetermined value, then indicating this outgoing message to have dye marker, is through hyperchromatic message therefore.Otherwise, if should specifically not use the position to be set to second predetermined value different from the first predetermined value, then indicate this message not have dye marker, be the message of no dyeing therefore.
Alternatively, also can add additional bit to whole message package, to be used for arranging such dye marker.More specifically, in such embodiments, dye marker can be invested on the message package integral body, thereby form new package by encapsulating again.Above-described all only is the exemplary embodiment that realizes dye marker, and other embodiment also are possible, and scope of the present invention is unrestricted in this regard.
Next, method proceeds to step S206, receives the message of importing into dye marker in response to other virtual machines from cluster, storage with this import into message for information about with the ingredient as the snapshot of communication port.
More particularly, when creating virtual machine local express photograph, may exist from the message of other virtual machines in the cluster and be imported into by communication port.As indicated above, each virtual machine in the cluster virtual machine at snapshot constantly with manner of execution 200.Therefore, the message of just being sent by other virtual machines in the cluster constantly at snapshot will be colored, and, have dye marker that is.Thus, in destination virtual machine one side, can detect from what communication port received and import message into and whether have dye marker.Do not have dye marker if detect the message of importing into of reception, can think that then this message just was transmitted at communication port before the zero hour at snapshot, belonged to message in transit.Thus, will store this message as the part of the snapshot of communication port at step S206.
By method 200, each virtual machine in the cluster can dye to the message of sending from this virtual machine constantly at snapshot.Thus, can judge as take over party's destination virtual machine and should preserve which message to consist of the snapshot of communication port.Like this, by manner of execution 200, each virtual machine has not only created the local express photograph of oneself, has also created the snapshot of the communication port related with it.By the communication port snapshot that local express shines and they create that makes up all individual virtual machines, just can generate the snapshot (this also will describe in detail the generation method of cluster snapshot in conjunction with Fig. 4 hereinafter) of whole cluster virtual machine.
Below with reference to Fig. 3, what it showed according to the present invention another exemplary embodiment is used for generating the snapshot that is associated with a virtual machine of cluster virtual machine with the indicative flowchart of the method 300 that is used for generation cluster snapshot.Identical with method 200, according to embodiments of the invention, method 300 can be performed for each virtual machine in the cluster, and can be carried out by the snapshot agent that is associated with virtual machine.Will be understood that method 300 can be considered to above a kind of specific specific implementation of the method 200 described in conjunction with Fig. 2.
After method 300 beginnings, at step S302, start the establishment of the local express photograph of virtual machine in response to the snapshot indication.The snapshot indication is for example sent by the virtual machine that serves as the coordinator in the cluster, and this also will be explained below.In addition, according to embodiments of the invention, the establishment of virtual machine local express photograph can start at once in response to the snapshot indication.Alternatively, the establishment of virtual machine local express photograph also can start a period of time after receiving snapshot indication, needs only for example to be not later than to receive from first of other virtual machines in the cluster to be colored the message of importing into of (having dye marker).This only is exemplary, and other startup opportunitys or trigger condition also are possible.
In the embodiment shown in the method 300, create the local express of virtual machine according to comprising two steps, that is, be activated in response to the establishment of virtual machine local express photograph at step S304, suspend the operation of virtual machine; And at step S306, store the data relevant with this virtual machine and state with the part as the local express photograph on the backstage.
Be appreciated that step S302-S306 corresponding to the step S202 that above describes with reference to figure 2, that is, the local express that creates virtual machine shines.Especially, according to embodiments of the invention, execution in step S304 is not necessary with the operation that suspends virtual machine, that is, step S304 is optional.According to some alternative, shine thereby can in the situation that virtual machine continues to carry out, preserve snapshot virtual machine state establishment local express constantly.Scope of the present invention is unrestricted in this regard.
In addition, in the embodiment that virtual machine is suspended, the operation of virtual machine can recover the term of execution of step S306 or afterwards.For example, in certain embodiments, can be after the local state of virtual machine that mark need to be stored or the normal operation that after actual storage is finished, recovers virtual machine.Alternatively or additionally, virtual machine also can resume operation in response to other conditions, for example suspend and reach the schedule time, receive the explicit recovery instruction from cluster, etc.Scope of the present invention is unrestricted in this regard.
Then at step S310, by the import message of communication port reception from other virtual machines in the cluster.At this moment, because virtual machine is in halted state, the message of importing into that therefore receives at step S310 is not directly to be forwarded to virtual machine, but is for example processed by the snapshot agent of manner of execution 300 in advance.
Notice that although in Fig. 3 step S308 and S310 are presented at after step S304 and the S306, this only is for clear purpose is described.In fact, step S308 and the S310 startup that is in response to equally local snapshot creation among the step S302 is carried out.In other words, the operation of step S308 and S310 and step S304 and/or S306 can carry out simultaneously or exist at least in part overlapping.
