CN116107518B - Storage cluster power consumption processing method and device, storage medium and electronic equipment - Google Patents
Storage cluster power consumption processing method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN116107518B CN116107518B CN202310382634.7A CN202310382634A CN116107518B CN 116107518 B CN116107518 B CN 116107518B CN 202310382634 A CN202310382634 A CN 202310382634A CN 116107518 B CN116107518 B CN 116107518B
- Authority
- CN
- China
- Prior art keywords
- power consumption
- peak
- storage cluster
- memories
- historical
- 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.)
- Active
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
- G06F3/0625—Power saving in storage systems
-
- 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]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
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)
- Power Sources (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a storage cluster power consumption processing method and device, a storage medium and electronic equipment. Wherein the method comprises the following steps: acquiring historical service data volumes respectively corresponding to a plurality of historical moments of a storage cluster and power consumption corresponding to the historical service data volumes, wherein the historical moments are moments with time sequences in a preset historical period; according to the historical business data volume and the power consumption corresponding to the historical business data volume, determining peak time, low peak time, peak power consumption corresponding to the peak time and low peak power consumption corresponding to the low peak time of the storage cluster; and determining the global power consumption of a plurality of memories included in the storage cluster based on the peak power consumption, the low peak power consumption and the power consumption threshold corresponding to each of the preset power consumption levels. The invention solves the technical problem of non-ideal energy saving of the storage clusters in the related technology.
Description
Technical Field
The present invention relates to the field of memory technologies, and in particular, to a method and apparatus for processing power consumption of a storage cluster, a storage medium, and an electronic device.
Background
At present, solid-state drive (SSD) technology is fast-moving, has uninterrupted working capacity, can process I/O (input/output) intensive work load, and in most systems, cannot run full of the hardware capacity of the SSD, that is to say, the SSD running with full power consumption is a resource waste. In the related art, SSD is often used as a cache, and a Hard Disk Drive (HDD) is used as a distributed storage system of a data storage system, so that energy consumption is reduced through an HDD dormancy technology, a full flash memory requirement with high performance requirements cannot be met, and energy saving and consumption reduction efficiency cannot be considered under the condition of high real-time performance.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The embodiment of the invention provides a storage cluster power consumption processing method, a storage cluster power consumption processing device, a storage medium and electronic equipment, which at least solve the technical problem of non-ideal storage cluster energy conservation in the related technology.
According to an aspect of an embodiment of the present invention, there is provided a storage cluster power consumption processing method, including: acquiring historical service data volumes respectively corresponding to a plurality of historical moments of a storage cluster and power consumption corresponding to the historical service data volumes, wherein the historical moments are moments with time sequences in a preset historical period; determining a peak time period, a low peak time period, a peak power consumption corresponding to the peak time period and a low peak power consumption corresponding to the low peak time period of the storage cluster according to the historical service data volume and the power consumption corresponding to the historical service data volume, wherein the peak time period is a time period when the service data volume of the storage cluster in a preset operation period is greater than a peak threshold value, and the low peak time period is a time period when the service data volume of the storage cluster in the preset operation period is less than a low peak threshold value; and determining global power consumption of a plurality of memories included in the storage cluster based on the peak power consumption, the low peak power consumption and power consumption thresholds corresponding to a plurality of preset power consumption levels respectively.
According to another aspect of the embodiment of the present invention, there is provided a storage cluster power consumption processing apparatus, including: the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring historical service data volumes respectively corresponding to a plurality of historical moments of a storage cluster and power consumption corresponding to the historical service data volumes, and the plurality of historical moments are moments with time sequences in a preset historical period; a first determining module, configured to determine, according to the historical traffic data and power consumption corresponding to the historical traffic data, a peak period, a low peak period, a peak power consumption corresponding to the peak period, and a low peak power consumption corresponding to the low peak period, where the peak period is a period in which the traffic data of the storage cluster in a predetermined operation period is greater than a peak threshold, and the low peak period is a period in which the traffic data of the storage cluster in the predetermined operation period is less than a low peak threshold; and the second determining module is used for determining the global power consumption of a plurality of memories included in the storage cluster based on the peak power consumption, the low peak power consumption and power consumption thresholds respectively corresponding to a plurality of preset power consumption levels.
According to another aspect of embodiments of the present invention, there is provided a non-volatile storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform any one of the storage cluster power consumption processing methods.
According to another aspect of an embodiment of the present invention, there is provided an electronic apparatus including: one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the storage cluster power consumption processing method of any of the claims.
In the embodiment of the invention, the power consumption corresponding to the historical service data volume is obtained by obtaining the historical service data volume respectively corresponding to a plurality of historical moments of a storage cluster, wherein the plurality of historical moments are moments with time sequences in a preset historical period; determining a peak time period, a low peak time period, a peak power consumption corresponding to the peak time period and a low peak power consumption corresponding to the low peak time period of the storage cluster according to the historical service data volume and the power consumption corresponding to the historical service data volume, wherein the peak time period is a time period when the service data volume of the storage cluster in a preset operation period is greater than a peak threshold value, and the low peak time period is a time period when the service data volume of the storage cluster in the preset operation period is less than a low peak threshold value; and determining global power consumption of a plurality of memories included in the storage cluster based on the peak power consumption, the low peak power consumption and power consumption thresholds corresponding to a plurality of preset power consumption levels respectively. The method achieves the aim of balancing the business data volume and the memory energy consumption, achieves the technical effect of improving the memory power consumption utilization rate, and further solves the technical problem of non-ideal energy saving of the memory clusters in the related technology.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
FIG. 1 is a flow chart of an alternative storage cluster power consumption processing method provided in accordance with an embodiment of the present invention;
FIG. 2 is a schematic diagram of an alternative storage cluster power consumption processing method provided according to an embodiment of the present invention;
FIG. 3 is a functional block diagram of an alternative storage cluster power consumption processing method provided in accordance with an embodiment of the present invention;
FIG. 4 is a schematic illustration showing an alternative storage cluster power consumption processing method according to an embodiment of the present invention;
FIG. 5 is a balanced schematic diagram of an alternative storage cluster power consumption processing method provided in accordance with an embodiment of the present invention;
fig. 6 is a schematic diagram of an alternative storage cluster power consumption processing apparatus according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of description, the following will describe some terms or terms related to the embodiments of the present application:
an enterprise-level SSD (solid state drive) refers to a solid state disk applied to various enterprise-level scenarios such as high-performance computing, edge computing, high-end storage, and data centers, and has uninterrupted working capacity, and is capable of handling I/O intensive workloads, such as database files, index logs, data analysis, and other transaction operations with high performance requirements.
