CN109086009A - A kind of method for managing and monitoring and device, computer readable storage medium - Google Patents
A kind of method for managing and monitoring and device, computer readable storage medium Download PDFInfo
- Publication number
- CN109086009A CN109086009A CN201810879817.9A CN201810879817A CN109086009A CN 109086009 A CN109086009 A CN 109086009A CN 201810879817 A CN201810879817 A CN 201810879817A CN 109086009 A CN109086009 A CN 109086009A
- Authority
- CN
- China
- Prior art keywords
- storage equipment
- storage
- equipment
- performance evaluation
- evaluation score
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F3/0653—Monitoring storage devices or 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
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0614—Improving the reliability of storage systems
- G06F3/0616—Improving the reliability of storage systems in relation to life time, e.g. increasing Mean Time Between Failures [MTBF]
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)
- Debugging And Monitoring (AREA)
Abstract
This application discloses a kind of method for managing and monitoring and device, computer readable storage medium, which comprises obtains one or more monitor control index data of all storage equipment in storage cluster;According to the monitor control index data of all storage equipment of acquisition, the comprehensive performance evaluation score of each storage equipment is calculated;Storage strategy is adjusted according to the comprehensive performance evaluation score of each storage equipment.The application passes through the monitor control index data according to all storage equipment; calculate the comprehensive performance evaluation score of each storage equipment; and correspondingly adjust storage strategy; the service life aging and corrupted for reducing storage equipment are endangered and are influenced caused by entire storage cluster, preferably protect the data of entire storage cluster.
Description
Technical field
The present invention relates to storage equipment technical field more particularly to a kind of method for managing and monitoring and devices, computer-readable
Storage medium.
Background technique
With the arrival of information age, computer application is more and more wider, in the storing process of computerized information, to depositing
The requirement for storing up equipment is also higher and higher.It is currently stored neck that software definition, which stores (Software Defined Storage, SDS),
The hot spot technology in domain, in SDS, the relevant control work of all storages is all only at the external software relative to physical store hardware
In.
SDS has planned how to store and access data, but it does not account for the storage service life aging of equipment and bad
Damage harm and influence caused by entire storage cluster.According to wooden pail effect, in single or several storage equipment due to bad
After damage generates read-write slowly, since the single of the corrupted or several storage equipment more or less all share the one of entire cluster
Part read-write requests, this part read-write requests are not completed, and entire read-write operation just be can not be completed, and therefore, cause entire cluster
The response of part read-write requests it is slow.
Summary of the invention
The embodiment of the invention provides a kind of method for managing and monitoring and device, computer readable storage medium, can reduce
The service life aging and corrupted for storing equipment are endangered and are influenced caused by entire storage cluster.
In order to reach the object of the invention, the technical solution of the embodiment of the present invention is achieved in that
The embodiment of the invention provides a kind of method for managing and monitoring, comprising:
Obtain one or more monitor control index data of all storage equipment in storage cluster;
According to the monitor control index data of all storage equipment of acquisition, the comprehensive performance evaluation of each storage equipment is calculated
Score;
Storage strategy is adjusted according to the comprehensive performance evaluation score of each storage equipment.
In the present embodiment, the monitor control index data include at least one of:
Store equipment read rate, storage equipment writing speed, the storage equipment number IOPS per second being written and read, storage
Equipment single read-write operation average latency, capacity of memory device are write using percentage, application layer read latency time, application layer
Delay time.
In the present embodiment, the monitor control index data of all storage equipment according to acquisition calculate each storage and set
Standby comprehensive performance evaluation score, comprising:
To each monitor control index data, the arithmetic average of all storage equipment in the storage cluster is calculated;
According to the arithmetic average of calculated every monitor control index data, the reference base of every monitor control index data is set
Number, and according to the score value for calculating each storage equipment items monitor control index data with reference to radix;
According to the score value of each storage equipment items monitor control index data, the comprehensive performance evaluation point of each storage equipment is calculated
Number.
In the present embodiment, the comprehensive performance evaluation score according to each storage equipment adjusts storage strategy, comprising:
According to the comprehensive performance evaluation score of each storage equipment, the average behavior for calculating all storage equipment is commented
Valence score;
The average behavior evaluation score for comparing all storage equipment is commented divided by the comprehensive performance of each storage equipment
The size of the ratio of valence score and preset adjustment weight threshold;
When the ratio of the storage equipment is greater than or equal to the adjustment weight threshold, the storage is reduced
The read-write probability of equipment.
In the present embodiment, when the ratio of the storage equipment is greater than or equal to the adjustment weight threshold, institute
It states and storage strategy is adjusted according to the comprehensive performance evaluation score of each storage equipment, further includes:
It is counted since current time in preset first confirmation phase duration, often presets all storages of unit time
The average behavior evaluation score of equipment is greater than or equal to institute divided by the ratio for the comprehensive performance evaluation score for storing equipment described in this
State the number of adjustment weight threshold;
When the number counted is greater than or equal to preset first frequency threshold value, triggering reduces the storage equipment
Read and write the operation of probability.