Next, method 300 proceeds to step S312, imports message in this judgement and whether has dye marker.As mentioned above, one imports message into and does not have dye marker and illustrate that this message has been the message in transit that is transmitted at communication port constantly at snapshot, thereby should be stored in the snapshot of cluster (more particularly, being kept in the snapshot of communication port).On the other hand, have dye marker if import message into, illustrate that then this message is that source virtual machine just sends constantly at snapshot, therefore need not to preserve the part as the cluster snapshot.
Particularly, as shown in Figure 3, do not have dye marker (branch's "No") if determine to import into message at step S312 place, method 300 proceeds to step S314, this message stores that will not have a dye marker with buffer zone that current virtual machine is associated in.Method 300 proceeds to step S318 then, and this will be explained below.
On the other hand, have dye marker (branch's "Yes") if determine to import into message at step S312 place, method 300 will be carried out a series of corresponding processing to this type of message of importing into that is colored.Usually, according to the embodiment of the present invention, the processing that this class has the message of dye marker should not make the snapshot of communication port that any renewal or change occur.Particularly, method 300 proceeds to step S316 along branch's "Yes" of step S312, removes dye marker entrained in the message at this.Method 300 proceeds to step S318 then.
Next at step S318, judge whether virtual machine resumes operation.As mentioned above, the operation at step S304 time-out virtual machine is optional.Correspondingly, step S318 also is optional.In other words, in the situation that virtual machine operations is not suspended, method 300 can be at skips steps S318 after step S314 and the S316 and direct execution in step S320.
Particularly, if determine that at step S318 place virtual machine not yet resumes operation (branch's "No"), method 300 is returned step S310 and is imported message into to continue receiving other.On the other hand, if determine recovery operation of virtual machine (branch's "Yes") at step S318 place, method 300 proceeds to step S320, this virtual machine interval is received, the treated message of importing into is transmitted to virtual machine.Be appreciated that, the message that is forwarded to virtual machine at step S320 place comprises namely that all that be buffered in the buffer zone at step S314 do not have the message of importing into of dye marker, also comprise have dye marker originally, but be removed dye marker at step S316 those import message into.
Note, be not transmitted to virtual machine with the message of dye marker at step S320 in buffer zone and do not represent these message are deleted from buffer zone.On the contrary, these message still can be stored in the buffer zone so that in subsequent step S324 processing, this will be explained below.
After step S320, method 300 judges at step S322 place whether the predetermined state that is associated with virtual machine is met.According to embodiments of the invention, predetermined condition is usually relevant with the state of virtual machine.For example, in certain embodiments, predetermined condition can be included in the establishment of the virtual machine local express photograph of step S302 place startup and finish.Alternatively, predetermined condition can also comprise starting at from the moment that step S302 starts the local express photograph and passed through a predetermined period.For example, according to some embodiment of the present invention, can when all being met, these two think that predetermined condition is met.In other words, can be as the criterion with that satisfies afterwards in these two conditions.Notice that these predetermined conditions are only exemplary, other predetermined conditions equally within the scope of the present invention.
If determine that at step S322 place predetermined condition is not satisfied (branch's "No"), method 300 is returned step S310 and is continued reception from the message of importing into of other virtual machines.On the other hand, if determine that at step S322 place predetermined condition is met (branch's "Yes"), method 300 proceeds to step S324, this storage be buffered in the buffer zone not with the relevant information of all message of dye marker, with the part as the communication port snapshot of cluster.Here the relevant information of said message comprises message itself, also can comprise source, destination and other any relevant parameters or the information of message.
After execution in step S324, can think that the snapshot that is associated with virtual machine has created to finish.The snapshot that generates comprises two parts generally: the local express of virtual machine shines and the communication port snapshot.
Alternatively, method 300 is execution in step S326 then, adds dye marker in order to stop to spreading out of message.In other words, satisfy in response to predetermined condition, the message that spreads out of of other virtual machines no longer will be added dye marker (that is, no longer being colored) in the cluster so that this virtual machine will send at communication port.This is because the snapshot of virtual machine is generated at this moment.
Notice that step S326 is optional, and it can be carried out or simultaneously execution according to different order with step S324.Method 300 finishes after step S326.
Can see, in the embodiment shown in fig. 3, be not to receive the undyed message of importing into just at once it to be preserved to create the communication port snapshot at every turn, but in predetermined condition (for example, local snapshot creation is finished, or overtime) the unified message of importing into that does not have dye marker that receives during this period of preserving afterwards.Certainly, this only is exemplary, does not in fact have importing into of dye marker just to be stored as the communication port snapshot at once after the message also be feasible receiving each.