And (3) mixed flash distributed storage, wherein an enterprise SSD is used as a cache, and a hard disk drive HDD is used as a distributed storage system of the data storage system.
The full-flash distributed storage is a distributed storage system, wherein all the included memories are enterprise SSDs.
The PUE value (Power usage Effectiveness) is the ratio between the total equipment energy consumption of the data center for processing service data and the energy consumption of the IT equipment (including equipment refrigeration, power distribution and power consumption), and the closer the PUE value is to 1, the more the electricity consumed by the data center is used in the computing power of the data center, namely in the processing of the service.
The storage resource Pool, also known as Pool, logically partitions the storage services provided by a storage cluster into one or more storage areas, which can be understood as the name space for data objects.
SSD technology has been in rapid progress, and the read IOPS (Input output operation per second, read/write per second) of single SSDs has broken through 100 tens of thousands. In systems where multiple SSDs are present, the software capability of the service is harder to reach the hardware bottleneck, i.e., in most systems, the SSD cannot be run full. That is, SSD operating with full power consumption is a waste of resources. In order to reduce resource waste, how to refine operation and maintenance energy-saving control so as to improve energy utilization efficiency and reduce PUE value is a problem to be solved in a data center.
In the related art, the storage is set as the HDD, and the energy consumption is reduced by means of the dormancy technology, the scheme is mainly used for archiving a cold storage environment, archived data is rarely accessed again, and when the archived data is accessed, a disk can be awakened to access, so that the real-time performance and the performance requirements are not high. The related scheme can not meet the full-flash requirement with high performance requirements, can not provide an energy consumption utilization rate processing scheme for full-flash distributed storage, and has the problem of unsatisfactory energy saving effect.
In view of the foregoing, embodiments of the present invention provide a method embodiment for processing power consumption of a storage cluster, it should be noted that the steps illustrated in the flowchart of the figures may be performed in a computer system, such as a set of computer-executable instructions, and that although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order other than that illustrated herein.
Fig. 1 is a flowchart of a storage cluster power consumption processing method according to an embodiment of the present invention, as shown in fig. 1, the method includes the steps of:
step S102, obtaining historical service data volumes respectively corresponding to a plurality of historical moments of a storage cluster and power consumption corresponding to the historical service data volumes, wherein the historical moments are moments with time sequences in a preset historical period;
It can be understood that the storage cluster includes a plurality of memories, which are configured to perform data processing on the received service, and in a plurality of historical moments when there is a time sequence, the storage cluster corresponds to historical service data volumes respectively, and resources are required to be consumed in the processing process of the historical service data volumes, so that power consumption corresponding to the historical service data volumes is obtained, and the corresponding relationship between the processing capacity and the power consumption of the storage cluster can be reflected by using the historical service data volumes.
Alternatively, the storage clusters may be all-flash distributed storage.
Alternatively, the storage cluster may include a plurality of memories that are SSDs, or enterprise-level SSDs.
Step S104, determining a peak time period, a low peak time period, a peak power consumption corresponding to the peak time period and a low peak power consumption corresponding to the low peak time period of the storage cluster according to the historical service data volume and the power consumption corresponding to the historical service data volume, wherein the peak time period is a time period when the service data volume of the storage cluster is greater than a peak threshold value in a preset operation period, and the low peak time period is a time period when the service data volume of the storage cluster is less than the low peak threshold value in the preset operation period;
It can be appreciated that, according to the above-mentioned historical traffic data volume and the power consumption corresponding to the above-mentioned historical traffic data volume, the corresponding relationship between the processing capacity and the power consumption of the storage cluster is represented. Because the traffic is not fixed, a certain rule may exist in a time angle, and the traffic is periodically increased or decreased, through the power consumption corresponding to the historical traffic in a plurality of historical moments, the linkage relation among the processing time dimension, the data volume dimension and the power consumption dimension can be embodied, so that the peak time period of the storage cluster in which the traffic is greater than the peak threshold value in the preset operation period and the peak power consumption corresponding to the peak time period are determined, and the low peak time period of the storage cluster in which the traffic is less than the low peak threshold value in the preset operation period and the low peak power consumption corresponding to the low peak time period are determined. Through the processing, the historical business data volume and the power consumption change trend are used for determining the business data volume change trend, so that the business data volume and the power consumption are balanced, and the power consumption utilization rate is improved.
In an alternative embodiment, the determining the peak period, the low peak period, the peak power consumption corresponding to the peak period, and the low peak power consumption corresponding to the low peak period of the storage cluster according to the historical traffic data volume and the power consumption corresponding to the historical traffic data volume includes: determining the service type of the current service of the storage cluster, and determining the corresponding power consumption of the storage cluster for processing the first service with the same service type in the power consumption corresponding to the historical service data volume; and determining the peak time period, the low peak time period, the peak power consumption and the low peak power consumption based on the power consumption corresponding to the first service.