In the present embodiment, the comprehensive performance evaluation score according to each storage equipment adjusts storage strategy, comprising:
According to the comprehensive performance evaluation score of each storage equipment, the average behavior for calculating all storage equipment is commented
Valence score;
The average behavior evaluation score for comparing all storage equipment is commented divided by the comprehensive performance of each storage equipment
The size of the ratio of valence score and preset migrating data threshold value;
When the ratio of the storage equipment is greater than or equal to the migrating data threshold value, the storage is migrated
The data of equipment storage.
In the present embodiment, when the ratio of the storage equipment is greater than or equal to the migrating data threshold value, institute
It states and storage strategy is adjusted according to the comprehensive performance evaluation score of each storage equipment, further includes:
It is counted since current time in preset second confirmation phase duration, often presets all storages of unit time
The average behavior evaluation score of equipment is greater than or equal to institute divided by the ratio for the comprehensive performance evaluation score for storing equipment described in this
State the number of migrating data threshold value;
When the number counted is greater than or equal to preset second frequency threshold value, triggering migrates the storage equipment and deposits
The operation of the data of storage.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage
Have one or more program, one or more of programs can be executed by one or more processor, with realize such as with
The step of upper described in any item method for managing and monitoring.
The embodiment of the invention also provides a kind of monitoring management apparatus, including processor and memory, in which:
The processor is for executing the monitor supervisor stored in memory, to realize as described in any of the above item
The step of method for managing and monitoring.
The embodiment of the invention also provides a kind of monitoring management apparatus, including data acquisition module, computing module and adjustment
Module, in which:
Data acquisition module, for obtaining one or more monitor control index data of all storage equipment in storage cluster;
Computing module calculates each storage equipment for all monitor control index data for storing equipment according to acquisition
Comprehensive performance evaluation score;
Module is adjusted, for adjusting storage strategy according to the comprehensive performance evaluation score of each storage equipment.
The technical solution of the embodiment of the present invention, has the following beneficial effects:
Method for managing and monitoring and device provided in an embodiment of the present invention, computer readable storage medium, by according to all
The monitor control index data of equipment are stored, the comprehensive performance evaluation score of each storage equipment is calculated, and correspondingly adjust storage strategy,
The service life aging and corrupted for reducing storage equipment are endangered and are influenced caused by entire storage cluster, are preferably protected whole
The data of a storage cluster.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is a kind of flow diagram of method for managing and monitoring of the embodiment of the present invention;
Fig. 2 is a kind of structural schematic diagram of monitoring management apparatus of the embodiment of the present invention;
Fig. 3 is the structural schematic diagram of another monitoring management apparatus of the embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention
Embodiment be described in detail.It should be noted that in the absence of conflict, in the embodiment and embodiment in the application
Feature can mutual any combination.
As shown in Figure 1, a kind of method for managing and monitoring according to the present invention, includes the following steps:
Step 101: obtaining one or more monitor control index data of all storage equipment in storage cluster;
In the present embodiment, the monitor control index data include at least one of:
Store equipment read rate, storage equipment writing speed, the storage equipment number (Input/ per second being written and read
Output Operations Per Second, IOPS), the storage single read-write operation of equipment (Input/Output, IO) it is average
Waiting time, capacity of memory device use percentage, application layer read latency time, application layer write delay time.
It should be noted that the IOPS performance of storage equipment refers to what storage equipment acceptable how many times host per second issued
Access, an IO of host need repeatedly access storage that can just complete.For example, a smallest data block is written in host,
It will be by three steps such as " send write request, write-in data, receive write-in confirmation ", that is, 3 storage end access.
It is to indicate the handling capacity of storage equipment that equipment read rate, which is stored, plus storage equipment writing speed, and throughput value is bigger,
Storage device performance is better.Storage IO PS value is higher, and the read and write rate for indicating storage equipment is faster.Store the single IO of equipment
Average latency is longer, indicates that storage equipment is busier, it is also longer to fail delay caused by handling in time.In certain applications
Have to the read-write delay judgement on storage equipment, i.e. application layer read latency time and application layer write delay time, these data
It is also more lower better.
In the present embodiment, the storage equipment includes the storage equipment such as hard disk, USB flash disk.
Step 102: according to the monitor control index data of all storage equipment of acquisition, calculating the synthesis of each storage equipment
Performance evaluation score;
In the present embodiment, the monitor control index data of all storage equipment according to acquisition calculate each storage and set
Standby comprehensive performance evaluation score, comprising:
To each monitor control index data, the arithmetic average of all storage equipment in the storage cluster is calculated;
According to the arithmetic average of calculated every monitor control index data, the reference base of every monitor control index data is set
Number, and according to the score value for calculating each storage equipment items monitor control index data with reference to radix;
According to the score value of each storage equipment items monitor control index data, the comprehensive performance evaluation point of each storage equipment is calculated
Number.