Above referring to figs. 2 and 3 having described how generating snapshot of each virtual machine in the cluster virtual machine.Below with reference to Fig. 4, it shows the indicative flowchart of the method that is used to whole cluster virtual machine generating snapshot 400 according to an illustrative embodiment of the invention.
After method 400 beginnings, at step S402, send the snapshot indication by a virtual machine that is chosen as the coordinator in a plurality of virtual machines in the cluster (for example, being designated as " the first virtual machine ") to other virtual machines.According to embodiments of the invention, the first virtual machine can be selected at random.Alternatively, the selection of the first virtual machine can be based on mode of operation, the load of each virtual machine in the cluster, etc.And for example, the first virtual machine also can be in advance agreement or artificial appointment.In a word, can select or specify according to any suitable mode as the first virtual machine of coordinator, scope of the present invention be unrestricted in this regard.
Next, at step S404, all virtual machines in the cluster (comprising the first virtual machine itself as the coordinator) generate snapshot associated therewith in response to the snapshot indication.Especially, according to embodiments of the invention, each virtual machine generates the snapshot that is associated according to above-described method (for example, method 200 or 300).In this way, the snapshot that generates comprises the local express photograph of virtual machine, and the snapshot of the communication port that is associated with this virtual machine.
At last, at step S406, all virtual machines from cluster are collected the local express photograph of this virtual machine that generates and the snapshot of communication port.These snapshots are combined, and have namely generated cluster at given snapshot snapshot constantly.As example, according to some embodiment of the present invention, each virtual machine can be after snapshot creation is finished be submitted to the result the first virtual machine as the coordinator so that the snapshot that each virtual machine is generated by the first virtual machine (comprise local express according to and communication port snapshot) gather and integrate.Alternatively, but each virtual machine also can be stored in the snapshot of each self-generating the memory location of public visit, so that the first virtual machine is from accessing and obtain snapshot here.Various Committing Mechanisms all are possible, and scope of the present invention is unrestricted in this regard.
Below with reference to Fig. 5, its show according to an illustrative embodiment of the invention be used for will comprise that the cluster virtual machine of a plurality of virtual machines returns to the indicative flowchart of given snapshot method 500 constantly.Notice that cluster is to generate according to the method 400 of above describing with reference to figure 4 at described snapshot snapshot constantly.
After method 500 beginnings, at step S502, the first virtual machine that is chosen as the coordinator in a plurality of virtual machines by cluster sends to other virtual machines and recovers indication.According to embodiments of the invention, the first virtual machine can be selected at random.Alternatively, the selection of the first virtual machine can be based on mode of operation, the load of each virtual machine in the cluster, etc.And for example, the first virtual machine also can be in advance agreement or artificial appointment.In a word, can select or specify according to any suitable mode as the first virtual machine of coordinator, scope of the present invention be unrestricted in this regard.
Especially, in certain embodiments, the first virtual machine that serves as the coordinator in the first virtual machine that serves as the coordinator at step S502 place and the method 400 at step S402 place is identical.Certainly, the two also can be different.
Next, method 500 proceeds to step S504, in response to recovering indication, makes each virtual machine (comprising the first virtual machine itself as the coordinator) in the cluster return to the snapshot state in the moment according to the local express photograph of this virtual machine oneself.Running status according to local snapshot restore virtual machine is well known by persons skilled in the art, does not repeat them here.
At last, at step S506, load the message of having stored according to the communication port snapshot, make each described message be sent to the destination virtual machine.For example, these message can be loaded into the local virtual interchanger of being responsible for information receiving and transmitting in the virtual machine, and are sent to immediately correct destination virtual machine.
According to some embodiment of the present invention, each virtual machine can will be finished after recovery operation is finished and report the first virtual machine of submitting to as the coordinator.The recovery of all virtual machines in receiving cluster of the first virtual machine is finished after the report, confirms that the recovery operation of cluster is finished.Alternatively, but each virtual machine also can be finished recovery separately the memory location that report is stored in public visit, so that the first virtual machine is from accessing and obtain to recover to finish report here.Various Committing Mechanisms all are possible, and scope of the present invention is unrestricted in this regard.
With reference now to Fig. 6,, its show according to an illustrative embodiment of the invention be used for to generate the snapshot that is associated with a virtual machine of cluster virtual machine with the schematic block diagram of the equipment 600 that is used for generation cluster snapshot.This virtual machine is communicated by letter with other virtual machines in the cluster by communication port.
As shown in the figure, equipment 600 comprises: local fast photographing device 602, configuration are used for creating in response to the snapshot indication local express photograph of described virtual machine; Message dyeing apparatus 604, configuration is used for making in response to the startup of described establishment and will spreads out of message from each of other virtual machines that described virtual machine sends to described cluster and be added dye marker, and the described local express that described dye marker indication is creating described virtual machine shines; And the passage fast photographing device, configuration is used for receiving in response to other virtual machines from described cluster and does not have the importing message into of described dye marker and store the described relevant information of message of importing into as the part of the snapshot of described communication port.