It will be appreciated that the power consumption of the required processing consumption for different traffic types is different, e.g. the read intensive traffic power consumption is lower than the write intensive traffic power consumption. Therefore, in order to improve the energy saving efficiency in a refined way, the service type of the current service of the storage cluster is determined, and the corresponding power consumption of the storage cluster for processing the first service with the same service type is determined in the power consumption corresponding to the historical service data according to the service type, and the power consumption corresponding to the first service is referred to, so that the change trend of the power consumption for processing the current service is estimated. And determining peak time, low peak time, peak power consumption and low peak power consumption based on the power consumption corresponding to the first service.
Alternatively, the service types may be various, for example: the database IO intensive service can be divided into writing intensive service and reading intensive service, the service depends on reading and writing capability, and IOPS is generally used as capability measurement index. The method can also be an image service, and the image service takes the bandwidth capability as a capability measurement index. The power consumed for providing high IOPS or large bandwidth traffic handling in a storage cluster is different, so traffic types have an impact on power consumption.
In an alternative embodiment, the method further comprises: and determining a target class range corresponding to the service type and a target class included in the target class range from the plurality of power consumption classes based on the power consumption corresponding to the first service.
It can be appreciated that the power consumption levels are preset, and the power consumption ranges possibly consumed by different types of services need to be selected according to the service type of the current service. Accordingly, a target class range corresponding to the service type is determined among the plurality of power classes based on the power consumption corresponding to the first service, and a target class included in the target class range may be one or more. Through the treatment, the energy-saving effect is further improved.
Optionally, the above-described plurality of power consumption level distributions correspond to different operating configurations, such as: the operation configuration can be used for setting and matching the rotation speed of the fan and the power supply according to multiple power consumption levels so as to achieve the best power consumption reduction effect.
In an optional embodiment, the determining, based on the power consumption corresponding to the first service, a target class range corresponding to the service type and a target class included in the target class range in the plurality of power consumption classes includes: determining a target service capability required for processing the current service; determining the required power consumption corresponding to the target service capacity based on the power consumption corresponding to the first service; and determining the target grade range and the target grade based on the required power consumption corresponding to the target service capability.
It can be understood that in the practical application scenario, the processing of the service data volume can be characterized from the number angle, and can also be characterized based on the processing level angle, so that the service capability required by the processing is embodied. Thus, there is a need to determine the target service capabilities required to handle the current service. The method comprises the steps of determining required power consumption corresponding to target service capability based on power consumption corresponding to first service, determining a target grade range based on the required power consumption corresponding to the target service capability, and determining a target grade.
For ease of understanding, specific examples are given, for example: service 1 needs a high IOPS, service 2 needs a low IOPS, and service 1 tends to consume large power consumption in the case that the data volumes of service 1 and service 2 are the same. This may be due to the high performance requirements required for the process service 1, as well as the high cooling requirements. The service capability of different requirements is reflected, and the required power consumption is different.
Optionally, the target level range is determined according to a possible range of power consumption corresponding to the first service, and a certain redundancy amount may be reserved. For ease of understanding, the description is given, for example: there are 10 power consumption levels, only 3-6 power consumption levels are possible for read intensive traffic, plus a certain redundancy setting the target level range to 2-7 power consumption levels.
Step S106, determining global power consumption of a plurality of memories included in the storage cluster based on the peak power consumption, the low peak power consumption and power consumption thresholds respectively corresponding to a plurality of preset power consumption levels.
It can be appreciated that the setting policy for global power consumption of a plurality of memories included in the storage cluster is determined according to the peak power consumption, the low peak power consumption, and the power consumption threshold corresponding to each of the plurality of power consumption classes.
In an optional embodiment, the determining global power consumption of the plurality of memories included in the storage cluster based on the peak power consumption, the low peak power consumption, and power consumption thresholds corresponding to the preset power consumption levels respectively includes: determining a first level of the plurality of power consumption levels, wherein the power consumption threshold is smaller than a preset first threshold; and under the condition that the peak power consumption is smaller than the power consumption threshold corresponding to the first level, taking the preset first power consumption as the global power consumption.
It can be understood that the global setting can issue one-key setting to a plurality of memories, which is a convenient setting mode, under the condition that the peak power consumption is smaller than the first threshold value, the low peak threshold value is necessarily smaller than the first threshold value, and the first level corresponding to the first threshold value is a setting mode which consumes smaller power among a plurality of power consumption levels, so that the preset first power consumption is adopted as the global power consumption of the plurality of memories, excessive waste of resources is not caused, meanwhile, excessive setting processing is performed at the level that the consumed power consumption is lower, the energy saving effect cannot be obviously improved, and the problem of frequent adjustment to the memories is caused. Through the processing, under the condition that the storage group is at a lower power consumption level, global power consumption setting is conducted on the memories according to the first power consumption, so that rapid and efficient power consumption regulation and control are facilitated, repeated setting of the memories is avoided, and the service life of the memories is prolonged.
In an optional embodiment, the determining global power consumption of the plurality of memories included in the storage cluster based on the peak power consumption, the low peak power consumption, and power consumption thresholds corresponding to the preset power consumption levels respectively includes: determining a second level of the plurality of power consumption levels, wherein the power consumption threshold is larger than a preset second threshold, and the power consumption threshold corresponding to the first level is smaller than the power consumption threshold corresponding to the second level; and determining a global power consumption adjustment strategy based on the peak time when the peak power consumption is greater than the power consumption threshold corresponding to the second level and the low peak power consumption is less than the power consumption threshold corresponding to the first level.