It should be noted that the arithmetic average of calculated every monitor control index data can be directly disposed as each
The reference radix of item monitor control index data, the reference radix of every monitor control index data can also be set as calculating with described
Every monitor control index data arithmetic average be independent variable functional value, the present invention is to this and with no restrictions.In addition, step
102 can also calculate the comprehensive performance evaluation score of each storage equipment by other methods, for example, to each monitor control index number
According to, the arithmetic average of all storage equipment in the storage cluster is not calculated, it is directly each with reference to radix calculating according to preset
Then the score value for storing equipment items monitor control index data calculates the comprehensive performance evaluation score of each storage equipment.But pass through
The arithmetic average for calculating all storage equipment in the storage cluster, can more dynamically obtain institute in entire storage cluster
There is the behavior pattern of storage equipment, so that the adjustment of storage strategy is more flexibly effective.
It is described to calculate each storage equipment items monitor control index number with reference to radix according to described in an example of the present embodiment
According to score value, comprising:
According to the reference radix of a monitor control index data, a reference value of the monitor control index data is calculated, wherein a reference value=
With reference to radix/X, X is that (such as in calculating process below, X value is 0.7 to preset ratio value, can also be in practical application
Take other values);
According to the current monitor achievement data value of calculated a reference value and each storage equipment, being somebody's turn to do for each storage equipment is calculated
The score value of monitor control index data: the score value=current monitor achievement data value/a reference value.
Illustratively, by taking the IOPS value for storing equipment as an example, it is assumed that the IOPS value of a hard disk is 120, and all hard disks are put down
Equal IOPS value IOPSIt is average=135, i.e. IOPS are 135 with reference to radix, then a reference value of IOPS are set to 135/0.7=192.86,
Therefore, the score value of the IOPS of the hard disk are as follows: 120/192.86=0.62 points.
The calculation method of score value of calculation method and IOPS of the score value of all other monitor control index data is similar, needs to infuse
Meaning can be with separate computations in the score value of the score value and storage equipment writing speed that calculate storage equipment read rate, can also be with
Calculate the score value of sum of the two (storing the handling capacity of equipment);When calculating application layer read latency time, application layer write delay
Between score value when, equally can with separate computations, can also calculate sum of the two (i.e. storage equipment quantization delay) score value.
The score value of separate computations storage equipment read rate and the score value of storage equipment writing speed are as follows:
Assuming that the read rate readRate=220MB/s of the hard disk, the average read rate readRate of all hard disksIt is average=
200MB/s, i.e. read rate are 200MB/s with reference to radix, then a reference value of read rate are set to 200/0.7=285.71MB/s,
Therefore, the score value of the read rate of the hard disk are as follows: 220/285.71=0.77 points.
Assuming that the writing speed writeRate=75MB/s of the hard disk, the average writing speed writeRate of all hard disksIt is average=
80MB/s, i.e. writing speed are 80MB/s with reference to radix, then a reference value of writing speed are set to 80/0.7=114.29MB/s, because
This, the score value of the writing speed of the hard disk are as follows: 75/114.29=0.66 points.
Assuming that the application program read latency appReadWait=50ms of the hard disk, the average application program of all hard disks is read
Postpone appReadWaitIt is average=45ms, i.e. the reference radix of application program read latency are 45ms, then by application program read latency
A reference value is set to 45/0.7=64.29ms, therefore, the score value of the application program read latency of the hard disk are as follows: 50/64.29=0.78
Point.
Assuming that the application program write delay appWriteWait=80ms of the hard disk, the average application program of all hard disks are write
Postpone appWriteWaitIt is average=70ms, i.e. the reference radix of application program write delay are 70ms, then by application program write delay
A reference value be set to 70/0.7=100ms, therefore, the score value of the application program write delay of the hard disk are as follows: 80/100=0.8 point.
Assuming that the capacity of the hard disk is 0.9 point using the score value of percentage, the score value of single IO average latency is
0.88 point, then the comprehensive performance evaluation score of the hard disk can be calculated according to the following formula:
In another example, storage equipment read rate and storage equipment writing speed are calculated altogether, that is, calculates storage and sets
The score value of standby handling capacity is as follows:
Still by taking the read rate of above-mentioned hard disk and writing speed as an example, the handling capacity Throu=220+75=295MB/ of the hard disk
S, the average throughput Throu of all hard disksIt is average=200+80=280MB/s, i.e. the reference radix of handling capacity are 280MB/s, then
The a reference value of handling capacity is set to 280/0.7=400MB/s, therefore, the score value of the handling capacity of the hard disk are as follows: 295/400=
0.74 point.