According to some optional embodiment of the present invention, described local fast photographing device 602 can comprise: pause device, and configuration is used for suspending the operation of described virtual machine; And back-up device, configuration is used at backstage storage data and the state relevant with described virtual machine.According to some optional embodiment of the present invention, equipment 600 may further include: recovery device, configuration are used for the term of execution of back-up device or the operation that recovers afterwards described virtual machine.
According to some optional embodiment of the present invention, message dyeing apparatus 604 can comprise: the first dyeing apparatus, configuration be used for utilizing the described package that spreads out of message with described dye marker is not set; Perhaps the second dyeing apparatus disposes for adding additional bit to described package to be used for arranging described dye marker.
According to some optional embodiment of the present invention, passage fast photographing device 606 can comprise: the message buffering device, and configuration is used for the described message buffering that imports into to buffer zone; The first message transmission device, configuration are used for the described message of importing into is transmitted to described virtual machine; And message storage devices, configuration is used for being met in response to definite predetermined condition relevant with described virtual machine, stores the described relevant information of message of importing into as the part of the snapshot of described communication port.
According to some optional embodiment of the present invention, equipment 600 may further include: dyed message processing apparatus, configuration is used for receiving the message of importing into described dye marker in response to other virtual machines from described cluster, processes that have a described dye marker described imported message into and the snapshot that do not upgrade described communication port.
According to some optional embodiment of the present invention, dyed message processing apparatus can comprise: message solution dyeing apparatus, configuration are used for removing described dye marker from the described message of importing into described dye marker; And second message transmission device, configuration is used for and will be transmitted to described virtual machine through the described described message of importing into that removes.
According to some optional embodiment of the present invention, equipment 600 may further include: the dyeing forbidden device, configuration is used for being met in response to the predetermined condition that is associated with described virtual machine, makes each that will send to other virtual machines the described cluster from described virtual machine spread out of message and is not added dye marker.
According to some optional embodiment of the present invention, it is one of following that described predetermined condition comprises: the described local snapshot creation of described virtual machine is finished; And from beginning to create the described local express of described virtual machine according to starting at through scheduled time slot.
For the purpose of clear, the sub-device that optional device and each device comprise is not shown among Fig. 6.Yet, should be appreciated that each device that comprises in the equipment 600 corresponds respectively to above referring to figs. 2 and 3 the method 200 of describing and each step of 300.Thus, the device that above is equally applicable to equipment 600 and wherein comprises referring to figs. 2 and 3 the operation described and feature does not repeat them here.
In addition, should be appreciated that equipment 600 can utilize variety of way to realize.For example, in certain embodiments, equipment 600 can utilize software and/or firmware to realize.For example, equipment 600 may be implemented as the application that each virtual machine in the cluster is associated, and for example is called the virtual machine snapshot agency.Alternatively or additionally, equipment 600 can partially or fully be realized based on hardware.Other modes known or in the future exploitation also are feasible now, and scope of the present invention is unrestricted in this regard.
Below with reference to Fig. 7, it shows the schematic block diagram of the computer system 700 that is suitable for putting into practice the embodiment of the invention.For example, computer system 700 can be served as the resident physical machine thereon of virtual machine.
As shown in Figure 7, computer system can comprise: CPU (CPU (central processing unit)) 701, RAM (random access memory) 702, ROM (ROM (read-only memory)) 703, system bus 704, hard disk controller 705, keyboard controller 706, serial interface controller 707, parallel interface controller 708, display controller 709, hard disk 710, keyboard 711, serial external unit 712, parallel external unit 713 and display 714.In these equipment, with system bus 704 coupling CPU 701, RAM 702, ROM 703, hard disk controller 705, keyboard controller 706, serialization controller 707, parallel controller 708 and display controller 709 arranged.Hard disk 710 and hard disk controller 705 couplings, keyboard 711 and keyboard controller 706 couplings, serial external unit 712 and serial interface controller 707 couplings, parallel external unit 713 and parallel interface controller 708 couplings, and display 714 and display controller 709 couplings.Should be appreciated that the described structured flowchart of Fig. 7 illustrates just to the purpose of example, rather than limitation of the scope of the invention.In some cases, can increase or reduce as the case may be some equipment.
As mentioned above, equipment 600 can be realized by hardware, such as chip, ASIC, SOC etc.These hardware can be integrated in the computer system 700.In addition, embodiments of the invention also can be realized by the form of computer program.For example, the method 200-500 that describes with reference to figure 2-Fig. 5 can realize by computer program.This computer program can be stored in RAM for example shown in Figure 7 704, ROM 704, hard disk 710 and/or any suitable storage medium, perhaps downloads on the computer system 700 from suitable position by network.Computer program can comprise the computer code part, and it comprises can be by the programmed instruction of suitable treatment facility (for example, the CPU shown in Fig. 7 701) execution.Described programmed instruction can comprise the instruction for implementation method 200-500 any one or a plurality of step at least.