It can be understood that in the case where the difference between the peak power consumption and the low peak power consumption is large, this means that the fluctuation of the data amount of such a service is large, it is inappropriate to simply perform uniform global power consumption setting, the global power consumption satisfying the peak power consumption may be high, meaning of energy saving control is lost, and setting according to the low peak power consumption in order to reduce the power consumption results in difficulty in satisfying the demand in the peak period of the service. Therefore, in the case where the peak power consumption is larger than the power consumption threshold corresponding to the second level and the low peak power consumption is smaller than the power consumption threshold corresponding to the first level, it is necessary to determine the global power consumption adjustment policy based on the fact that the difference between the peak power consumption and the low peak power consumption is large during the peak period. Through the processing, the service with high peak-to-low peak difference and large power consumption level fluctuation is subjected to fine treatment, and the energy-saving effect is improved.
In an alternative embodiment, the determining a global power consumption adjustment policy based on the peak hours includes: under the condition that the peak time is not entered, taking the first power consumption as the global power consumption; and under the condition of entering the peak time, adopting a preset second power consumption to regulate the global power consumption to obtain regulated global power consumption, wherein the second power consumption is larger than the first power consumption.
It can be understood that in the case where the peak period is not entered, the smaller first power consumption is set as the global power consumption, and each of the plurality of memories is set. With the change of the traffic trend, after the traffic is gradually busy and enters the peak period, the global power consumption needs to be improved, and the second power consumption with larger power consumption is adjusted. By the above processing, automatic power consumption adjustment during busy peak hours can be realized.
In an alternative embodiment, the method further comprises: determining a first number of first memories for burst response in the plurality of memories, and a second number of second memories other than the first number of first memories, wherein the first number is smaller than the second number; setting the second number of second memories by using the global power consumption; and setting the first number of first memories by adopting preset third power consumption, wherein the third power consumption is larger than the global power consumption.
It will be appreciated that there may be a situation where the rate of change of the traffic data amount is large in both the peak period and the low peak period, this situation is a burst response, in order to cope with such a burst response, a first number of first memories and a second number of second memories are provided, and it is to be noted that the first memories are redundancy-provided for the second memories, and therefore the first number is smaller than the second number, and the first memories as burst responses require a higher processing power than the second memories, and therefore, the first number of first memories is provided with a third power consumption, and the third power consumption is set to be greater than the global power consumption. Through the processing, a redundancy setting mode is adopted, the service data volume of the first memory for coping with sudden increase is reserved, global power consumption is not directly regulated, the change of the service data volume is favorably and elastically coped with, and the power consumption waste of redundancy setting is reduced.
In an alternative embodiment, the method further comprises: selecting the first number of second memories from the second number of second memories under the condition that the storage cluster triggers wear balance processing; the third power consumption is adopted to regulate the global power consumption corresponding to the first number of second memories respectively, so that the regulated first number of second memories are obtained; and adjusting the third power consumption corresponding to the first number of first memories respectively by adopting the global power consumption to obtain the adjusted first number of first memories.
It will be appreciated that the plurality of memories included in the storage cluster may wear during the writing/writing process, so that in order to keep the memories in the whole storage cluster in a similar operating state, it is necessary to ensure that the wear state of each memory is balanced, which is beneficial to improving the overall lifetime of the storage cluster. Therefore, since the first memory is provided as redundancy, the processing capacity per se is high, and the wear is larger than that of the second memory having low power consumption, and the wear balancing process is required. The second number of second memories is selected as a substitute for the first number of first memories, i.e. also the first number of second memories. And the original global power consumption of the first number of second memories is changed into the third power consumption with higher processing capacity by adopting the third power consumption as the redundancy setting. After the first number of second memories is adjusted, the first number of first memories is released from the higher operation level, and the original third power consumption of the first number of first memories is changed to global power consumption with lower processing capacity. Through the processing, a plurality of memories can be alternately in a high abrasion state, so that the overall abrasion of the storage cluster is kept balanced.
In an alternative embodiment, the storage cluster is composed of a plurality of distributed storage nodes, each of the plurality of distributed storage nodes includes a predetermined amount of memory, and the first amount of the first memory is uniformly distributed in the plurality of distributed storage nodes.
It will be appreciated that to further ensure wear leveling, each of the plurality of distributed storage nodes has a respective distribution of the same amount of first memory such that the first amount of first memory is evenly distributed. By the aid of the processing, the abrasion state of each distributed storage node is the same, and the phenomenon that all memories in the same node are first memories for burst response is avoided, so that node pressure is overlarge, single-point damage is easier to occur, and stable operation of a storage cluster is affected.
In an alternative embodiment, before determining the first number of first memories for burst response in the plurality of memories and the second number of second memories other than the first number of first memories, the method further includes: determining a burst response time period of the storage cluster according to the historical service data volume and the power consumption corresponding to the historical service data volume, wherein the burst response time period is a time period when the change rate of the service data volume exceeds a preset rate threshold; and triggering the storage cluster to set the burst response under the condition of entering the burst response period.
It can be understood that according to the historical service data volume and the power consumption corresponding to the historical service data volume, the data volume variation trend of the current service can be reflected, the burst response time period of the storage cluster is determined, the burst response time period is a time period in which the service data volume variation rate exceeds a preset rate threshold, and under the condition of entering the burst response time period, the storage cluster is triggered to perform burst response setting, and it is required to be noted that the burst response time period is overlapped or non-overlapped with the peak time period and the low peak time period.
In an alternative embodiment, the method further comprises: and under the condition that the service data volume of the current task of the storage cluster is larger than a preset data volume threshold, the storage cluster adopts a full-power-consumption operation mode, wherein the full-power-consumption operation mode is the maximum processing capacity of the storage cluster.
It can be understood that in the case that the traffic data volume of the current task is greater than the preset data volume threshold, the current task is regarded as needing to operate in a full power consumption mode to provide the maximum processing capacity, once the traffic data volume is greater than the number threshold, the full power consumption operation does not cause excessive energy waste, when the traffic data volume is already in large quantity, once the situation of instant surge occurs, the adjustment setting of the power consumption may cause that the traffic data volume cannot be kept up, and the processing efficiency is affected. Through the processing, the operation in a full power consumption mode is triggered based on the service data volume of the current task, so that the guarantee of stable processing is provided for the application scene with larger service data volume.
In an alternative embodiment, the method further comprises: detecting the read-write data quantity corresponding to the first memories of the first quantity respectively; and triggering the storage cluster to carry out wear balance processing under the condition that the read-write data quantity corresponding to any one of the first memories is larger than a preset trigger threshold value.
It can be understood that the wear degree is reflected by the read-write data volume of the memory, and when any corresponding read-write data volume is detected to be larger than the preset trigger threshold, the wear of any memory is considered to reach a certain degree, and the wear balance processing is needed.
Through the steps S102 to S106, the purpose of balancing the business data volume and the memory energy consumption can be achieved, the technical effect of improving the memory power consumption utilization rate is achieved, and the technical problem that the memory cluster is not ideal in energy saving in the related technology is solved.
Based on the foregoing embodiments and optional embodiments, an optional implementation manner is provided in the present invention, and fig. 2 is a schematic diagram of an optional storage cluster power consumption processing method provided in an embodiment of the present invention, where a storage resource pool (i.e. a storage cluster) is a full-flash distributed storage, and includes a plurality of distributed storage nodes, such as node servers in fig. 2, each node server includes a plurality of SSD memories, and application services handled by the storage resource pool may be multiple, and are illustrated by application service 1 and application service n in fig. 2.
The IOPS, the bandwidth and the time delay of each SSD in the storage resource pool and the consumed power consumption are continuously monitored, the peak period of the busy state, the low peak period of the idle state and the service surge period with high data volume change rate are analyzed, the relation between the historical service data volume and the corresponding power consumption is obtained, and a service model is formed.
Fig. 3 is a schematic block diagram of an alternative storage cluster power consumption processing method according to an embodiment of the present invention, where, as shown in fig. 3, after a current service inputs a storage resource pool, SSD processing with high real-time performance is performed, and a global power consumption setting policy for SSD is determined according to a service capability required by the current service and a corresponding power consumption level. Also, in order to prevent the coping inadequacy caused by the surge in traffic, a burst response setting is also added as the coping. Wherein, according to the service model, the current storage resource pool capacity is judged, a plurality of power consumption levels are set, and the power consumption levels 1 to 3 in fig. 3 are only shown as examples. Each power consumption level corresponds to a service capability with a current power consumption level, the service capability may have multiple types, xi and Yi in fig. 3 are schematic identifiers of capability types, i is an identifier of a power consumption level, power consumption level 1 corresponds to a service capability (X1, Y1), and other power consumption levels are the same. Under different power consumption levels, the rotating speed of the fan and the power supply setting can be adjusted in a matched mode, so that the best power consumption reduction effect is achieved.
Still illustrated by power consumption level 1, the service capabilities (X1, Y1) are determined according to the service model obtained by analysis, and represent the service level, such as IOPS or bandwidth, that can be provided by the SSD at power consumption level 1. The estimated business capability changes with the change of the business model obtained by the analysis. The difference of service types also has an influence on consumed power consumption, such as IOPS (input output) based on database type IO intensive service and video type based on bandwidth capability. Other factors, read-intensive business power consumption is low compared to write-intensive business power consumption.
According to the information provided by the service model established by the monitoring historical service data, service peaks and service low peaks of the current service type in the previous processing can be confirmed, and the service peaks and the service low peaks are used as references of the current service, namely, peak power consumption of the current service in the peak time period is marked as A, low peak power consumption of the low peak time period is marked as B, and the peak power consumption and the low peak power consumption are respectively compared with a plurality of preset power consumption levels based on the peak power consumption and the low peak power consumption.
If the peak power consumption is smaller than the power consumption level 1, setting the global power consumption as 1, setting the actual single-disk SSD power consumption as the minimum value and recording as aW (watt), and setting a plurality of SSDs at a power consumption setting higher than aW according to the storage redundancy so as to cope with the temporary scheduling of burst traffic.
When the peak power consumption is below the power consumption level 2 and above the power consumption level 1, namely between the power consumption level 1 and the power consumption level 2, and the peak power consumption is below the power consumption level 1, the global power consumption adjustment strategy needs to be set according to the period time. And automatically improving the power consumption global setting in the peak period, and simultaneously providing SSD of burst service response so as to cope with the IO response time of the scheduling level.
Fig. 4 is a schematic drawing showing an alternative storage cluster power consumption processing method according to an embodiment of the present invention, as shown in fig. 4, in order to ensure wear leveling for each SSD, SSDs for processing burst responses are uniformly distributed on all the plurality of distributed storage nodes. SSD3 in node server 1, as selected in FIG. 4, and SSDn2 in node server n are illustrative only.
And monitoring the read-write data quantity of the SSD for burst response, and scheduling and waking up the SSD with the same quantity to accept the burst service requirement when the read-write data quantity reaches a preset trigger threshold value so as to ensure the balance of SSD abrasion of data writing. Fig. 5 is a schematic diagram illustrating a balance of an alternative storage cluster power consumption processing method according to an embodiment of the present invention, as shown in fig. 5, in which SSD3 in node server 1 and SSDn2 in node server n are initially set to operate according to power consumption level 2, and when detecting that the read-write data amount reaches a predetermined trigger threshold, SSD2 in node server 1 and SSDn3 in node server n are determined to be processed as new burst responses, and the original power consumption level 1 is up-regulated to power consumption level 2. Then SSD3 in lower regulation point server 1 and SSDn2 in node server n are operated according to power consumption level 1, in this way, the rotation is in high wear state, ensuring that wear state of SSD is balanced.
In addition, when a service is newly added or changed, the setting of the overall power consumption is triggered. And when the business data volume of the current task is larger than a preset data volume threshold value, the maximum processing capacity is heard by adopting a full-power running mode.
At least the following effects are achieved by the above alternative embodiments: and storing the resource pool and the SSD existing operation monitoring data, establishing a service model for analysis to obtain a service change trend, evaluating the integral capacity of the SSD, and setting a reasonable power consumption level. According to the service characteristics and periodicity, dynamic power consumption setting is supported, and lower power consumption values are set in idle. And combining the redundancy, setting SSD for fast responding to the burst service, effectively solving the problem of blocking and scheduling the burst service, setting a service writing quantity threshold value, reasonably switching SSD, and avoiding unbalance of data writing in a cluster.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
The embodiment also provides a device for processing power consumption of a storage cluster, which is used for implementing the foregoing embodiments and preferred implementations, and is not described in detail. As used below, the terms "module," "apparatus" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
According to an embodiment of the present invention, there is further provided an apparatus embodiment for implementing a storage cluster power consumption processing method, and fig. 6 is a schematic diagram of a storage cluster power consumption processing apparatus according to an embodiment of the present invention, as shown in fig. 6, where the storage cluster power consumption processing apparatus includes: the acquisition module 602, the first determination module 604, and the second determination module 606 are described below.
An obtaining module 602, configured to obtain historical service data amounts respectively corresponding to a plurality of historical time instants and power consumption corresponding to the historical service data amounts, where the plurality of historical time instants are time instants with time sequences in a predetermined historical period;
a first determining module 604, coupled to the obtaining module 602, configured to determine, according to the historical traffic data and power consumption corresponding to the historical traffic data, a peak period, a low peak period, a peak power consumption corresponding to the peak period, and a low peak power consumption corresponding to the low peak period, where the peak period is a period in which the traffic data of the storage cluster in a predetermined operation period is greater than a peak threshold, and the low peak period is a period in which the traffic data of the storage cluster in the predetermined operation period is less than a low peak threshold;
The second determining module 606 is connected to the first determining module 604, and is configured to determine global power consumption of the plurality of memories included in the storage cluster based on the peak power consumption, the low peak power consumption, and power consumption thresholds corresponding to a plurality of preset power consumption levels, respectively.
In the storage cluster power consumption processing device provided by the embodiment of the invention, through the obtaining module 602, the historical service data volume corresponding to each of a plurality of historical moments of the storage cluster and the power consumption corresponding to the historical service data volume are obtained, wherein the plurality of historical moments are moments with time sequences in a preset historical period; a first determining module 604, coupled to the obtaining module 602, configured to determine, according to the historical traffic data and power consumption corresponding to the historical traffic data, a peak period, a low peak period, a peak power consumption corresponding to the peak period, and a low peak power consumption corresponding to the low peak period, where the peak period is a period in which the traffic data of the storage cluster in a predetermined operation period is greater than a peak threshold, and the low peak period is a period in which the traffic data of the storage cluster in the predetermined operation period is less than a low peak threshold; the second determining module 606 is connected to the first determining module 604, and is configured to determine global power consumption of the plurality of memories included in the storage cluster based on the peak power consumption, the low peak power consumption, and power consumption thresholds corresponding to a plurality of preset power consumption levels, respectively. The method achieves the aim of balancing the business data volume and the memory energy consumption, achieves the technical effect of improving the memory power consumption utilization rate, and further solves the technical problem of non-ideal energy saving of the memory clusters in the related technology.
It should be noted that each of the above modules may be implemented by software or hardware, for example, in the latter case, it may be implemented by: the above modules may be located in the same processor; alternatively, the various modules described above may be located in different processors in any combination.
It should be noted that, the above-mentioned obtaining module 602, the first determining module 604, and the second determining module 606 correspond to steps S102 to S106 in the embodiment, and the above-mentioned modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of the above-mentioned embodiments. It should be noted that the above modules may be run in a computer terminal as part of the apparatus.
It should be noted that, the optional or preferred implementation manner of this embodiment may be referred to the related description in the embodiment, and will not be repeated herein.
The storage cluster power consumption processing apparatus may further include a processor and a memory, where the acquisition module 602, the first determination module 604, the second determination module 606, and the like are all stored as program units, and the processor executes the program units stored in the memory to implement corresponding functions.
The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel may be provided with one or more. The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.
The embodiment of the invention provides a nonvolatile storage medium, and a program is stored on the nonvolatile storage medium, and the program is executed by a processor to realize a storage cluster power consumption processing method.
The embodiment of the invention provides an electronic device, which comprises a processor, a memory and a program stored on the memory and capable of running on the processor, wherein the following steps are realized when the processor executes the program: acquiring historical service data volumes respectively corresponding to a plurality of historical moments of a storage cluster and power consumption corresponding to the historical service data volumes, wherein the historical moments are moments with time sequences in a preset historical period; determining a peak time period, a low peak time period, a peak power consumption corresponding to the peak time period and a low peak power consumption corresponding to the low peak time period of the storage cluster according to the historical service data volume and the power consumption corresponding to the historical service data volume, wherein the peak time period is a time period when the service data volume of the storage cluster in a preset operation period is greater than a peak threshold value, and the low peak time period is a time period when the service data volume of the storage cluster in the preset operation period is less than a low peak threshold value; and determining global power consumption of a plurality of memories included in the storage cluster based on the peak power consumption, the low peak power consumption and power consumption thresholds corresponding to a plurality of preset power consumption levels respectively. The device herein may be a server, a PC, etc.
The invention also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with the method steps of: acquiring historical service data volumes respectively corresponding to a plurality of historical moments of a storage cluster and power consumption corresponding to the historical service data volumes, wherein the historical moments are moments with time sequences in a preset historical period; determining a peak time period, a low peak time period, a peak power consumption corresponding to the peak time period and a low peak power consumption corresponding to the low peak time period of the storage cluster according to the historical service data volume and the power consumption corresponding to the historical service data volume, wherein the peak time period is a time period when the service data volume of the storage cluster in a preset operation period is greater than a peak threshold value, and the low peak time period is a time period when the service data volume of the storage cluster in the preset operation period is less than a low peak threshold value; and determining global power consumption of a plurality of memories included in the storage cluster based on the peak power consumption, the low peak power consumption and power consumption thresholds corresponding to a plurality of preset power consumption levels respectively.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present invention and is not intended to limit the present invention. Various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are to be included in the scope of the claims of the present invention.
Claims (13)
1. A storage cluster power consumption processing method, comprising:
acquiring historical service data volumes respectively corresponding to a plurality of historical moments of a storage cluster and power consumption corresponding to the historical service data volumes, wherein the historical moments are moments with time sequences in a preset historical period;
determining a peak time period, a low peak time period, a peak power consumption corresponding to the peak time period and a low peak power consumption corresponding to the low peak time period of the storage cluster according to the historical service data volume and the power consumption corresponding to the historical service data volume, wherein the peak time period is a time period when the service data volume of the storage cluster in a preset operation period is greater than a peak threshold value, and the low peak time period is a time period when the service data volume of the storage cluster in the preset operation period is less than a low peak threshold value;
determining global power consumption of a plurality of memories included in the storage cluster based on the peak power consumption, the low peak power consumption and power consumption thresholds corresponding to a plurality of preset power consumption levels respectively;
the determining global power consumption of the memories included in the storage cluster based on the peak power consumption, the low peak power consumption and power consumption thresholds corresponding to the preset power consumption levels respectively includes: determining a first level of the plurality of power consumption levels, wherein the power consumption threshold is smaller than a preset first threshold; taking the preset first power consumption as the global power consumption under the condition that the peak power consumption is smaller than the power consumption threshold corresponding to the first level;
The method further comprises the steps of: determining a first number of first memories for burst response in the plurality of memories, and a second number of second memories other than the first number of first memories, wherein the first number is less than the second number; setting the second number of second memories with the global power consumption; and setting the first number of first memories by adopting preset third power consumption, wherein the third power consumption is larger than the global power consumption.
2. The method of claim 1, wherein determining peak hours, low peak hours, peak power consumption corresponding to the peak hours, and low peak power consumption corresponding to the low peak hours of the storage cluster based on the historical traffic data volume and power consumption corresponding to the historical traffic data volume comprises:
determining the service type of the current service of the storage cluster, and determining the corresponding power consumption of the storage cluster for processing the first service with the same service type in the power consumption corresponding to the historical service data volume;
and determining the peak time, the low peak time, the peak power consumption and the low peak power consumption based on the power consumption corresponding to the first service.
3. The method according to claim 2, wherein the method further comprises:
and determining a target grade range corresponding to the service type and target grades included in the target grade range in the multiple power consumption grades based on the power consumption corresponding to the first service.
4. The method of claim 3, wherein the determining, based on the power consumption corresponding to the first service, a target class range corresponding to the service type among the plurality of power consumption classes, and a target class included in the target class range, comprises:
determining target service capacity required for processing the current service;
determining the required power consumption corresponding to the target service capacity based on the power consumption corresponding to the first service;
and determining the target grade range and the target grade based on the required power consumption corresponding to the target service capability.
5. The method of claim 1, wherein determining global power consumption of a plurality of memories included in the storage cluster based on the peak power consumption, the low peak power consumption, and power consumption thresholds respectively corresponding to a plurality of preset power consumption levels comprises:
Determining a second level of the power consumption levels, wherein the power consumption threshold value of the second level is larger than a preset second threshold value, and the power consumption threshold value corresponding to the first level is smaller than the power consumption threshold value corresponding to the second level;
and determining a global power consumption adjustment strategy based on the peak time when the peak power consumption is greater than the power consumption threshold corresponding to the second level and the low peak power consumption is less than the power consumption threshold corresponding to the first level.
6. The method of claim 1, wherein the determining a global power consumption adjustment policy based on the peak hours comprises:
taking the first power consumption as the global power consumption without entering the peak time;
and under the condition of entering the peak time, adopting a preset second power consumption to regulate the global power consumption to obtain regulated global power consumption, wherein the second power consumption is larger than the first power consumption.
7. The method according to claim 1, wherein the method further comprises:
selecting the first number of second memories from the second number of second memories in case the storage cluster triggers a wear leveling process;
The third power consumption is adopted to adjust the global power consumption corresponding to the first number of second memories respectively, so that the adjusted first number of second memories are obtained;
and adjusting the third power consumption corresponding to the first quantity of first memories respectively by adopting the global power consumption to obtain the adjusted first quantity of first memories.
8. The method of claim 7, wherein the method further comprises:
detecting the read-write data quantity corresponding to the first memories of the first quantity respectively;
and triggering the storage cluster to carry out wear balance processing under the condition that the read-write data quantity corresponding to any one of the first memories is larger than a preset trigger threshold value.
9. The method of claim 1, wherein the storage cluster is comprised of a plurality of distributed storage nodes, each of the plurality of distributed storage nodes including a predetermined amount of memory, the first amount of memory being evenly distributed among the plurality of distributed storage nodes.
10. The method according to any one of claims 1 to 6, further comprising:
And under the condition that the service data volume of the current task of the storage cluster is larger than a preset data volume threshold, the storage cluster adopts a full-power-consumption operation mode, wherein the full-power-consumption operation mode is the maximum processing capacity of the storage cluster.
11. A storage cluster power consumption processing apparatus, comprising:
the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring historical service data volumes respectively corresponding to a plurality of historical moments of a storage cluster and power consumption corresponding to the historical service data volumes, and the plurality of historical moments are moments with time sequences in a preset historical period;
a first determining module, configured to determine, according to the historical traffic data and power consumption corresponding to the historical traffic data, a peak period, a low peak period, a peak power consumption corresponding to the peak period, and a low peak power consumption corresponding to the low peak period, where the peak period is a period in which the traffic data of the storage cluster in a predetermined operation period is greater than a peak threshold, and the low peak period is a period in which the traffic data of the storage cluster in the predetermined operation period is less than a low peak threshold;
The second determining module is used for determining global power consumption of a plurality of memories included in the storage cluster based on the peak power consumption, the low peak power consumption and power consumption thresholds respectively corresponding to a plurality of preset power consumption levels;
the second determining module is further configured to determine a first level, among the multiple power consumption levels, of which a power consumption threshold is smaller than a preset first threshold; taking the preset first power consumption as the global power consumption under the condition that the peak power consumption is smaller than the power consumption threshold corresponding to the first level;
the second determining module is further configured to determine a first number of first memories for burst response in the plurality of memories, and a second number of second memories other than the first number of first memories, where the first number is smaller than the second number; setting the second number of second memories with the global power consumption; and setting the first number of first memories by adopting preset third power consumption, wherein the third power consumption is larger than the global power consumption.
12. A non-volatile storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the storage cluster power consumption processing method of any one of claims 1 to 10.
13. An electronic device, comprising: one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the storage cluster power consumption processing method of any of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310382634.7A CN116107518B (en) | 2023-04-11 | 2023-04-11 | Storage cluster power consumption processing method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310382634.7A CN116107518B (en) | 2023-04-11 | 2023-04-11 | Storage cluster power consumption processing method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116107518A CN116107518A (en) | 2023-05-12 |
| CN116107518B true CN116107518B (en) | 2023-07-14 |
Family
ID=86256519
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310382634.7A Active CN116107518B (en) | 2023-04-11 | 2023-04-11 | Storage cluster power consumption processing method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116107518B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5529114B2 (en) * | 2008-04-21 | 2014-06-25 | アダプティブ コンピューティング エンタープライジズ インク | System and method for managing energy consumption in a computing environment |
| US10169104B2 (en) * | 2014-11-19 | 2019-01-01 | International Business Machines Corporation | Virtual computing power management |
| CN110515539B (en) * | 2019-07-22 | 2022-05-17 | 平安科技（深圳）有限公司 | Cloud disk mounting method, device, equipment and storage medium based on cloud storage |
| CN114488972A (en) * | 2021-12-28 | 2022-05-13 | 武汉乾能皓源科技有限公司 | Off-peak production scheduling method based on energy consumption data production line |
| CN115759480A (en) * | 2022-12-19 | 2023-03-07 | 武汉理工大学 | Multistage energy storage type port operation interaction method, device, equipment and medium |
-
2023
- 2023-04-11 CN CN202310382634.7A patent/CN116107518B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN116107518A (en) | 2023-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7739388B2 (en) | Method and system for managing data center power usage based on service commitments | |
| US8065541B2 (en) | Server power consumption controller, and method and computer program for controlling server power consumption | |
| US20100138677A1 (en) | Optimization of data distribution and power consumption in a data center | |
| CN110196767B (en) | Service resource control method, device, equipment and storage medium | |
| CN111818159B (en) | Management method, device, equipment and storage medium of data processing node | |
| US9823875B2 (en) | Transparent hybrid data storage | |
| US20080184230A1 (en) | Systems and methods for determining power consumption profiles for resource users and using the profiles for resource allocation | |
| US11188261B2 (en) | Memory controllers for solid-state storage devices | |
| CN110096350B (en) | Cold and hot area division energy-saving storage method based on cluster node load state prediction | |
| US20150317556A1 (en) | Adaptive quick response controlling system for software defined storage system for improving performance parameter | |
| US11734183B2 (en) | Method and apparatus for controlling data flow in storage device, storage device, and storage medium | |
| Hanson et al. | What computer architects need to know about memory throttling | |
| US20230125240A1 (en) | Storage System and Energy-Saving Control Method | |
| CN110737717A (en) | database migration method and device | |
| CN116107518B (en) | Storage cluster power consumption processing method and device, storage medium and electronic equipment | |
| CN111506425B (en) | Method and device for processing quality of service data | |
| CN102063263B (en) | Method, device and system for responding read-write operation request of host computer by solid state disk | |
| CN101776946B (en) | Method for controlling power consumption on basis of object-based storage system | |
| CN109831391B (en) | Flow control method, storage device and system in distributed storage system | |
| CN110806918A (en) | Virtual machine operation method and device based on deep learning neural network | |
| CN113805812B (en) | Cache management method, device, equipment and storage medium | |
| CN114205232A (en) | Interface service platform capable of automatically expanding capacity | |
| US11507427B2 (en) | Application program management method and apparatus | |
| Makrani | Storage and Memory Characterization of Data Intensive Workloads for Bare Metal Cloud | |
| KR101655832B1 (en) | Data pre-load management method and terminal device thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |