CN112799596A - Capacity expansion control method and device for storage resources and electronic equipment - Google Patents
Capacity expansion control method and device for storage resources and electronic equipment Download PDFInfo
- Publication number
- CN112799596A CN112799596A CN202110150400.0A CN202110150400A CN112799596A CN 112799596 A CN112799596 A CN 112799596A CN 202110150400 A CN202110150400 A CN 202110150400A CN 112799596 A CN112799596 A CN 112799596A
- Authority
- CN
- China
- Prior art keywords
- storage
- storage pool
- pool
- time period
- capacity expansion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0604—Improving or facilitating administration, e.g. storage management
- G06F3/0607—Improving or facilitating administration, e.g. storage management by facilitating the process of upgrading existing storage systems, e.g. for improving compatibility between host and storage device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/061—Improving I/O performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0638—Organizing or formatting or addressing of data
- G06F3/0644—Management of space entities, e.g. partitions, extents, pools
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a capacity expansion control method and device for storage resources and electronic equipment, wherein the method comprises the following steps: under the condition of receiving a prediction request, obtaining storage state information of a storage pool, wherein the storage pool is a storage pool built on a cloud platform; predicting storage demand of the storage pool in a first time period in the future according to at least the storage state information; the first time period is a preset time period after the current moment; and under the condition that the storage demand meets a resource capacity expansion condition, executing capacity expansion operation on the storage pool so that the available storage resources of the storage pool meet the storage demand in the first time period.
Description
Technical Field
The present application relates to the field of data storage technologies, and in particular, to a method and an apparatus for controlling expansion of a storage resource, and an electronic device.
Background
With the development of networks, the storage of cloud platforms continues to increase, and monitoring and expansion of storage capacity need to consume a large amount of manpower and financial resources. Under the condition that a private cloud platform constructed by an OpenStack project is stored in a storage Area network SAN (storage Area network), a switching Virtual circuit SVC (switching Virtual circuit) is adopted to manage the expansion of storage resources.
The expansion of the storage resources comprises the processes of: firstly, a storage pool is distributed in the SVC, then a computing node is configured so that the SVC can identify the storage device, then an OpenStack storage component issues a configuration file, then a cloud mirror image is migrated to a new storage pool, finally a virtual machine delivery test is carried out based on the migrated mirror image, and the storage pool expansion is completed.
Since the above expansion process is complicated, when the capacity of the resource pool is insufficient, the storage resource is expanded, and the delivery speed of the expanded storage resource may be very slow due to the influence of the network, the disk input/output, and other factors.
Disclosure of Invention
In view of this, the present application provides a method, an apparatus and an electronic device for controlling expansion of storage resources, which includes:
a capacity expansion control method of storage resources comprises the following steps:
under the condition of receiving a prediction request, obtaining storage state information of a storage pool, wherein the storage pool is a storage pool built on a cloud platform;
predicting storage demand of the storage pool in a first time period in the future according to at least the storage state information; the first time period is a preset time period after the current moment;
and under the condition that the storage demand meets a resource capacity expansion condition, executing capacity expansion operation on the storage pool so that the available storage resources of the storage pool meet the storage demand in the first time period.
Preferably, the method for performing capacity expansion operation on the storage pool includes at least:
adding a storage device to the storage pool;
updating configuration information corresponding to the storage pool on the cloud platform;
configuring an operating system for the added storage devices in the storage pool.
The method preferably adds a storage device to the storage pool, and includes:
building a new storage device in the storage pool;
or starting the storage device in the closed state in the storage pool;
or, dividing the storage device for the cloud platform in the storage devices allocated to other platforms in the storage pool.
Preferably, the method for configuring an operating system for the storage device added in the storage pool includes:
obtaining an image file of an operating system in the original storage equipment in the storage pool;
and migrating the image file of the operating system to the storage device added in the storage pool.
In the above method, preferably, the storage parameters of the storage devices added in the storage pool correspond to the storage requirements.
The method preferably predicts the storage demand of the storage pool in a first time period at least according to the storage status information, and includes:
sampling the storage state information according to a corresponding time sequence to obtain sampling data;
and at least performing prediction processing on the sampled data to obtain the storage requirement of the storage pool in a first time period.
Preferably, the method further includes, after performing the capacity expansion operation on the storage pool:
and carrying out abnormal inspection on the expanded storage pool to obtain an inspection result, wherein the inspection result represents whether the expansion of the storage pool is successful.
The method preferably performs exception checking on the expanded storage pool, and includes any one or more of the following:
checking whether the operating system in the expanded storage pool is normal;
checking whether the storage resources in the expanded storage pool have delivery abnormity;
and checking whether the cloud platform can read and write the expanded storage pool.
A capacity expansion control device for a storage resource includes:
the storage obtaining unit is used for obtaining storage state information of a storage pool under the condition that a prediction request is received, wherein the storage pool is a storage pool built on a cloud platform;
a demand prediction unit, configured to predict storage demand of the storage pool in a first time period in the future according to at least the storage status information; the first time period is a preset time period after the current moment;
and the storage control unit is used for executing capacity expansion operation on the storage pool under the condition that the storage demand meets a resource capacity expansion condition, so that the available storage resources of the storage pool meet the storage demand in the first time period.
An electronic device, comprising:
the memory is used for storing an application program and data generated by the running of the application program;
a processor for executing the application to implement:
under the condition of receiving a prediction request, obtaining storage state information of a storage pool, wherein the storage pool is a storage pool built on a cloud platform;
predicting storage demand of the storage pool in a first time period in the future according to at least the storage state information; the first time period is a preset time period after the current moment;
and under the condition that the storage demand meets a resource capacity expansion condition, executing capacity expansion operation on the storage pool so that the available storage resources of the storage pool meet the storage demand in the first time period.