Above spirit of the present invention and principle have been explained in conjunction with some specific embodiments.According to embodiments of the invention, provide a kind of technical scheme that becomes the cluster virtual machine snapshot by means of message dyeing mechanism next life.During the snapshot of generating virtual machines cluster, the local express photograph of each virtual machine not only can be obtained in this way, and the constantly state of communication port of snapshot can be effectively recorded.Like this, compared with prior art, embodiments of the present invention can generate snapshot for cluster virtual machine with a kind of more effectively, reliably and flexibly method.
According to embodiments of the invention, the cluster snapshot operation can be carried out by the snapshot agent of each virtual machine.Like this, the cluster snapshot has the good transparency, all is transparent for the application on the virtual machine and OS.And this scheme has good extendability and versatility, and back compatible has the cluster virtual machine framework, for example based on the cluster of TCP or UDP network service.
Should be noted that embodiments of the invention can realize by the combination of hardware, software or software and hardware.Hardware components can utilize special logic to realize; Software section can be stored in the storer, and by suitable instruction execution system, for example microprocessor or special designs hardware are carried out.Those having ordinary skill in the art will appreciate that above-mentioned equipment and method can and/or be included in the processor control routine with computer executable instructions realizes, for example such as the mounting medium of disk, CD or DVD-ROM, provide such code such as the programmable memory of ROM (read-only memory) (firmware) or such as the data carrier of optics or electronic signal carrier.Equipment of the present invention and module thereof can be by such as VLSI (very large scale integrated circuit) or gate array, realize such as the semiconductor of logic chip, transistor etc. or such as the hardware circuit of the programmable hardware device of field programmable gate array, programmable logic device etc., also can use the software of being carried out by various types of processors to realize, also can by the combination of above-mentioned hardware circuit and software for example firmware realize.
The communication network of mentioning in the instructions can comprise disparate networks, include but not limited to LAN (Local Area Network) (" LAN "), wide area network (" WAN "), according to the network of IP agreement (for example, the Internet) and ad-hoc network (for example, ad hoc peer-to-peer network).
Although should be noted that some devices or the sub-device of having mentioned equipment in above-detailed, this division only is not enforceable.In fact, according to embodiments of the invention, the feature of above-described two or more devices and function can be specialized in a device.Otherwise, the feature of an above-described device and function can Further Division for to be specialized by a plurality of devices.
In addition, although described in the accompanying drawings the operation of the inventive method with particular order,, this is not that requirement or hint must be carried out these operations according to this particular order, or the operation shown in must carrying out all could realize the result of expectation.On the contrary, the step of describing in the process flow diagram can change execution sequence.Additionally or alternatively, can omit some step, a plurality of steps be merged into a step carry out, and/or a step is decomposed into a plurality of steps carries out.
Although described the present invention with reference to some specific embodiments, should be appreciated that the present invention is not limited to disclosed specific embodiment.The present invention is intended to contain interior included various modifications and the equivalent arrangements of spirit and scope of claims.The scope of claims meets the most wide in range explanation, thereby comprises all such modifications and equivalent structure and function.
Claims (18)
1. the snapshot that is associated with a virtual machine in the cluster virtual machine of a generation is with the method for the snapshot that is used for generating described cluster, and described virtual machine is communicated by letter with other virtual machines in the described cluster by communication port, and described method comprises:
In response to the snapshot indication, the local express that creates described virtual machine shines;
In response to the startup of described establishment, make each that will send to other virtual machines the described cluster from described virtual machine spread out of message and be added dye marker, the described local express that described dye marker indication is creating described virtual machine shines; And
Receive the message of importing into described dye marker in response to other virtual machines from described cluster, store the described relevant information of message of importing into as the part of the snapshot of described communication port.
2. method according to claim 1 wherein creates the local express of described virtual machine according to comprising:
Suspend the operation of described virtual machine;
At backstage storage data and the state relevant with described virtual machine; And
In described backstage memory period or the operation that recovers afterwards described virtual machine.
3. method according to claim 1 wherein spreads out of message to each that will send to other virtual machines the described cluster from described virtual machine and adds dye marker and comprise:
That utilizes the described package that spreads out of message does not arrange described dye marker with the position; Perhaps
Add additional bit to be used for arranging described dye marker to described package.
4. method according to claim 1 wherein receives the described relevant information of importing message into of message stores of importing into described dye marker in response to other virtual machines from described cluster and comprises as the part of the snapshot of described communication port:
With the described message buffering that imports in buffer zone;
The described message of importing into is transmitted to described virtual machine; And
Be met in response to definite predetermined condition relevant with described virtual machine, store the described relevant information of message of importing into as the part of the snapshot of described communication port.
5. method according to claim 1 further comprises:
Receive the message of importing into described dye marker in response to other virtual machines from described cluster, process that have a described dye marker described imported message into and the snapshot that do not upgrade described communication port.
6. method according to claim 5, wherein process the described message of importing into described dye marker and comprise:
Remove described dye marker from the described message of importing into described dye marker; And
To be transmitted to described virtual machine through the described described message of importing into that removes.
7. method according to claim 1 further comprises:
Be met in response to the predetermined condition that is associated with described virtual machine, make each that will send to other virtual machines the described cluster from described virtual machine spread out of message and be not added dye marker.
8. according to claim 4 or 7 described methods, wherein said predetermined condition comprise following at least one:
The described local snapshot creation of described virtual machine is finished; And
From beginning to create the described local express of described virtual machine according to starting at through scheduled time slot.
9. method that is used for the snapshot of generating virtual machines cluster, described cluster comprises a plurality of virtual machines that utilize communication port to communicate with one another, described method comprises:
Send the snapshot indication by the first virtual machine that is chosen as the coordinator in described a plurality of virtual machines to other virtual machines;
In response to the indication of described snapshot, each described method generates the snapshot that is associated with each virtual machine in described a plurality of virtual machines according to claim 1-8; And
Collect the described snapshot that is associated with each virtual machine in described a plurality of virtual machines, with for the snapshot that generates described cluster.
10. one kind returns to given snapshot method constantly with cluster virtual machine, and described cluster comprises a plurality of virtual machines, and described cluster requires 9 described methods and generate in described snapshot snapshot right to use constantly, and described method comprises:
Send the recovery indication by the first virtual machine that is chosen as the coordinator in described a plurality of virtual machines to other virtual machines;
In response to described recovery indication, each virtual machine that makes described a plurality of virtual machines according to the local express of this virtual machine according to returning to described snapshot state constantly; And
Snapshot according to described communication port loads the message of having stored, so that each described message is sent to the destination virtual machine.
11. one kind is the equipment of a virtual machine generating snapshot in the cluster virtual machine, described virtual machine is communicated by letter with other virtual machines in the described cluster by communication port, and described equipment comprises:
Local fast photographing device, configuration are used for creating in response to the snapshot indication local express photograph of described virtual machine;
The message dyeing apparatus, configuration is used for making in response to the startup of described establishment and will spreads out of message from each of other virtual machines that described virtual machine sends to described cluster and be added dye marker, and the described local express that described dye marker indication is creating described virtual machine shines; And
Passage fast photographing device, configuration are used for receiving in response to other virtual machines from described cluster and do not have the importing message into of described dye marker and store the described relevant information of message of importing into as the part of the snapshot of described communication port.
12. equipment according to claim 11, wherein said local fast photographing device comprises:
Pause device, configuration is used for suspending the operation of described virtual machine;
Back-up device, configuration are used at backstage storage data and the state relevant with described virtual machine; And
Recovery device, configuration are used in the operating period of described back-up device or the operation that recovers afterwards described virtual machine.
13. equipment according to claim 11, wherein said message dyeing apparatus comprises:
The first dyeing apparatus, configuration be used for utilizing the described package that spreads out of message with described dye marker is not set; Perhaps
The second dyeing apparatus, configuration are used for adding additional bit to be used for arranging described dye marker to described package.
14. equipment according to claim 11, wherein said passage fast photographing device comprises:
The message buffering device, configuration is used for the described message buffering that imports into to buffer zone;
The first message transmission device, configuration are used for the described message of importing into is transmitted to described virtual machine; And
Message storage devices, configuration are used for being met in response to definite predetermined condition relevant with described virtual machine, store the described relevant information of message of importing into as the part of the snapshot of described communication port.
15. equipment according to claim 11 further comprises:
Dyed message processing apparatus, configuration is used for receiving the message of importing into described dye marker in response to other virtual machines from described cluster, processes that have a described dye marker described imported message into and the snapshot that do not upgrade described communication port.
16. equipment according to claim 15, wherein said dyed message processing apparatus comprises:
Message solution dyeing apparatus, configuration are used for removing described dye marker from the described message of importing into described dye marker; And
The second message transmission device, configuration are used for and will be transmitted to described virtual machine through the described described message of importing into that removes.
17. equipment according to claim 11 further comprises:
The dyeing forbidden device, configuration is used for being met in response to the predetermined condition that is associated with described virtual machine, makes each that will send to other virtual machines the described cluster from described virtual machine spread out of message and is not added dye marker.
18. according to claim 14 or 17 described equipment, wherein said predetermined condition comprise following at least one:
The described local snapshot creation of described virtual machine is finished; And
From beginning to create the described local express of described virtual machine according to starting at through scheduled time slot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210103120.5A CN103365741B (en) | 2012-03-30 | 2012-03-30 | For the snapshot of cluster virtual machine and the method and apparatus of recovery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210103120.5A CN103365741B (en) | 2012-03-30 | 2012-03-30 | For the snapshot of cluster virtual machine and the method and apparatus of recovery |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103365741A true CN103365741A (en) | 2013-10-23 |
| CN103365741B CN103365741B (en) | 2016-05-04 |
Family
ID=49367159
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210103120.5A Active CN103365741B (en) | 2012-03-30 | 2012-03-30 | For the snapshot of cluster virtual machine and the method and apparatus of recovery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103365741B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729264A (en) * | 2013-12-23 | 2014-04-16 | 国云科技股份有限公司 | Method for backing up and restoring Windows virtual machine system disk |
| CN105117346A (en) * | 2015-09-24 | 2015-12-02 | 上海爱数软件有限公司 | Automatic testing method and system for distributed system of virtualization platform |
| CN107844420A (en) * | 2017-10-27 | 2018-03-27 | 南京国电南自电网自动化有限公司 | A kind of dichotomy in-circuit emulation and error-checking method based on virtual machine snapshot |
| CN108959547A (en) * | 2018-07-02 | 2018-12-07 | 山东汇贸电子口岸有限公司 | A kind of PV snapshot distributed experiment & measurement system restoration methods |
| CN109313565A (en) * | 2016-05-02 | 2019-02-05 | 诺基亚通信公司 | Snapshot creation in virtual network environment |
| CN109753340A (en) * | 2017-11-08 | 2019-05-14 | 阿里巴巴集团控股有限公司 | Virtual machine snapshot processing method, apparatus and system |
| CN109783272A (en) * | 2017-11-10 | 2019-05-21 | 阿里巴巴集团控股有限公司 | Disk snapshot processing method, device and equipment |
| CN110972497A (en) * | 2018-11-02 | 2020-04-07 | 深信服科技股份有限公司 | Disaster recovery method and device for virtualization platform |
| CN111008095A (en) * | 2019-12-17 | 2020-04-14 | 山东超越数控电子股份有限公司 | State snapshot generation and recovery method facing edge cloud |
| CN113791870A (en) * | 2021-09-24 | 2021-12-14 | 上海交通大学 | Fine-grained migration method and system for distributed system of WebAssembly virtual machine |
| CN116150797A (en) * | 2023-04-21 | 2023-05-23 | 深圳市科力锐科技有限公司 | Data protection method, system, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101097526A (en) * | 2006-06-29 | 2008-01-02 | 联想(北京)有限公司 | Virtual machine system and accessing control method of hardware equipment |
| CN101243413A (en) * | 2005-06-24 | 2008-08-13 | 信科索尔特公司 | System and method for virtualizing backup images |
| US20110131289A1 (en) * | 2009-12-01 | 2011-06-02 | Kang Ho Kim | Method and apparatus for switching communication channel in shared memory communication environment |
| US20110231696A1 (en) * | 2010-03-17 | 2011-09-22 | Vmware, Inc. | Method and System for Cluster Resource Management in a Virtualized Computing Environment |
-
2012
- 2012-03-30 CN CN201210103120.5A patent/CN103365741B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101243413A (en) * | 2005-06-24 | 2008-08-13 | 信科索尔特公司 | System and method for virtualizing backup images |
| CN101097526A (en) * | 2006-06-29 | 2008-01-02 | 联想(北京)有限公司 | Virtual machine system and accessing control method of hardware equipment |
| US20110131289A1 (en) * | 2009-12-01 | 2011-06-02 | Kang Ho Kim | Method and apparatus for switching communication channel in shared memory communication environment |
| US20110231696A1 (en) * | 2010-03-17 | 2011-09-22 | Vmware, Inc. | Method and System for Cluster Resource Management in a Virtualized Computing Environment |
Non-Patent Citations (1)
| Title |
|---|
| 张旻佳: "《虚拟集群环境下多虚拟机协同检查点容错系统》", 《万方学位论文》, 20 September 2011 (2011-09-20), pages 2 - 3 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729264B (en) * | 2013-12-23 | 2016-07-13 | 国云科技股份有限公司 | A kind of Windows virtual machine system disk backup and reduction method |
| CN103729264A (en) * | 2013-12-23 | 2014-04-16 | 国云科技股份有限公司 | Method for backing up and restoring Windows virtual machine system disk |
| CN105117346A (en) * | 2015-09-24 | 2015-12-02 | 上海爱数软件有限公司 | Automatic testing method and system for distributed system of virtualization platform |
| CN109313565A (en) * | 2016-05-02 | 2019-02-05 | 诺基亚通信公司 | Snapshot creation in virtual network environment |
| CN107844420A (en) * | 2017-10-27 | 2018-03-27 | 南京国电南自电网自动化有限公司 | A kind of dichotomy in-circuit emulation and error-checking method based on virtual machine snapshot |
| CN107844420B (en) * | 2017-10-27 | 2020-08-28 | 南京国电南自电网自动化有限公司 | Binary online simulation and error checking method based on virtual machine snapshot |
| CN109753340A (en) * | 2017-11-08 | 2019-05-14 | 阿里巴巴集团控股有限公司 | Virtual machine snapshot processing method, apparatus and system |
| CN109753340B (en) * | 2017-11-08 | 2021-07-13 | 阿里巴巴集团控股有限公司 | Virtual machine snapshot processing method, device and system |
| CN109783272A (en) * | 2017-11-10 | 2019-05-21 | 阿里巴巴集团控股有限公司 | Disk snapshot processing method, device and equipment |
| CN109783272B (en) * | 2017-11-10 | 2023-01-24 | 阿里巴巴集团控股有限公司 | Disk snapshot processing method, device and equipment |
| CN108959547B (en) * | 2018-07-02 | 2022-02-18 | 上海浪潮云计算服务有限公司 | PV snapshot distributed database cluster recovery method |
| CN108959547A (en) * | 2018-07-02 | 2018-12-07 | 山东汇贸电子口岸有限公司 | A kind of PV snapshot distributed experiment & measurement system restoration methods |
| CN110972497A (en) * | 2018-11-02 | 2020-04-07 | 深信服科技股份有限公司 | Disaster recovery method and device for virtualization platform |
| CN111008095A (en) * | 2019-12-17 | 2020-04-14 | 山东超越数控电子股份有限公司 | State snapshot generation and recovery method facing edge cloud |
| CN113791870A (en) * | 2021-09-24 | 2021-12-14 | 上海交通大学 | Fine-grained migration method and system for distributed system of WebAssembly virtual machine |
| CN113791870B (en) * | 2021-09-24 | 2024-03-26 | 上海交通大学 | WebAssemble virtual machine distributed system fine granularity migration method and system |
| CN116150797A (en) * | 2023-04-21 | 2023-05-23 | 深圳市科力锐科技有限公司 | Data protection method, system, equipment and storage medium |
| CN116150797B (en) * | 2023-04-21 | 2023-08-01 | 深圳市科力锐科技有限公司 | Data protection method, system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103365741B (en) | 2016-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103365741A (en) | Method and equipment for snapshot and recovery of virtual machine cluster | |
| CN109445802B (en) | Privatized Paas platform based on container and method for publishing application thereof | |
| CN102165431B (en) | On-the-fly replacement of physical hardware with emulation | |
| CN103778031B (en) | Distributed system multilevel fault tolerance method under cloud environment | |
| CN100409191C (en) | Method and system for managing multi-node SMP system | |
| KR100959173B1 (en) | Component architecture | |
| US20130091334A1 (en) | Method for data backup, device and system | |
| US20210158083A1 (en) | Dynamic container grouping | |
| CN105187512A (en) | Method and system for load balancing of virtual machine clusters | |
| CN103827832B (en) | System and method for persisting transaction records in a transactional middleware machine environment | |
| CN111124277A (en) | Deep learning data set caching method, system, terminal and storage medium | |
| CN104077199B (en) | Based on partition method and the system of the high-availability cluster of shared disk | |
| CN102355369A (en) | Virtual clustered system as well as processing method and processing device thereof | |
| CN106201566A (en) | The rich big special hot upgrade method of software of profit and equipment | |
| CN102597958A (en) | Symmetric live migration of virtual machines | |
| CN104239120B (en) | The method, apparatus and system of a kind of status information synchronization of virtual machine | |
| CN105357042A (en) | High-availability cluster system, master node and slave node | |
| CN106385330A (en) | Network function virtualization composer realization method and device | |
| CN104793981B (en) | A kind of online snapshot management method and device of cluster virtual machine | |
| CN105573825A (en) | Cross-operating system inter-task synchronization method and device | |
| Porter et al. | Type-safe updating for modular WSN software | |
| CN107743618A (en) | Technology for data center environment checkpointing | |
| CN114565502A (en) | GPU resource management method, scheduling method, device, electronic equipment and storage medium | |
| CN106911522A (en) | A kind of fault handling method and system based on cloud environment | |
| Aumage | Heterogeneous multi-cluster networking with the Madeleine III communication library |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200408 Address after: Massachusetts, USA Patentee after: EMC IP Holding Company LLC Address before: Massachusetts, USA Patentee before: EMC Corp. |