126results about How to "Reduce migration time" patented technology

The invention related to method for online transporting external storage (ES) of virtual machine (VM). In Push stage, the method includes following steps: sending data of all ES of VM to destination host (DH); manager of VM monitors ES access of VM in current procedure for sending ES, records update state of ES block in the sending procedure, and marks dirty blocks of written dirty ES; sending dirty blocks to DH form source host (SH) circularly till presetting condition is reached; the method stops sending data of ES and enters into halt stage; based on information of recording update state of ES to determine remnant dirty blocks of ES and sizes, and to send all remnant dirty blocks to DH form SH. In pull stage, based on information of recording update state of ES to carry out synchronous operation for remnant dirty blocks. The invention guarantees: very short halt time, not dependent on hardware environment of shared ES, and applicable to distributed environment.

The invention discloses a data migration method. The method comprises the following steps of: connecting a source database to acquire source data according with a preset condition, wherein the source data have field index information, and the preset condition is an extraction condition set aiming at the field index information; and connecting a target database to store the acquired source data as target data. The invention can improve the efficiency of data migration, particularly the efficiency of mass data migration and save the migration time.

The storage control device of the present invention uses a temporary volume to move data rapidly between volume groups. The storage control device forms a plurality of volume groups by grouping volumes of the same performance. At least one or more temporary volumes are each pre-provided in the respective volume groups. The control section calculates and manages the priority levels of the respective data. The data with the highest priority level in the lower volume group are copied beforehand to the temporary volume in the upper volume group at a time when the data are not being accessed by the host. As a result, data can be moved rapidly when data migration is executed and so forth.

The invention features fiber reinforced bone repair putties and fiber reinforced pliable lyophilized implants which are useful for the treatment of bone defects. The putties and lyophilized implants include ceramic particles. The formulations of the invention can exhibit reduced migration of the ceramic particles, and are mechanically strengthened so the materials can be aggressively manipulated by a physician during an implantation procedure without tearing or puncturing.

The present invention provides a storage subsystem capable of realizing efficient data migration and high access performance. During migration of data between storage subsystems, data migration methods are selected between a “PUSH” type and a “PULL” type method based on a data migration policy set in advance to perform data migration processes. An access characteristics of a file and a folder storing the file are determined based on a file access frequency or a final access date and time information in a migration source storage subsystem, and the migration order of a file group determined to have a high possibility of being accessed during data migration is changed between the “PUSH” type and the “PULL” type.

An embodiment of the invention discloses a method and device for on-line integral migration of a virtual machine. The invention relates to the field of communication. Source virtual machine storage is divided into a basic file and other files according to the migration levels of a source virtual machine. First, the basic file is copied to a target host machine to enable the virtual machine to be started quickly in the target host machine, and therefore the service migration time of the virtual machine is greatly shortened. The method comprises the steps of receiving the migration level corresponding to the source virtual machine and sent by a central controller, and dividing the source virtual machine storage into the basic file and the other files according to the migration level corresponding to the source virtual machine; sending the basic file to the target host machine so that the virtual machine can be started in the target host machine according to the basic file; releasing source virtual machine resources; sending the other files to the target virtual machine.

The storage control device of the present invention uses a temporary volume to move data rapidly between volume groups. The storage control device forms a plurality of volume groups by grouping volumes of the same performance. At least one or more temporary volumes are each pre-provided in the respective volume groups. The control section calculates and manages the priority levels of the respective data. The data with the highest priority level in the lower volume group are copied beforehand to the temporary volume in the upper volume group at a time when the data are not being accessed by the host. As a result, data can be moved rapidly when data migration is executed and so forth.

The invention provides a clean room environment-based safe virtual machine migration method. Through the method, the credibility of physical computers is validated before the migration of a virtual machine, so that the virtual machine can be migrated onto a credible physical computer, and the confidentiality and integrity of the virtual machine data in the transmission process can be ensured. According to the method, the number of migration iterations can be decreased to a certain extent, so that the migration efficiency is improved; and the method is simple in realization process and easy to operate.

The invention provides a dynamic migration and optimization method of virtual machines based on remote direct memory access. The method comprises the steps: step 1, a source virtual machine transfers synchronous copying information for marking memory change situations to a targeted virtual machine at the beginning of the pre-copying stage; step 2, after the transferring of the copying information is finished, the source virtual machine continues to execute upper-level application service; step 3, the targeted virtual machine sends receipt information to the source virtual machine; step 4, the source virtual machine sends service switching information to the targeted virtual machine; step 5, the targeted virtual machine utilizes on-demand recovery strategies and remotely reads final dirty page data at the backstage by utilizing an RDMA (Remote Direct Memory Access) model; step 6, the targeted virtual machine finishes the synchronization of the final dirty pages and sends migration completion information to the source virtual machine; and the source virtual machine releases all resources. The overall migration time and the service interruption time of the dynamic migration of the virtual machines are shortened, and meanwhile, the influence on the upper-level application service caused by the dynamic migration is reduced.

The invention provides a data migration method based on a cloud platform. The method includes the steps: (1) transmitting virtual machine migration requests to physical hosts within a communication range by a physical host to be migrated; (2) receiving the virtual machine migration requests and then calculating various usable resources by the physical hosts to obtain performance vectors; (3) acquiring adaptive vectors among the virtual machine demands and the physical host performance vectors, and transmitting the adaptive vectors D to the physical host to be migrated; (4) calculating the distance between every two physical hosts and selecting a target physical host the closest to an average value for migration average according to distance ranking results after receiving the adaptive vectors of the physical hosts by the physical host to be migrated. According to the data migration method based on the cloud platform, the migration process of virtual machines is further optimized, performance and resource consumption is reduced, and overall migration time is shortened.

The invention relates to a method for preparing a nickel oxide electrochromic film by a hydrothermal method. The method comprises the following steps of: dissolving nickel acetate tetrahydrate in a mixed solution of alcohol and n-butyl alcohol, dropwise adding ammonia water to the mixed solution after the nickel acetate tetrahydrate is dissolved to obtain sol; coating the sol to the surface of FTO (Fluorine-doped Tin Oxide) conductive glass in a rotary manner, drying the sol to obtain the FTO conductive glass with a crystal seed layer; mixing the nickel acetate tetrahydrate, urea and a solvent to obtain a reaction solution; immersing the FTO conductive glass with the crystal seed layer to the reaction solution for carrying out hydrothermal reaction; keeping the reaction solution for 6 hours to 12 hours under the condition of 160 DEG C to 180 DEG C, cooling the reaction solution to the room temperature, cleaning, drying and roasting to obtain the nickel oxide electrochromic film. The preparation method disclosed by the invention is simple, low in cost and likely applied to the glass surface film-making industry. The nanometer structure nickel oxide film directly grows on the surface of the FTO conductive glass by a hydrothermal method, so that the nickel oxide and the substrate have better binding force for being beneficial to electron conduction. Meanwhile, the electrochemical stability of the film is also improved.

The invention discloses a device, a system and a method for online storage migration of a virtual machine system. The method includes: copying files by controlling a first storage controller of a source storage device and a second storage controller of a target storage device, copying a master image file to the target storage device, recognizing whether the size of a slave image file accords with the terminate threshold condition or not, if yes, responding to the terminate threshold condition to stop the virtual machine system and migrating to the target storage device, and integrating the master image file and the slave image file to form a new system file. By using the storage controllers for realizing a migration mechanism of mass data copying operations, occupancy and dependency on resources of a physical mainframe by the storage migration method are avoided, influences on performances of the physical mainframe and the virtual machine system on the physical mainframe are weakened, and flexibility, rapidness and high efficiency in online storage migration of the virtual machine system are realized.

The invention provides an online migration system implementation and optimization method for a Docker container. The online migration system realization and optimization method at least comprises thefollowing steps: determining an integrated collection mechanism of mirror image layer data based on different container file systems and parent-child relationships between mirror image layers thereofso as to complete integrated collection of the mirror image layer data; determining the latest version of the mirror image layer data based on a Diff command between the parent mirror image layer andthe child mirror image layer, and realizing transmission of the latest version of the mirror image layer data between the source machine container and the target machine container to complete iteration synchronization of the mirror image layer data; realizing iterative synchronization of memory in accordance with the implementation of the Pre-Copy mechanism; and executing container recovery operation of the target machine container under the condition that the iteration synchronization of the mirror image layer data and the memory is completed.

The invention discloses a MapReduce bandwidth optimization method which comprises the following steps: after Hadoop work is submitted, an OpenFlow controller, according to task execution node information sent by JobTracker and through a Map intermediate value routing strategy, determines nodes for carrying out a Map intermediate value merge task, updates corresponding flow entry and sends the flow entry to an OpenFlow switch; and the OpenFlow switch receives and installs the flow entry through a secure channel, then, carries out flow entry matching on the received data packets, and if behavior type for merging the Map intermediate values is matched therewith, carries out merging of the Map intermediate values. Through the combination of the OpenFlow and Hadoop, and by utilizing data handling capacity of the OpenFlow switch, the Map intermediate values, that is, the intermediate tuple data obtained after the action of a map() function, are subjected to merge processing in advance, thereby greatly relieving the problem of network congestion in the data migration process and improving Hadoop work efficiency substantially.

The invention discloses a container dynamic migration method and system based on a minimum migration quantity and designs a dynamic container migration model. The invention aims to provide a containerdynamic migration optimization method based on the minimum migration quantity. According to the method, by fitting increase speeds of containers in a source server, the containers for dynamic migration are selected according to the principle of selecting the containers with high migration increase speeds and high occupation rates. In this way, the migration quantity is reduced under the conditionof guaranteeing cluster load balance, and therefore the utilization rate of resources is increased.

The invention discloses a preparation method of a silver phosphate composite photocatalyst for treating malachite green in water. The method comprises the following steps of: (1) performing ultrasonictreatment on multi-walled carbon nanotubes (MWCNTs) treated by HNO3 for 2-5 h; (2) dropwise adding an AgNO3 solution to a MWCNTs solution and performing stirring in the dark for 6-20 h; (3) adding Na2HPO4.12H2O dropwise to the above solution, performing stirring in the dark for 1 to 6 hours, and then performing vacuum drying; (4) uniformly mixing [(CH3)2CHO]4Ti, Sr(Ac)2 and Cr(NO3)3.9H2O with a molar ratio of 20:19:1 in an ethylene glycol solution, performing continuous stirring at 120-160 DEG C until the solution becomes a powder; (5) mixing the obtained powder with NaOH solution with a concentration of 2-6 mol / L under stirring for 20-60 min, placing the mixture in a hydrothermal reaction kettle, and performing a reaction at 180 DEG C for 30-40 h; and (6) performing ultrasonic treatmenton MWCNTs@Ag3PO4 for 10 to 60 min, adding a polyvinylpyrrolidone solution, performing stirring for 20-60 min, adding the ultrasonically-treated Cr:SrTiO3 dropwise to the above stirred solution, performing a reaction for 3-8 hours, and performing washing and drying, so as to obtain Ag3PO4@MWCNTs@Cr:SrTiO3. The material prepared by the preparation method of the invention has the advantages of friendliness to environment, economy, good visible light catalytic performance and the like.

The embodiment of the invention relates to a data migration method and a data migration device of a solid state disk and the solid state disk. The data migration method comprises the following steps: reading first data of a first data block in a solid state storage unit in a data register of the storage unit, and naming the first data of the data register with read-in data as second data; checking and correcting the second data; and writing the checked and corrected second data in a second data block of the storage unit. The embodiment of the invention improves the efficiency of data migration, reduces the time of the data migration and improves the data rate of the data migration.

The invention relates to a mobile communication technique that discloses a base station node transfer method and relative system, to effectively and reliably transfer NodeB. The invention divides the transfer process into two steps as preparation and execution; wherein, in the preparation step, guiding out the MML script of said transfer from relative RNC relative to the transferred base station node, and extracting out the interface distribution data of NodeB to be modified by user; in the execution step, via executing the modified MML script, realizing the transfer of NodeB; and in the preparation step, selectively building backup database, in which to modifying and executing MML script, to check the legality of data.

The invention discloses a virtual machine on-line migration optimizing method capable of sensing compound application characteristics and the network bandwidth and belongs to the technical field of software. The method comprises the steps that firstly, an application characteristic environment and network bandwidth environment of a virtual machine are sensed, and the number of memory dirty pages is collected; secondly, the number of memory dirty pages is forecasted by means of a grey prediction model; thirdly, the dirty page rate of an iteration cycle of the virtual machine is calculated; fourthly, the use conditions of the network bandwidth are collected; fifthly, according to the network bandwidth required for applications in the virtual machine, whether the virtual machine is a network-intensive virtual machine or not is judged, and then network bandwidth reservation is conducted. In the face of virtual machine migration of network-intensive applications or memory-intensive applications, extra overhead in the migration process can be reduced, the transmission efficiency in the migration process is improved, and the migration time is effectively reduced.

Disclosed in the invention is a method for data migration in a peer-to-peer (P2P) network. The method comprises the following steps that: when it is needed to carry out data migration, a node that needs to carry out data emigration compares a current data version of migrated data with a data version corresponding to an immigrated node, determines increment data and sends the increment data to the immigrated node; and the immigrated node restores data of a latest version according to the increment data and data stored by the immigrated node itself. Meanwhile, the invention discloses a system for data migration in a P2P network. According to the method and the system, the data volume and migration time of data migration in a P2P network can be substantially reduced, thereby improving the speed and the reliability of the data migration.

The invention discloses a data migration method and a storage medium. The method comprises the steps that an Hbase database is divided into multiple predetermined regions; relational data in a predetermined relational database is converted into TLV-format data, and the TLV-format data is stored into a preset TLV-format file; and the data in the preset TLV-format file is concurrently migrated to the predetermined regions through predetermined migration instances. According to the method, the relational data in the predetermined relational database is converted into the TLV-format data, and therefore original BLOB-type data also can be migrated; and in the migration process, the Hbase database is partitioned, therefore, the data can be migrated concurrently, data migration time is greatly shortened, and the problem that in the prior art, existing data migration tools can well support the relational data but do not support the original BLOB-type data, and consequently efficient data migration cannot be realized is solved.

The invention discloses a crude oil emulsion fluid electrostatic coalescer. The crude oil emulsion fluid electrostatic coalesce comprises a barrel which is of a cylindrical structure, wherein a grounding terminal inlet pipeline and an outlet pipeline are arranged on the outer side surface of the barrel; the two ends of the barrel are connected with an insulating end enclosure and end surface sealing covers; cable introducing holes which are used for introducing high / low-voltage cables and are connected with multiple high / low-voltage electrodes in the barrel are formed in the two end surface sealing covers respectively; a low-voltage electrode is arranged on an axis, and a high-voltage electrode is wound outside the axis in a concentric manner, and the high-voltage electrode is closest to the barrel housing; a plurality of foldout supporting plates for guiding the crude oil emulsion fluid and supporting high / low-voltage electrodes are arranged on the inner part of the barrel. The crude oil emulsion fluid electrostatic coalesce has the advantages of being compact in structure, small in floor space and convenient to dismount, is suitable for an oil-water separating process on the sea and improving original oil-water separating equipment; uneven electric fields are introduced to achieve good coalescence effect on uncharged liquid drops in the emulsion fluid with low moisture content, which is difficult to treat by dipole coalescence and electrophoresis coalescence through normal electric dehydrating equipment, so that the treatment capacity of electrostatic coalescence equipment is strengthened.

The invention relates to a virtual machine real-time migration method based on counting rank ordering. The method specifically comprises the following steps of a step 1 that the times that each memory page is dirtied are stored in a storage array; a step 2 that the memory pages are ranked from low to high according to the dirtying times; a step 3 that the ranked memory pages are transmitted from a source host to a target host according to the sequence. The method has the beneficial effects that the memory pages with more dirtying times are placed on the last period of each round as far as possible for carrying out transmission judgment, and the condition that the same page is transmitted for many times due to the frequent dirtying can be reduced as far as possible, so that the time that the page with high dirtying probability is transmitted is delayed as far as possible, and the probability that the page is retransmitted frequently is reduced; the transition time is reduced; the migratory data size is reduced; the migration efficiency is thus improved.

The invention provides a Notes mailbox transfer method, comprising steps of: attaining the user information of the transferred Notes mailbox from the prior email server; attaining the Notes mailbox information of the user from the prior email server according to the attained user information; according to the attained user information, copying the email of the user Notes mailbox from the prior email server to a target email server; informing the user about the transfer information of the Notes mailbox and modifying the client environment of the user; setting the quota of the user Notes mailbox in the target email server. The invention further provides a Notes mailbox transfer system. The Notes mailbox transfer system and method can automatically transfer Notes mailboxes quickly.

The invention provides a file migration method of a Map Reduce distributed system and file migration equipment of the Map Reduce distributed system. Migration operation which is used for migrating a target file is started. The migration operation at least comprises a first Map task and a second Map task which are executed in a parallel mode, and a Reduce task which corresponds to the first Map task and the second Map task so that in the Reduce task, metadata, in the target Map Reduce distributed system, of the target file can be generated. Due to the fact that the migration task which enables the target file to be migrated at least comprises the first Map task and the second Map task, and the first Map task and the second Map task are executed in the parallel mode, migration time of the target file can be shortened, and accordingly migration efficiency of the target is improved.

The invention discloses a data migration method, which comprises the following steps: reading a data fragment in a first database, and writing the read data fragment into a data file; obtaining indexinformation corresponding to the data segment in the first database, and writing the index information into an index file; executing a data writing operation to write data in the data file into a target database; and when the data writing operation is interrupted and restarted, reading non-migrated data in the first database according to the index information in the index file and writing the non-migrated data into the target database. The invention further discloses a data migration device and a readable storage medium. The invention aims to realize that data transmission can be continued based on the data transmission progress before interruption after interruption occurs in a large number of data migration processes, reduce the data migration time and improve the overall transmission efficiency of the interrupted data migration process.

The invention discloses a method for realizing virtual machine disk image cross-storage live migration and a virtual machine system and relates to the technical field of virtual machines. The method for realizing virtual machine disk image cross-storage live migration comprises the steps that an initial disk image is copied to a target storage area when a source side virtual machine operates, change, occurring during copying, of a source side disk image is recorded, and a corresponding I / O function digit image is generated; the source side virtual machine is stopped temporarily after copying of the initial disk image is completed, and the I / O function digit image is copied to the target storage area; a target side virtual machine is started, and the source side disk image is reserved and copied to the target storage area. According to the method for realizing virtual machine disk image cross-storage live migration and the virtual machine system, the change, occurring during the period when the source side disk image is copied to the target side from the source side, of the source side disk image is recorded through the I / O function digit image, repeated copying of the disk image is avoided, and the overall virtual machine migration time is shortened; meanwhile, the virtual machine on the target side can be started after copying of the disk image and the I / O function digit image is completed, and thus the operating time during which the virtual machine is switched to the target side from the source side is greatly shortened.

Provided in the invention is a state-sensing-based VM migration scheduling method. The method comprises: step one, state information of physical machines (PM) and virtual machines (VM) is collected in real time; step two, on the basis of a resource consumption sequence, VM sorting is carried out; step three, a destination and a migration path are determined for each to-be-migrated VM by using a simulated annealing algorithm; and step four, an exchange path is designed to realize maximum parallel migration.

The invention provides a scheduling method and system for virtual-machine memory self-adaption thermal migration in a hybrid cloud mode. The method includes the steps that a dirty-page-rate prediction model is established and used for predicting the current dirty page rate of a source virtual machine memory after iteration copying is carried out; the source virtual machine memory is subjected to iteration copying one time, and the current dirty page rate is compared with a current-dirty-page-rate threshold value, whether the continuous iteration copying step is carried out or stopping copying and copying as required are carried out is determined; the source virtual machine memory is subjected to continuous iteration copying, and according to the time number of continuous iteration copying or comparison of the current dirty page rate and the current-dirty-page-rate threshold value, and whether stopping copying is carried out or not is determined, wherein the current-dirty-page-rate threshold value is equal to the average value of the current dirty page rates of all applications in the source virtual machine memory. By means of the scheduling method and system for virtual-machine memory self-adaption thermal migration in the hybrid cloud mode, whole migration time can be effectively shortened, the total memory-data migration amount is greatly reduced, and meanwhile self-adaption virtual-machine resources in different application scenes are scheduled.