According to the scheme, in the capacity expansion control method and device for the storage resources and the electronic device, under the condition that the prediction request is received, the storage state information of the storage pool built on the cloud platform is obtained, so that the storage demand of the storage pool in the future time period is predicted, and further, under the condition that the storage in the future time period needs to meet the resource capacity expansion condition, namely capacity expansion needs to be carried out, capacity expansion operation is carried out on the storage pool, so that the available storage resources in the storage pool can meet the storage demand in the future time period. Therefore, whether the capacity of the storage pool needs to be expanded in the future time period or not is predicted, and the capacity expansion of the resources is carried out in advance when needed, so that the available storage resources in the storage pool are ensured to be in an abundant state all the time through the front-end capacity expansion of the available storage resources, and the condition that the delivery rate of the resources is slow due to the capacity expansion when the available resources are in shortage can be avoided.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart illustrating an implementation of a method for controlling capacity expansion of a storage resource according to an embodiment of the present application;
FIG. 2 is an exemplary graph of time periods in an embodiment of the present application;
fig. 3 is a partial flowchart of a method for controlling capacity expansion of a storage resource according to an embodiment of the present application;
fig. 4 is another flowchart of a method for controlling capacity expansion of a storage resource according to an embodiment of the present disclosure;
fig. 5 is another partial flowchart of a method for controlling capacity expansion of a storage resource according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a capacity expansion control apparatus for storage resources according to a second embodiment of the present application;
fig. 7 is another schematic structural diagram of a capacity expansion control apparatus for storage resources according to a second embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device according to a third embodiment of the present application;
fig. 9-15 are diagrams respectively illustrating an example of a storage pool built on an OpenStack cloud computing platform according to the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, an implementation flowchart of a storage resource capacity expansion control method provided in an embodiment of the present application is shown, where the method may be applied to an electronic device, such as a computer or a server, which is connected to a storage pool built on a cloud platform and is capable of performing data processing and storage pool control. The technical scheme in the embodiment is mainly used for capacity expansion control of the storage pool so as to improve the resource delivery rate.
Specifically, the method in this embodiment may include the following steps:
step 101: a prediction request is received.
The prediction request may be generated by the electronic device according to a certain frequency. Specifically, a timer provided in the electronic device generates a prediction request in real time according to the configured prediction frequency, and in this embodiment, the prediction request generated by the timer is received and responded to.
It should be noted that the prediction request may include a request identifier corresponding to the storage pool, where the request identifier is used to represent prediction for performing capacity expansion control on the storage pool.
Step 102: storage status information for the storage pool is obtained.
The storage pool may also be understood as a resource pool, which includes storage devices capable of providing storage resources for users, where the storage pool is a storage pool established on a cloud platform, such as a storage pool established on an OpenStack cloud computing platform, and the storage pool may be an SAN type storage pool, which includes a plurality of storage devices to form the storage pool.
Specifically, in this embodiment, the storage status information of the storage pool at the current time and at a plurality of historical times may be obtained by reading data in various dimensions related to the storage pool, where the storage status information includes information of available storage resources and/or occupied storage resources of the storage pool at the current time and at the historical times, information of devices or applications occupying the storage resources of the storage pool, and the like.
For example, the storage status information obtained in this embodiment includes information such as monitoring data, an OpenStack database, a configuration Management database cmdb (configuration Management database), and a switching Virtual circuit svc (switching Virtual circuit) database.
The monitoring data refers to load monitoring data of computing resources in the storage pool, such as the memory utilization rate of a central processing unit (cpu); the OpenStack database information refers to the virtual machine state and network state information of the cloud computing platform, such as whether the virtual machine is occupied; the CMDB information includes information of the full life cycle of the configuration items and relationships between the configuration items, including physical relationships, real-time communication relationships, non-real-time communication relationships, and dependency relationships, and in this embodiment, the CMDB information includes information of all asset devices, such as the production type, total number, number in an operating state, and the like of the physical devices; the SVC database information contains information about the storage devices, such as the number of storage devices, the total capacity of each storage device, the current remaining capacity of each storage device, and the like.
Step 103: based at least on the storage status information, a storage demand of the storage pool for a first period of time in the future is predicted.
Wherein the first time period is a predetermined time period after the current time, as shown in fig. 2, the storage demand of the storage pool in the predetermined time period is predicted in step 103.
In this embodiment, storage state information at the current time and the historical time is processed, and then storage demand stored in a predetermined time period after the current time is predicted, where the storage demand represents delivery demand of a user on a storage pool in a first time period in the future, for example, the storage pool needs to deliver available storage resources of a specific storage type of a specific size to the user in the first time period.
Step 104: and judging whether the storage requirement meets the resource capacity expansion condition or not, and executing the step 105 under the condition that the storage requirement meets the resource capacity expansion condition.
The resource capacity expansion condition is a condition that whether available storage resources are in short supply in a future first time period is determined for currently remaining available storage resources in the storage pool, based on this, in this embodiment, it is determined whether a predicted storage demand in the first time period meets the resource capacity expansion condition, if the storage demand meets the resource capacity expansion condition, it may be determined that there is a situation that available storage resources are in short supply in the storage pool in the future first time period if the storage area is not subjected to resource capacity expansion, that is, a situation that resource capacity expansion is required in the future first time period, and thus, step 105 is executed if the storage demand meets the resource capacity expansion condition.
Specifically, the resource capacity expansion condition may be: the storage demand in the storage demand is greater than or equal to the storage remaining amount of the storage pool, or the storage demand in the storage demand is greater than or equal to a certain proportion of the storage remaining amount of the storage pool, such as the storage demand in the storage demand is greater than or equal to 80% of the storage remaining amount of the storage pool, and so on;
the demand amount and the remaining amount herein refer to the amount of storage space, such as the amount of address space.