Application layer read latency time, application layer write delay time are calculated altogether, that is, calculate the application journey of storage equipment
The score value of the quantization delay of sequence is as follows:
Still by taking the application program read latency of above-mentioned hard disk and application program write delay as an example, the application program of the hard disk quantifies
Postpone appWait=50+80=130ms, the average application program quantization delay appWait of all hard disksIt is average=45+70=
The reference radix of 115ms, i.e. application program quantization delay is 115ms, then a reference value by application program quantization delay is set to
115/0.7=164.3ms, therefore, the score value of the application program quantization delay of the hard disk are as follows: 130/164.3=0.79 points.
For score value and the score value of single IO average latency still by the capacity of above-mentioned hard disk using percentage, then may be used
To calculate the comprehensive performance evaluation score of the hard disk according to the following formula:
In calculating process, the function and variable declaration used are as shown in table 1:
Table 1
It should be noted that two formula mentioned above are two example formulas of the invention, specifically calculating
In the process, other calculation formula also can be used, if the comprehensive performance evaluation score of final calculated hard disk with
The variation of one or more of readRate, writeRate, IOPS value three be in positive change, with UsedPer,
The variation of one or more of perIOwait, appReadWait, appWriteWait are in inverse change.
To the quantizing rule explanation of quantization function Quant (value, base):
For a certain monitor control index data, first calculate the arithmetic mean of instantaneous values of all storage equipment, with it is calculated count it is flat
Mean value, which is used as, refers to radix, calculates a reference value of the monitor control index data, and a reference value is with reference to radix/preset ratio value, so
Afterwards according to a reference value by the monitor control index data value of each hard disk, quantization is mapped in [0, base] this section, and upper limit value is
Base, lower limit value 0.
Step 103: storage strategy is adjusted according to the comprehensive performance evaluation score of each storage equipment.
In an example of the present embodiment, the comprehensive performance evaluation score adjustment storage plan according to each storage equipment
Slightly, comprising:
According to the comprehensive performance evaluation score of each storage equipment, the average behavior for calculating all storage equipment is commented
Valence score;
The average behavior evaluation score for comparing all storage equipment is commented divided by the comprehensive performance of each storage equipment
The size of the ratio of valence score and preset adjustment weight threshold;
When the ratio of the storage equipment is greater than or equal to the adjustment weight threshold, the storage is reduced
The read-write probability of equipment.
It specifically, can be by concluding the storage equipment to cold data memory block, to reduce the storage equipment
Read-write probability.
For example, it is assumed that preset adjustment weight threshold is 200%, it is assumed that the score score of suspicious hard disk is 20 points, is owned
Hard disk is equally divided into 50 points, then the ratio is 50/20=250%, when having reached adjustment weight threshold, then this is suspicious hard
Disk is concluded to cold data memory block, and notifies administrator.Notice form can be the diversified forms such as wechat, QQ, mailbox, short message.
When notifying administrator, moreover it is possible to support prompting function, such as every five minutes notices can be set once, administrator is needed to respond one
Reply can be just terminated after confirmation message.
In this example, when the ratio of the storage equipment is greater than or equal to the adjustment weight threshold, institute
It states and storage strategy is adjusted according to the comprehensive performance evaluation score of each storage equipment, further includes:
It is counted since current time in preset first confirmation phase duration, often presets all storages of unit time
The average behavior evaluation score of equipment is greater than or equal to institute divided by the ratio for the comprehensive performance evaluation score for storing equipment described in this
State the number of adjustment weight threshold;
When the number counted is greater than or equal to preset first frequency threshold value, triggering reduces the storage equipment
Read and write the operation of probability.
For example, setting the first confirmation phase duration to 100 minutes, presetting unit time is 1 minute, is calculated from for the first time
Ratio be more than that adjustment weight threshold starts to be counted, if calculated ratio per minute is super in continuous 100 minutes
The number for crossing the adjustment weight threshold reaches 90 times or more, then reduces the read-write probability of the storage equipment.
In another example of the present embodiment, the comprehensive performance evaluation score adjustment storage plan according to each storage equipment
Slightly, comprising:
According to the comprehensive performance evaluation score of each storage equipment, the average behavior for calculating all storage equipment is commented
Valence score;
The average behavior evaluation score for comparing all storage equipment is commented divided by the comprehensive performance of each storage equipment
The size of the ratio of valence score and preset migrating data threshold value;
When the ratio of the storage equipment is greater than or equal to the migrating data threshold value, the storage is migrated
The data of equipment storage.
For example, preset migrating data threshold value is 400%, still by taking the suspicious hard disk of front as an example, the ratio is 50/
20=250% does not reach migrating data threshold value, then does not have to migrate the suspicious hard disk data above on other hard disks;It is false
If the score score of another suspicious hard disk is 10 points, the average mark of all hard disks is still 50 points, then the ratio is 50/10=
500%, reach migrating data threshold value, has then migrated another suspicious hard disk data above on other hard disks, and notify to manage
Reason person.
In this example, when the ratio of the storage equipment is greater than or equal to the migrating data threshold value, institute
It states and storage strategy is adjusted according to the comprehensive performance evaluation score of each storage equipment, further includes:
It is counted since current time in preset second confirmation phase duration, often presets all storages of unit time
The average behavior evaluation score of equipment is greater than or equal to institute divided by the ratio for the comprehensive performance evaluation score for storing equipment described in this
State the number of migrating data threshold value;
When the number counted is greater than or equal to preset second frequency threshold value, triggering migrates the storage equipment and deposits
The operation of the data of storage.
For example, setting the second confirmation phase duration to 50 minutes, presetting unit time is 1 minute, is calculated from for the first time
Ratio be more than that migrating data threshold value starts to be counted, if calculated ratio per minute is super in continuous 50 minutes
The number for crossing the migrating data threshold value reaches 40 times or more, then migrates the data of the storage equipment storage.
It should be noted that adjustment weight threshold is less than migrating data threshold value, it is each to store the calculated ratio of equipment
Size indicate its maximum portative data volume size, ratio is smaller, and portative data volume is smaller.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage
Have one or more program, one or more of programs can be executed by one or more processor, with realize such as with
The step of upper described in any item method for managing and monitoring.
As shown in Fig. 2, the embodiment of the invention also provides a kind of monitoring management apparatus, including processor 201 and memory
202, in which:
The processor 201 is for executing the monitor supervisor stored in memory 202, to realize such as any of the above item
The step of described method for managing and monitoring.
As shown in figure 3, the embodiment of the invention also provides a kind of monitoring management apparatus, including data acquisition module 301, meter
Calculate module 302 and adjustment module, in which:
Data acquisition module 301, for obtaining one or more monitor control index numbers of all storage equipment in storage cluster
According to;
Computing module 302 calculates each storage and sets for all monitor control index data for storing equipment according to acquisition
Standby comprehensive performance evaluation score;
Module 303 is adjusted, for adjusting storage strategy according to the comprehensive performance evaluation score of each storage equipment.
In the present embodiment, the monitor control index data include at least one of:
When storing equipment read rate, storage equipment writing speed, storage IO PS, the storage single IO average waiting of equipment
Between, capacity of memory device use percentage, application layer read latency time, application layer write delay time.
In the present embodiment, the storage equipment includes the storage equipment such as hard disk, USB flash disk.
In the present embodiment, the computing module 302 is specifically used for:
To each monitor control index data, the arithmetic average of all storage equipment in the storage cluster is calculated;
According to the arithmetic average of calculated every monitor control index data, the reference base of every monitor control index data is set
Number, and according to the score value for calculating each storage equipment items monitor control index data with reference to radix;
According to the score value of each storage equipment items monitor control index data, the comprehensive performance evaluation point of each storage equipment is calculated
Number.
It should be noted that the computing module 302 can be by the arithmetic mean of calculated every monitor control index data
Value, is directly disposed as the reference radix of every monitor control index data, the reference radix of every monitor control index data can also be set
Be set to using the arithmetic average of calculated every monitor control index data as the functional value of independent variable, the present invention to this not
It is limited.In addition, the computing module 302 can also calculate the comprehensive performance evaluation point of each storage equipment by other methods
Number, for example, not calculating the arithmetic average of all storage equipment in the storage cluster, directly to each monitor control index data
According to the preset score value for calculating each storage equipment items monitor control index data with reference to radix, the comprehensive of each storage equipment is then calculated
Close performance evaluation score.But the arithmetic average by calculating all storage equipment in the storage cluster, it can more move
The behavior pattern of all storage equipment in entire storage cluster is obtained to state, so that the adjustment of storage strategy is more flexibly
Effectively.
In an example of the present embodiment, the computing module 302 calculates each storage equipment with reference to radix according to described
The score value of every monitor control index data, comprising:
According to the reference radix of a monitor control index data, a reference value of the monitor control index data is calculated, wherein a reference value=
With reference to radix/X, X is preset ratio value (such as X=0.7);
According to the current monitor achievement data value of calculated a reference value and each storage equipment, being somebody's turn to do for each storage equipment is calculated
The score value of monitor control index data: the score value=current monitor achievement data value/a reference value.
Specifically calculating process can be found in example above, and details are not described herein again.In specific calculating process, it can make
With two example formulas of the invention, other calculation formula also can be used, as long as final calculated hard disk is comprehensive
Can one or more of evaluation score and readRate, writeRate, IOPS value three variation in positive change, with
The variation of one or more of UsedPer, perIOwait, appReadWait, appWriteWait are in inverse change
?.
In an example of the present embodiment, the adjustment module 303 is specifically used for:
According to the comprehensive performance evaluation score of each storage equipment, the average behavior for calculating all storage equipment is commented
Valence score;
The average behavior evaluation score for comparing all storage equipment is commented divided by the comprehensive performance of each storage equipment
The size of the ratio of valence score and preset adjustment weight threshold;
When the ratio of the storage equipment is greater than or equal to the adjustment weight threshold, the storage is reduced
The read-write probability of equipment.
Specifically, the adjustment module 303 can be by concluding the storage equipment to cold data memory block, to reduce
The read-write probability of the storage equipment.
In this example, when the ratio of the storage equipment is greater than or equal to the adjustment weight threshold, institute
Adjustment module 303 is stated to be also used to:
It is counted since current time in preset first confirmation phase duration, often presets all storages of unit time
The average behavior evaluation score of equipment is greater than or equal to institute divided by the ratio for the comprehensive performance evaluation score for storing equipment described in this
State the number of adjustment weight threshold;
When the number counted is greater than or equal to preset first frequency threshold value, triggering reduces the storage equipment
Read and write the operation of probability.
In another example of the present embodiment, the adjustment module 303 is specifically used for:
According to the comprehensive performance evaluation score of each storage equipment, the average behavior for calculating all storage equipment is commented
Valence score;
The average behavior evaluation score for comparing all storage equipment is commented divided by the comprehensive performance of each storage equipment
The size of the ratio of valence score and preset migrating data threshold value;
When the ratio of the storage equipment is greater than or equal to the migrating data threshold value, the storage is migrated
The data of equipment storage.
In this example, when the ratio of the storage equipment is greater than or equal to the migrating data threshold value, institute
Adjustment module 303 is stated to be also used to:
It is counted since current time in preset second confirmation phase duration, often presets all storages of unit time
The average behavior evaluation score of equipment is greater than or equal to institute divided by the ratio for the comprehensive performance evaluation score for storing equipment described in this
State the number of migrating data threshold value;
When the number counted is greater than or equal to preset second frequency threshold value, triggering migrates the storage equipment and deposits
The operation of the data of storage.
It should be noted that adjustment weight threshold is less than migrating data threshold value, it is each to store the calculated ratio of equipment
Size indicate its maximum portative data volume size, ratio is smaller, and portative data volume is smaller.
Method for managing and monitoring and device provided in an embodiment of the present invention, computer readable storage medium, by according to all
The monitor control index data of equipment are stored, the comprehensive performance evaluation score of each storage equipment is calculated, and correspondingly adjust storage strategy,
Reduce bring in hard disk ageing process and reads and writes the slowly influence caused by storage cluster.Also reduce hard disk aging bring
Storage failure is endangered and is influenced caused by entire storage cluster, preferably protects the data of entire storage cluster.
Those of ordinary skill in the art will appreciate that all or part of the steps in the above method can be instructed by program
Related hardware is completed, and described program can store in computer readable storage medium, such as read-only memory, disk or CD
Deng.Optionally, one or more integrated circuits also can be used to realize, accordingly in all or part of the steps of above-described embodiment
Ground, each module/unit in above-described embodiment can take the form of hardware realization, can also use the shape of software function module
Formula is realized.The present invention is not limited to the combinations of the hardware and software of any particular form.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of method for managing and monitoring characterized by comprising
Obtain one or more monitor control index data of all storage equipment in storage cluster;
According to the monitor control index data of all storage equipment of acquisition, the comprehensive performance evaluation point of each storage equipment is calculated
Number;
Storage strategy is adjusted according to the comprehensive performance evaluation score of each storage equipment.
2. the method according to claim 1, wherein the monitor control index data include at least one of:
Store equipment read rate, storage equipment writing speed, the storage equipment number IOPS per second being written and read, storage equipment
Single read-write operation average latency, capacity of memory device use percentage, application layer read latency time, application layer write delay
Time.
3. the method according to claim 1, wherein the monitoring of all storage equipment according to acquisition
Achievement data calculates the comprehensive performance evaluation score of each storage equipment, comprising:
To each monitor control index data, the arithmetic average of all storage equipment in the storage cluster is calculated;
According to the arithmetic average of calculated every monitor control index data, the reference radix of every monitor control index data is set,
And according to the score value for calculating each storage equipment items monitor control index data with reference to radix;
According to the score value of each storage equipment items monitor control index data, the comprehensive performance evaluation score of each storage equipment is calculated.
4. the method according to claim 1, wherein the comprehensive performance evaluation score according to each storage equipment
Adjust storage strategy, comprising:
According to the comprehensive performance evaluation score of each storage equipment, the average behavior evaluation point of all storage equipment is calculated
Number;
Compare the average behavior evaluation score of all storage equipment divided by the comprehensive performance evaluation point of each storage equipment
The size of several ratio and preset adjustment weight threshold;
When the ratio of the storage equipment is greater than or equal to the adjustment weight threshold, the storage equipment is reduced
Read-write probability.
5. according to the method described in claim 4, it is characterized in that, when the ratio of the storage equipment is greater than or equal to
When the adjustment weight threshold, the comprehensive performance evaluation score according to each storage equipment adjusts storage strategy, further includes:
It is counted since current time in preset first confirmation phase duration, often presets all storage equipment of unit time
Average behavior evaluation score divided by described in this store equipment comprehensive performance evaluation score ratio be greater than or equal to the tune
The number of whole weight threshold;
When the number counted is greater than or equal to preset first frequency threshold value, triggering reduces the read-write of the storage equipment
The operation of probability.
6. the method according to claim 1, wherein the comprehensive performance evaluation score according to each storage equipment
Adjust storage strategy, comprising:
According to the comprehensive performance evaluation score of each storage equipment, the average behavior evaluation point of all storage equipment is calculated
Number;
Compare the average behavior evaluation score of all storage equipment divided by the comprehensive performance evaluation point of each storage equipment
The size of several ratio and preset migrating data threshold value;
When the ratio of the storage equipment is greater than or equal to the migrating data threshold value, the storage equipment is migrated
The data of storage.
7. according to the method described in claim 6, it is characterized in that, when the ratio of the storage equipment is greater than or equal to
When the migrating data threshold value, the comprehensive performance evaluation score according to each storage equipment adjusts storage strategy, further includes:
It is counted since current time in preset second confirmation phase duration, often presets all storage equipment of unit time
Average behavior evaluation score be greater than or equal to described move divided by the ratio for the comprehensive performance evaluation score for storing equipment described in this
Move the number of data threshold;
When the number counted is greater than or equal to preset second frequency threshold value, the triggering migration storage equipment storage
The operation of data.
8. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage have one or
Multiple programs, one or more of programs can be executed by one or more processor, to realize such as claim 1 to 7
Any one of described in method for managing and monitoring the step of.
9. a kind of monitoring management apparatus, which is characterized in that including processor and memory, in which:
The processor is for executing the monitor supervisor stored in memory, to realize such as any one of claims 1 to 7
The step of described method for managing and monitoring.
10. a kind of monitoring management apparatus, which is characterized in that including data acquisition module, computing module and adjustment module, in which:
Data acquisition module, for obtaining one or more monitor control index data of all storage equipment in storage cluster;
Computing module calculates the comprehensive of each storage equipment for all monitor control index data for storing equipment according to acquisition
Close performance evaluation score;
Module is adjusted, for adjusting storage strategy according to the comprehensive performance evaluation score of each storage equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810879817.9A CN109086009B (en) | 2018-08-03 | 2018-08-03 | Monitoring management method and device and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810879817.9A CN109086009B (en) | 2018-08-03 | 2018-08-03 | Monitoring management method and device and computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109086009A true CN109086009A (en) | 2018-12-25 |
CN109086009B CN109086009B (en) | 2021-08-03 |
Family
ID=64833879
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810879817.9A Active CN109086009B (en) | 2018-08-03 | 2018-08-03 | Monitoring management method and device and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109086009B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111381768A (en) * | 2018-12-29 | 2020-07-07 | 北京亿阳信通科技有限公司 | Data monitoring method and device |
CN112540902A (en) * | 2020-12-03 | 2021-03-23 | 山东云海国创云计算装备产业创新中心有限公司 | Method, device and equipment for testing performance of system on chip and readable storage medium |
WO2022057374A1 (en) * | 2020-09-18 | 2022-03-24 | 苏州浪潮智能科技有限公司 | Method and apparatus for improving raid data backup efficiency |
CN114374707A (en) * | 2022-03-22 | 2022-04-19 | 联想凌拓科技有限公司 | Management method, device, equipment and medium for storage cluster |
WO2023138264A1 (en) * | 2022-01-21 | 2023-07-27 | 苏州浪潮智能科技有限公司 | Ssd data management method and related component |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101079324A (en) * | 2007-06-15 | 2007-11-28 | 华为技术有限公司 | Storage device, its life monitoring device and monitoring method |
US20130166727A1 (en) * | 2011-12-27 | 2013-06-27 | Solidfire, Inc. | Management of Storage System Access Based on Client Performance and Cluser Health |
US20160020965A1 (en) * | 2013-08-07 | 2016-01-21 | Hitachi, Ltd. | Method and apparatus for dynamic monitoring condition control |
CN106686082A (en) * | 2016-12-29 | 2017-05-17 | 华为技术有限公司 | Storage resource adjusting method and management node |
CN106856442A (en) * | 2015-12-09 | 2017-06-16 | 北京神州泰岳软件股份有限公司 | A kind of performance indications monitoring method and device |
CN107147547A (en) * | 2017-07-10 | 2017-09-08 | 山东超越数控电子有限公司 | A kind of cluster overall performance monitoring implementation method |
CN107844269A (en) * | 2017-10-17 | 2018-03-27 | 华中科技大学 | A kind of layering mixing storage system and method based on uniformity Hash |
CN107870843A (en) * | 2016-12-30 | 2018-04-03 | 平安科技(深圳)有限公司 | The method and device of nas server performance monitoring |
-
2018
- 2018-08-03 CN CN201810879817.9A patent/CN109086009B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101079324A (en) * | 2007-06-15 | 2007-11-28 | 华为技术有限公司 | Storage device, its life monitoring device and monitoring method |
US20130166727A1 (en) * | 2011-12-27 | 2013-06-27 | Solidfire, Inc. | Management of Storage System Access Based on Client Performance and Cluser Health |
US20160020965A1 (en) * | 2013-08-07 | 2016-01-21 | Hitachi, Ltd. | Method and apparatus for dynamic monitoring condition control |
CN106856442A (en) * | 2015-12-09 | 2017-06-16 | 北京神州泰岳软件股份有限公司 | A kind of performance indications monitoring method and device |
CN106686082A (en) * | 2016-12-29 | 2017-05-17 | 华为技术有限公司 | Storage resource adjusting method and management node |
CN107870843A (en) * | 2016-12-30 | 2018-04-03 | 平安科技(深圳)有限公司 | The method and device of nas server performance monitoring |
CN107147547A (en) * | 2017-07-10 | 2017-09-08 | 山东超越数控电子有限公司 | A kind of cluster overall performance monitoring implementation method |
CN107844269A (en) * | 2017-10-17 | 2018-03-27 | 华中科技大学 | A kind of layering mixing storage system and method based on uniformity Hash |
Non-Patent Citations (2)
Title |
---|
于滨等: "《基于Zabbix的分布式数字化监控系统设计与实现》", 《信息通信技术》 * |
熊永华等: "《云视频监控系统的能耗优化研究》", 《软件学报》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111381768A (en) * | 2018-12-29 | 2020-07-07 | 北京亿阳信通科技有限公司 | Data monitoring method and device |
WO2022057374A1 (en) * | 2020-09-18 | 2022-03-24 | 苏州浪潮智能科技有限公司 | Method and apparatus for improving raid data backup efficiency |
CN112540902A (en) * | 2020-12-03 | 2021-03-23 | 山东云海国创云计算装备产业创新中心有限公司 | Method, device and equipment for testing performance of system on chip and readable storage medium |
CN112540902B (en) * | 2020-12-03 | 2023-03-14 | 山东云海国创云计算装备产业创新中心有限公司 | Method, device and equipment for testing performance of system on chip and readable storage medium |
WO2023138264A1 (en) * | 2022-01-21 | 2023-07-27 | 苏州浪潮智能科技有限公司 | Ssd data management method and related component |
CN114374707A (en) * | 2022-03-22 | 2022-04-19 | 联想凌拓科技有限公司 | Management method, device, equipment and medium for storage cluster |
Also Published As
Publication number | Publication date |
---|---|
CN109086009B (en) | 2021-08-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109086009A (en) | A kind of method for managing and monitoring and device, computer readable storage medium | |
US10235055B1 (en) | Storage performance testing to evaluate moving data among arrays | |
JP5594664B2 (en) | System and method for storage tiering and migration techniques based on quality of service | |
US10007626B1 (en) | Storage performance testing to evaluate moving data among arrays | |
US9606728B2 (en) | Controlling a storage system | |
US7185168B2 (en) | System and method for quality of service management in a partitioned storage device or subsystem | |
US20110252210A1 (en) | Method and apparatus for rebalancing storage components within a storage tier | |
CN104268099B (en) | A kind of method and device for managing reading and writing data | |
US9760292B2 (en) | Storage system and storage control method | |
US10387039B2 (en) | Data storage management | |
US20180300066A1 (en) | Method and device for managing disk pool | |
US11199968B2 (en) | Using recurring write quotas to optimize utilization of solid state storage in a hybrid storage array | |
WO2018199794A1 (en) | Re-placing data within a mapped-raid environment | |
CN109213695A (en) | Buffer memory management method, storage system and computer program product | |
US20170220481A1 (en) | Raid Data Migration Through Stripe Swapping | |
US9858147B2 (en) | Storage apparatus and method of controlling storage apparatus | |
CN101251789A (en) | Cheap magnetic disc redundant array RAID5 roll rapid capacitance enlarging method | |
US20210224205A1 (en) | Tuning data storage equipment based on comparing observed i/o statistics with expected i/o statistics which are defined by operating settings that control operation | |
WO2014187574A1 (en) | Managing storage devices having a lifetime of a finite number of operations | |
Oe et al. | Automated tiered storage system consisting of memory and flash storage to improve response time with input-output (IO) concentration workloads | |
Lipetz et al. | Automated tiering in a QoS environment using coarse data | |
KR20130086449A (en) | Method for recording volume management program to relocate data block according to usage of each level volume | |
US12039203B1 (en) | Data storage system employing delayed responses to influence rate of bulk storage operations | |
US10747446B2 (en) | Computer system and storage device activation control method | |
US11403198B2 (en) | Managing data within solid state drive storage based on recurring write quotas |
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 |