Or, the resource capacity expansion condition may be: the storage type in the storage demand does not match the storage type in the storage pool, e.g., the device storage type in the storage pool does not support storage for the data storage type in the storage demand, and so on.
Or, the resource capacity expansion condition may be: the amount of storage demand in the storage demand is such that the remaining amount of storage in the storage pool for a first period of time is less than a preset threshold, e.g., the storage demand is such that the remaining amount of storage in the storage pool for a first period of time is less than 10%, and so on.
Step 105: a capacity expansion operation is performed on the storage pool such that the available storage resources of the storage pool meet the storage demand for the first time period.
In this embodiment, a capacity expansion operation may be performed on the storage pool according to information about storage demand or storage type in the storage demand, for example, to increase storage space or increase storage devices of a specific storage type. Therefore, the available storage resources in the storage pool can meet the storage requirement in the first time period, namely, the resource capacity expansion condition is not met any more, the available storage resources in the storage pool in the first time period in the future can meet the storage requirement in the first time period, and the condition that the available storage resources in the storage pool in the first time period are in shortage is avoided.
For example, the storage demand of the storage pool in the first time period is no longer greater than the storage remaining amount of the storage pool or no longer greater than 80% of the storage remaining amount, whereby the available storage resources of the storage pool are able to meet the storage demand.
According to the above scheme, in the capacity expansion control method for the storage resources provided in the embodiment of the present application, under the condition that the prediction request is received, the storage state information of the storage pool built on the cloud platform is obtained, so that the storage demand of the storage pool in the future time period is predicted, and further, under the condition that the storage in the future time period needs to meet the resource capacity expansion condition, that is, capacity expansion needs to be performed, the capacity expansion operation is performed on the storage pool, so that the available storage resources in the storage pool meet the storage demand in the future time period. It can be seen that, in this embodiment, by predicting whether the capacity of the storage pool needs to be expanded in a future time period and performing resource expansion in advance when needed, it is ensured that the available storage resources in the storage pool are always in an abundant state by pre-expansion of the available storage resources, and a situation of a slow resource delivery rate caused by expansion when the available resources are in shortage can be avoided.
In one implementation, when performing the capacity expansion operation on the storage pool in step 105, the following may be specifically implemented, as shown in fig. 3:
step 301: adding storage devices to the storage pool;
specifically, the following ways may be used to add a storage device to the storage pool in this embodiment:
in one manner, in this embodiment, a new storage device is built in the storage pool, for example, 10 SAN storage devices already exist in the storage pool, and in order to implement capacity expansion of the storage pool, in this embodiment, a new one or more SAN storage devices are built in the storage pool to increase the number of SAN storage devices in the storage pool, thereby implementing capacity expansion of the storage pool, as shown in fig. 4.
In another way, in this embodiment, storage devices in a shutdown state in a storage pool are started, for example, 10 SAN storage devices already exist in the storage pool, but only 7 SAN storage devices are in a state of being started and capable of being used, so to implement capacity expansion of the storage pool, in this embodiment, one or more SAN storage devices that are not started are started to increase the number of SAN storage devices that are started and capable of being used in the storage pool, thereby implementing capacity expansion of the storage pool, as shown in fig. 5.
In another implementation, the storage device may be divided for the cloud platform among the storage devices allocated for other platforms in the storage pool in this embodiment. For example, 10 SAN storage devices in the storage pool are allocated to the OpenStack cloud computing platform, in order to implement capacity expansion of storage resources of OpenStack, in this embodiment, one or more storage devices are divided from storage devices allocated to other platforms in the storage pool to the OpenStack cloud computing platform, so as to increase the number of SAN storage devices in the storage pool serving the OpenStack cloud computing platform in the storage pool, thereby implementing capacity expansion of the storage pool, as shown in fig. 6.
It should be noted that the storage parameters of the storage devices added in the storage pool in the present embodiment correspond to the storage requirements. That is to say, in this embodiment, a corresponding number and a corresponding type of storage devices may be added to the storage pool according to the information in the predicted storage demand, so that the storage parameters of the storage devices added to the storage pool are matched with the storage demand in the first time period, thereby ensuring that the storage pool after adding the storage devices can meet the storage demand in the first time period, and avoiding the situation that the available storage resources in the storage pool are idle.
Step 302: and updating the configuration information corresponding to the storage pool on the cloud platform.
The configuration information may include mirror information of the operating system, and may also include information of the relevant data state.
Specifically, in this embodiment, the image update and the update of the related data state may be performed by calling an OpenStack API or an instruction. For example, an OpenStack API or instruction is invoked to modify OpenStack configuration information and specify an operating system for the added storage device, e.g., specify an operating system in a storage device existing in the storage pool as an operating system of the added storage device, etc.
Step 303: an operating system is configured for the added storage devices in the storage pool.
Specifically, in this embodiment, the operating system image file of the storage device added in the storage pool may be migrated and migrated to the added storage device, so as to complete configuration of the operating system of the added storage device.
For example, in this embodiment, the image file of the operating system may be obtained from the original storage device in the storage pool, and then the image file of the operating system is migrated to the storage device added in the storage pool, so as to implement migration of the image file.
In one implementation, when predicting the storage demand of the storage pool in the first time period according to at least the storage status information in step 103, the following may be specifically implemented:
firstly, the storage state information is sampled according to a corresponding time sequence to obtain sampling data. For example, the storage status information includes time-series data sorted according to the historical time and the current time, and based on this, in order to simplify the calculation, the time-series data is resampled in the present embodiment, for example, the resampling granularity is up to the sampling level in the unit of day, so as to obtain the sample data.
Then, in this embodiment, at least the sample data is subjected to a prediction process to obtain the storage requirement of the storage pool in the first time period.
Note that the storage pool may deliver not only the OpenStack resource but also a resource such as a physical machine. Therefore, the prediction range involved in the prediction processing of the sample data in the present embodiment may include: SVC consumption, OpenStack resource delivery estimation, and other predictions of the dimensions in which SVC resources are consumed.
Specifically, in the embodiment, when the sample data is processed, the sample data may be specifically processed by using a corresponding prediction processing algorithm according to a service scenario, for example, in a general case, a differential integration Moving Average autoregressive model (arima) algorithm may be used to perform prediction processing on the sample data in the embodiment, so as to obtain a future storage requirement in 15; in a special case, a service item with a large resource demand may exist in the storage pool, so to improve the prediction accuracy, in this embodiment, the ARIMA and the artificially labeled resource demand data are combined to perform prediction processing on the sample data to obtain a storage demand for 15 days, so as to obtain a resource increase demand for the storage value in the future 15.
In one implementation, after performing the capacity expansion operation on the storage pool in step 105, the method in this embodiment may further include the following steps, as shown in fig. 4:
step 106: and carrying out exception checking on the expanded storage pool to obtain a checking result.
Wherein the check result represents whether the capacity expansion of the storage pool is successful.
Specifically, the items of the exception check may include any one or more items of check items related to the operating system, check items related to the virtual machine, check items related to reading and writing, and the like.
Based on this, in this embodiment, when performing exception checking on the expanded storage pool, any one or more of the following steps may be specifically included, as shown in fig. 5:
step 501: a check is made as to whether the operating system in the expanded storage pool is normal.
Wherein, checking whether the operating system is normal refers to: whether the migrated image file in the storage pool is migrated normally is checked, for example, whether the migration of the operating system image file in the storage device added in the storage pool is successful is checked.
Step 502: and checking whether the storage resources in the expanded storage pool have delivery abnormity.
The checking whether the storage resource has delivery exception includes: it is checked whether the storage resources can be delivered normally for the user. E.g., whether the virtual machine in the storage resource can be delivered normally, etc.
Step 503: and checking whether the cloud platform can read and write the expanded storage pool.
In a specific implementation, in this embodiment, after the capacity expansion operation on the storage pool is completed, the operation flow of the simulated delivery may be executed on the storage pool, so as to check whether the mirror image is migrated normally, whether the virtual machine is delivered normally, whether the cloud disk can be read and written normally, and the like according to data generated in the simulated delivery process.
It should be noted that, step 501, step 502, and step 503 may be executed in a certain order or simultaneously, and all the technical solutions implemented by different execution orders are within the protection scope of the present application.
Further, in this embodiment, after the capacity expansion of the storage pool is completed, the virtual machine and the cloud disk may be created based on the image file after the migration, and if the delivery of the virtual machine fails, it is indicated that the capacity expansion is abnormal, and at this time, defect self-healing repair may be performed or a message may be sent according to the type of the abnormality, so as to notify a person to perform the repair.
In addition, in this embodiment, after the capacity expansion of the storage pool is completed, the configuration information related to the storage pool may be updated correspondingly, for example, the information of all the storage devices related to the capacity expansion in the CMBD, the model and the capacity of the storage device to be expanded, and the like are updated.
Referring to fig. 6, a schematic structural diagram of a capacity expansion control apparatus for a storage resource according to a second embodiment of the present application is provided, where the apparatus may be configured in an electronic device, such as a computer or a server, that is connected to a storage pool built on a cloud platform and is capable of performing data processing and storage pool control. The technical scheme in the embodiment is mainly used for capacity expansion control of the storage pool so as to improve the resource delivery rate.
Specifically, the apparatus in this embodiment may include the following units:
a request receiving unit 601 configured to receive a prediction request;
a storage obtaining unit 602, configured to obtain storage state information of a storage pool when the request receiving unit 601 receives a prediction request, where the storage pool is a storage pool established on a cloud platform;
a demand predicting unit 603, configured to predict storage demand of the storage pool in a first time period in the future according to at least the storage status information; the first time period is a preset time period after the current moment;
a storage control unit 604, configured to perform a capacity expansion operation on the storage pool if the storage demand meets a resource capacity expansion condition, so that the available storage resources of the storage pool meet the storage demand in the first time period.
According to the above scheme, in the capacity expansion control device for storage resources provided in the second embodiment of the present application, under the condition that the prediction request is received, the storage state information of the storage pool built on the cloud platform is obtained, so as to predict the storage demand of the storage pool in the future time period, and further, under the condition that the storage in the future time period needs to meet the resource capacity expansion condition, that is, capacity expansion needs to be performed, capacity expansion operation is performed on the storage pool, so that the available storage resources in the storage pool meet the storage demand in the future time period. It can be seen that, in this embodiment, by predicting whether the capacity of the storage pool needs to be expanded in a future time period and performing resource expansion in advance when needed, it is ensured that the available storage resources in the storage pool are always in an abundant state by pre-expansion of the available storage resources, and a situation of a slow resource delivery rate caused by expansion when the available resources are in shortage can be avoided.
In one implementation manner, when performing a capacity expansion operation on the storage pool, the storage control unit 604 is specifically configured to: adding a storage device to the storage pool; updating configuration information corresponding to the storage pool on the cloud platform; configuring an operating system for the added storage devices in the storage pool.
Optionally, when the storage control unit 604 adds a storage device to the storage pool, it is specifically configured to: building a new storage device in the storage pool; or starting the storage device in the closed state in the storage pool; or, dividing the storage device for the cloud platform in the storage devices allocated to other platforms in the storage pool.
Optionally, when the storage control unit 604 configures an operating system for the storage device added in the storage pool, specifically, the operating system is configured to: obtaining an image file of an operating system in the original storage equipment in the storage pool; and migrating the image file of the operating system to the storage device added in the storage pool.
Optionally, the storage parameters of the storage devices added in the storage pool correspond to the storage requirements.
In one implementation, the demand prediction unit 603 is specifically configured to: sampling the storage state information according to a corresponding time sequence to obtain sampling data; and at least performing prediction processing on the sampled data to obtain the storage requirement of the storage pool in a first time period.
In one implementation, the apparatus in this embodiment may further include the following units, as shown in fig. 7:
after the storage control unit 604 performs the capacity expansion operation on the storage pool, the exception checking unit 605 is configured to perform exception checking on the expanded storage pool to obtain a checking result, where the checking result indicates whether the capacity expansion on the storage pool is successful.
Optionally, the exception checking unit 605 performs exception checking on the expanded storage pool, which includes any one or more of the following items: checking whether the operating system in the expanded storage pool is normal; checking whether the storage resources in the expanded storage pool have delivery abnormity; and checking whether the cloud platform can read and write the expanded storage pool.
It should be noted that, for the specific implementation of each unit in the present embodiment, reference may be made to the corresponding content in the foregoing, and details are not described here.
Referring to fig. 8, a structural schematic diagram of an electronic device provided in a third embodiment of the present application is shown, where the electronic device may be an electronic device, such as a computer or a server, that is connected to a storage pool built on a cloud platform and is capable of performing data processing and storage pool control. The technical scheme in the embodiment is mainly used for capacity expansion control of the storage pool so as to improve the resource delivery rate.
Specifically, the electronic device in this embodiment may include the following structure:
a memory 801 for storing an application program and data generated by the application program;
a processor 802 for executing the application to implement:
under the condition of receiving a prediction request, obtaining storage state information of a storage pool, wherein the storage pool is a storage pool built on a cloud platform;
predicting storage demand of the storage pool in a first time period in the future according to at least the storage state information; the first time period is a preset time period after the current moment;
and under the condition that the storage demand meets a resource capacity expansion condition, executing capacity expansion operation on the storage pool so that the available storage resources of the storage pool meet the storage demand in the first time period.
According to the scheme, in the electronic device provided by the third embodiment of the application, under the condition that the prediction request is received, the storage state information of the storage pool built on the cloud platform is obtained, so that the storage demand of the storage pool in a future time period is predicted, and then the capacity expansion operation is performed on the storage pool under the condition that the storage in the future time period needs to meet the resource capacity expansion condition, namely capacity expansion needs to be performed, so that the available storage resources in the storage pool meet the storage demand in the future time period. It can be seen that, in this embodiment, by predicting whether the capacity of the storage pool needs to be expanded in a future time period and performing resource expansion in advance when needed, it is ensured that the available storage resources in the storage pool are always in an abundant state by pre-expansion of the available storage resources, and a situation of a slow resource delivery rate caused by expansion when the available resources are in shortage can be avoided.
The technical solution of the present application is explained in detail below:
the inventor of the application researches and discovers a storage pool built by a cloud platform: with the rapid development of services, the storage of a private cloud platform will continue to increase, and monitoring and expansion of the storage capacity need to consume a large amount of manpower and financial resources. Taking a private cloud platform constructed by an OpenStack project as an example, when the backend storage is SAN storage, the expansion of managing storage resources by using SVC is a complex process, and includes the following steps:
1. allocating a storage pool in the SVC;
2. configuring the computing node to identify the storage device;
3. the OpenStack storage component issues a configuration file;
4. migrating the cloud mirror image to a new storage pool;
5. and performing virtual machine delivery test based on the migrated mirror image.
Such a complex process results in the need to allocate a new SVC storage pool once the SVC capacity reaches or approaches the limits of the expansion, which process may be longer and lower in power success at one time. It is necessary to prepare the SVC resource pool in advance by resource pre-allocation. When the resource pool is needed to be delivered, expanding the SVC resource pool to a deliverable level, and switching to the resource pool for delivery, wherein the delivery refers to providing resources for users.
In the resource preparation process, not only the storage resource but also necessary calculation resource preparation are required to be prepared. For example, the necessary operating system image needs to be copied into the resource pool to ensure that the relevant automation delivery is implemented based on the image. If such cloud computing front resource preparation is not performed, in the resource delivery process such as a virtual machine, the delivery speed is affected by factors such as a network and a disk IO, and becomes very slow.
As can be seen, in the current resource pool expansion scheme, the solution taking OpenStack as a core has no resource pre-design, and although the required delivery can be functionally realized, the delivery rate is significantly low, which results in poor user experience and application experience and low execution efficiency.
The poor user experience means that: after the capacity expansion is completed, the resource pre-delivery check is not carried out, so that the cloud host delivery is influenced; and the low efficiency means that: the cloud mirror image migration time involved after capacity expansion is long, and service cannot be provided for users in time.
In view of this, the inventor of the present application further studies and provides a technical scheme for resource pre-delivery based on capacity prediction, which can realize storage capacity prediction at the level of hours, days, weeks, and the like, can identify different storage types to issue adaptive configuration information by combining with a preset rule engine, and perform quality check on SVC storage and OpenStack cloud platforms after the storage resources are expanded; moreover, by allocating a small-capacity storage pool as a preposed resource pool, switching is triggered when resource delivery is carried out, and then a database and the CMDB need to be updated, so that new storage resources can be conveniently applied when next delivery is carried out; in addition, in a database ha (high available) or Cluster (Cluster) scenario, if two or more nodes belong to different SVC resource pools to deliver resources, the SVC resource pools may need to have consistent performance and may not be unbalanced. Therefore, assuming that HA or Cluster delivers through the resource pools A and B, any one of the storage pools A and B is full, and the HA or the Cluster switches to the storage pools C and D simultaneously during automatic delivery; the released storage pool may also be reused based on cloud platform lifecycle management rules.
Therefore, the technical scheme provided by the application can have the following advantages:
1. the user experience is better, and the efficiency is higher;
by resource preposition, the rapid SVC delivery capability is realized in place, the image of the rapid operating system is available, and the delivery efficiency of the virtual machine is ensured;
2. due to the fact that resources and environment checking time are more abundant, the power of the virtual machine and other resources which are delivered successfully at one time is guaranteed. The failure of cloud computing resource delivery caused by the complex SVC delivery process or the complex mirror image migration process is avoided;
3. based on the rule engine scheme, the arrangement process under a complex scene can be solved;
4. the risk brought to the cloud platform by storage and expansion can be reduced in the quality inspection process;
5. the resource pre-delivery is used for preparing for subsequent allocation of storage resources, so that the capacity expansion efficiency is improved;
6. the resource delivery check can verify the availability of the OpenStack cloud platform.
Specifically, the technical scheme of the application is summarized as follows:
the modules implemented by the technical solution of the present application are shown in fig. 9, and the following processes implemented by the modules are organized as follows in combination with steps 1 to 10 in fig. 10:
firstly, a console management timer program realized by the application can trigger a prediction program at regular time by the timer, such as step 1-step 2;
secondly, the prediction program realized by the method integrates monitoring data, an OpenStack database, a CMDB and an SVC database, the data are cleaned, a prediction algorithm is used for analyzing the data, and a decision-making program is triggered after the analysis, as shown in step 3;
a. and resampling the time sequence database data of the monitoring system according to the service scene so as to simplify calculation. For example, the granularity is resampled to the day level and future 15-day resource growth predictions are made based thereon.
b. The SVC resource pool delivers not only OpenStack resources but also physical machines and other resources. The prediction horizon will include SVC consumption, OpenStack resource delivery estimates, and other predictions of consumption of SVC resources.
c. And (4) selecting a prediction algorithm or manually marking to improve the prediction quality according to the service scene.
(1) For thin provisioning resource delivery, the use of classical prediction algorithms may often suffice, such as ARIMA and the like. The prediction accuracy may be insufficient based on this, but is suitable for most scenarios.
(2) Since private cloud resource pools are typically not very large. The large project will have a large impact on the resource pool, and the possible large project start time and the requirement for storage delivery can be manually entered in the prediction module, which will effectively improve the prediction quality.
And then, judging whether the SVC needs to be expanded by the decision program, and starting the arranging modules of different cloud computing resources under the condition that the SVC needs to be expanded in step 4. According to different service scenes, the capacity expansion mode has 3 modes, such as building a new storage device for a resource pool, switching the storage device in an idle state in the resource pool to an active state, dividing the storage devices of other services or platforms to a current cloud platform, and the like.
In addition, the rules engine generates the required execution orchestration policies. The arranging module acquires the strategies to be arranged, generates an execution instruction and executes the arranging activity, as shown in step 5:
a. calling an SVC API (Application Programming Interface) or an instruction to operate SVC storage;
b. calling an OpenStack API or an instruction to perform mirror image updating and related data state updating;
c. starting image migration, wherein after the image migration is finished, a quality inspection module is started, and if the quality inspection is passed, the state of the OpenStack system is updated;
and finally, the quality inspection module performs resource preposition delivery inspection. And (5) calling the rule engine of the intelligent analysis module again when the quality inspection is abnormal, generating a defect self-healing repair instruction or starting a notification program to inform a system administrator of manual intervention solution in step 8 until the quality inspection is finished in step 10. After the quality check is successful, the CMDB data needs to be updated, step 9.
The common checking items include whether the mirror image is migrated normally, whether the virtual machine is delivered normally, whether the cloud disk can be read and written normally, and the like.
The following describes a scheme of performing intelligent analysis at a timing in the present application with reference to a timing prediction flowchart shown in fig. 11:
first, the prediction module is described as follows:
1. triggered by a timer program, the prediction program obtaining data from a plurality of data sources (monitoring data, OpenStack database, SVC database, CMDB);
2. the existing data is analyzed by using a prediction algorithm, and possible prediction models are as follows: autoregressive moving average model ARMA (autoregressive moving average model), ARIMA, or the like. The predicted scenario is as follows:
a. predicting the capacity increase of the resource pool;
b. under the database HA scene, predicting the capacity conditions of the A and B storage pools;
c. physical storage device capacity growth prediction;
d. resources of cloud platforms such as OpenStack are delivered and increased or resources are recycled;
e. related devices such as physical machine resource commit growth or resource reclamation;
f. pre-resource preparation conditions;
g. the possible effects of manually supplementing large projects and voluntary deliveries such as SVC.
The Interface design UI (user Interface design) or data import function of the prediction module ensures that the manual supplementary data is stored in the corresponding database.
3. And triggering a rule engine decision module after the prediction process is completed.
The decision process in the present application is described in detail with reference to the decision process flow chart shown in fig. 12:
first, the decision module of the present application is described as follows:
1. starting;
2. and (3) determining whether the storage equipment needs capacity expansion or not by combining rule engine reasoning, wherein possible capacity expansion forms comprise:
a. expanding the capacity of the SVC currently used;
b. creating a new SVC resource pool, migrating resources such as images and the like, and preparing the resources in advance for future capacity expansion;
c. expanding the SVC resource which is ready to be placed in front, and activating delivery activities to the resource pool;
d. the resources are abundant and no operation is needed. And starting the timer for the next inspection, and analyzing.
3. If the SVC storage equipment needs to be expanded, namely the SVC storage pool is not enough, expanding the storage pool, wherein the expanding process of the SVC storage pool mainly comprises calling an SVC API (application programming interface) or an instruction to configure an SVC distribution storage pool, calling an OpenStack API or an instruction to issue configuration and service management, cloud mirror image migration and the like;
4. after the capacity expansion of the SVC storage pool is completed, whether the current storage pool is prepared by the preposed resources is checked, and if not, the resources are accurately preposed.
And triggering the mirror image migration module after the steps are completed.
The following describes the mirror migration module in the present application with reference to the mirror migration flowchart shown in fig. 13:
and identifying and acquiring a mirror image migration range from the database in the process of the mirror image migration module, wherein the mirror image migration range comprises information such as cloud platform positions and the like, then issuing a migration task, calling an OpenStack API to perform mirror image migration operation, and checking mirror image availability after migration is completed.
The following describes the quality inspection module in the present application with reference to the quality inspection flowchart shown in fig. 14:
the quality inspection module process is resource preposed delivery inspection, a virtual machine and a cloud disk are created based on the migrated mirror image, if the virtual machine delivery fails, an inspection program is triggered, the inspection program mainly comprises the steps of inspecting the availability of SVC, inspecting the health state of each component of OpenStack, inspecting the availability of the mirror image, and after all the problems are repaired, the virtual machine delivery inspection is restarted, namely the resource preposed delivery inspection is carried out, and resource cleaning is carried out under the condition that the inspection delivery is successful.
The following describes data synchronization in the present application with reference to a data synchronization flowchart shown in fig. 15:
after the SVC is expanded, the monitoring system API is called to update the monitoring configuration, for example, newly expanded SVC is updated, the configuration information such as monitoring required to be added, monitoring of capacity trend and monitoring of load update is updated, and then the API of the CMDB platform is called to add and modify CMDB data.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A capacity expansion control method of storage resources comprises the following steps:
under the condition of receiving a prediction request, obtaining storage state information of a storage pool, wherein the storage pool is a storage pool built on a cloud platform;
predicting storage demand of the storage pool in a first time period in the future according to at least the storage state information; the first time period is a preset time period after the current moment;
and under the condition that the storage demand meets a resource capacity expansion condition, executing capacity expansion operation on the storage pool so that the available storage resources of the storage pool meet the storage demand in the first time period.
2. The method of claim 1, performing a capacity expansion operation on the storage pool, comprising at least:
adding a storage device to the storage pool;
updating configuration information corresponding to the storage pool on the cloud platform;
configuring an operating system for the added storage devices in the storage pool.
3. The method of claim 2, wherein adding storage devices to the storage pool comprises:
building a new storage device in the storage pool;
or starting the storage device in the closed state in the storage pool;
or, dividing the storage device for the cloud platform in the storage devices allocated to other platforms in the storage pool.
4. The method of claim 2, configuring an operating system for the added storage devices in the storage pool, comprising:
obtaining an image file of an operating system in the original storage equipment in the storage pool;
and migrating the image file of the operating system to the storage device added in the storage pool.
5. The method of claim 2, wherein the storage parameters of the added storage devices in the storage pool correspond to the storage demand.
6. The method of claim 1, predicting storage demand of the storage pool for a first time period based at least on the storage status information, comprising:
sampling the storage state information according to a corresponding time sequence to obtain sampling data;
and at least performing prediction processing on the sampled data to obtain the storage requirement of the storage pool in a first time period.
7. The method of claim 1, further comprising, after performing a capacity expansion operation on the storage pool:
and carrying out abnormal inspection on the expanded storage pool to obtain an inspection result, wherein the inspection result represents whether the expansion of the storage pool is successful.
8. The method of claim 7, wherein performing exception checking on the expanded storage pool comprises any one or more of:
checking whether the operating system in the expanded storage pool is normal;
checking whether the storage resources in the expanded storage pool have delivery abnormity;
and checking whether the cloud platform can read and write the expanded storage pool.
9. A capacity expansion control device for a storage resource includes:
the storage obtaining unit is used for obtaining storage state information of a storage pool under the condition that a prediction request is received, wherein the storage pool is a storage pool built on a cloud platform;
a demand prediction unit, configured to predict storage demand of the storage pool in a first time period in the future according to at least the storage status information; the first time period is a preset time period after the current moment;
and the storage control unit is used for executing capacity expansion operation on the storage pool under the condition that the storage demand meets a resource capacity expansion condition, so that the available storage resources of the storage pool meet the storage demand in the first time period.
10. An electronic device, comprising:
the memory is used for storing an application program and data generated by the running of the application program;
a processor for executing the application to implement:
under the condition of receiving a prediction request, obtaining storage state information of a storage pool, wherein the storage pool is a storage pool built on a cloud platform;
predicting storage demand of the storage pool in a first time period in the future according to at least the storage state information; the first time period is a preset time period after the current moment;
and under the condition that the storage demand meets a resource capacity expansion condition, executing capacity expansion operation on the storage pool so that the available storage resources of the storage pool meet the storage demand in the first time period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110150400.0A CN112799596A (en) | 2021-02-03 | 2021-02-03 | Capacity expansion control method and device for storage resources and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110150400.0A CN112799596A (en) | 2021-02-03 | 2021-02-03 | Capacity expansion control method and device for storage resources and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112799596A true CN112799596A (en) | 2021-05-14 |
Family
ID=75813956
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110150400.0A Pending CN112799596A (en) | 2021-02-03 | 2021-02-03 | Capacity expansion control method and device for storage resources and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112799596A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113656162A (en) * | 2021-08-18 | 2021-11-16 | 恒生电子股份有限公司 | Resource application method and device, electronic equipment and storage medium |
| CN114461138A (en) * | 2021-12-24 | 2022-05-10 | 天翼云科技有限公司 | Scheduling method and device of storage resources, electronic equipment and readable storage medium |
| CN114928606A (en) * | 2022-01-29 | 2022-08-19 | 上海瀚银信息技术有限公司 | Scheduling method and system of server resources |
| CN115412567A (en) * | 2022-08-09 | 2022-11-29 | 浪潮云信息技术股份公司 | Cloud platform storage capacity planning system and method based on time series prediction |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100082900A1 (en) * | 2008-10-01 | 2010-04-01 | Hitachi, Ltd. | Management device for storage device |
| US20120042122A1 (en) * | 2006-10-16 | 2012-02-16 | Nobuo Beniyama | Storage capacity management system in dynamic area provisioning storage |
| CN103116475A (en) * | 2013-02-06 | 2013-05-22 | 浪潮电子信息产业股份有限公司 | Method of automatic simplifying allocation expansion |
| CN103365781A (en) * | 2012-03-29 | 2013-10-23 | 国际商业机器公司 | Method and device for dynamically reconfiguring storage system |
| WO2018077079A1 (en) * | 2016-10-31 | 2018-05-03 | 阿里巴巴集团控股有限公司 | Application capacity enlargement method, apparatus and system |
| CN112130767A (en) * | 2020-09-18 | 2020-12-25 | 苏州浪潮智能科技有限公司 | Storage pool use capacity determination method, device, equipment and medium |
| CN112130761A (en) * | 2020-09-04 | 2020-12-25 | 苏州浪潮智能科技有限公司 | Capacity expansion method and system for storage system and related device |
-
2021
- 2021-02-03 CN CN202110150400.0A patent/CN112799596A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120042122A1 (en) * | 2006-10-16 | 2012-02-16 | Nobuo Beniyama | Storage capacity management system in dynamic area provisioning storage |
| US20100082900A1 (en) * | 2008-10-01 | 2010-04-01 | Hitachi, Ltd. | Management device for storage device |
| CN103365781A (en) * | 2012-03-29 | 2013-10-23 | 国际商业机器公司 | Method and device for dynamically reconfiguring storage system |
| CN103116475A (en) * | 2013-02-06 | 2013-05-22 | 浪潮电子信息产业股份有限公司 | Method of automatic simplifying allocation expansion |
| WO2018077079A1 (en) * | 2016-10-31 | 2018-05-03 | 阿里巴巴集团控股有限公司 | Application capacity enlargement method, apparatus and system |
| CN112130761A (en) * | 2020-09-04 | 2020-12-25 | 苏州浪潮智能科技有限公司 | Capacity expansion method and system for storage system and related device |
| CN112130767A (en) * | 2020-09-18 | 2020-12-25 | 苏州浪潮智能科技有限公司 | Storage pool use capacity determination method, device, equipment and medium |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113656162A (en) * | 2021-08-18 | 2021-11-16 | 恒生电子股份有限公司 | Resource application method and device, electronic equipment and storage medium |
| CN114461138A (en) * | 2021-12-24 | 2022-05-10 | 天翼云科技有限公司 | Scheduling method and device of storage resources, electronic equipment and readable storage medium |
| CN114461138B (en) * | 2021-12-24 | 2024-06-07 | 天翼云科技有限公司 | Scheduling method and device of storage resources, electronic equipment and readable storage medium |
| CN114928606A (en) * | 2022-01-29 | 2022-08-19 | 上海瀚银信息技术有限公司 | Scheduling method and system of server resources |
| CN114928606B (en) * | 2022-01-29 | 2024-04-23 | 上海瀚银信息技术有限公司 | Scheduling method and system for server resources |
| CN115412567A (en) * | 2022-08-09 | 2022-11-29 | 浪潮云信息技术股份公司 | Cloud platform storage capacity planning system and method based on time series prediction |
| CN115412567B (en) * | 2022-08-09 | 2024-04-30 | 浪潮云信息技术股份公司 | Cloud platform storage capacity planning system and method based on time sequence prediction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112799596A (en) | Capacity expansion control method and device for storage resources and electronic equipment | |
| CN109582433B (en) | Resource scheduling method and device, cloud computing system and storage medium | |
| JPWO2007072544A1 (en) | Information processing apparatus, computer, resource allocation method, and resource allocation program | |
| EP3191948A1 (en) | Computing instance launch time | |
| CN112769810B (en) | Firewall testing method and device, nonvolatile storage medium and electronic device | |
| CN111309440B (en) | Method and equipment for managing and scheduling multiple types of GPUs | |
| CN111143039B (en) | Scheduling method and device of virtual machine and computer storage medium | |
| CN112416585A (en) | GPU resource management and intelligent scheduling method for deep learning | |
| CN111078404B (en) | Computing resource determining method and device, electronic equipment and medium | |
| CN111953809B (en) | Method, device, equipment and system for managing resource address | |
| CN115373861B (en) | GPU resource scheduling method and device, electronic equipment and storage medium | |
| CN113312153A (en) | Cluster deployment method and device, electronic equipment and storage medium | |
| US12026536B2 (en) | Rightsizing virtual machine deployments in a cloud computing environment | |
| CN114327881A (en) | Task scheduling method and device | |
| US9372731B1 (en) | Automated firmware settings framework | |
| CN116701043A (en) | Heterogeneous computing system-oriented fault node switching method, device and equipment | |
| WO2020206699A1 (en) | Predicting virtual machine allocation failures on server node clusters | |
| CN114598665A (en) | Resource scheduling method and device, computer readable storage medium and electronic equipment | |
| CN116483546B (en) | Distributed training task scheduling method, device, equipment and storage medium | |
| CN116992982A (en) | Model deployment method, device, system, electronic equipment and storage medium | |
| CN115794306A (en) | Resource allocation method and device based on preemption instance, electronic equipment and medium | |
| CN114020214A (en) | Storage cluster capacity expansion method and device, electronic equipment and readable storage medium | |
| CN113760446A (en) | Resource scheduling method, device, equipment and medium | |
| CN111858234A (en) | Task execution method, device, equipment and medium | |
| CN113271323A (en) | Cluster capacity expansion method and device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |