CN106021046A - Hard disk performance comparison method, device and server - Google Patents
Hard disk performance comparison method, device and server Download PDFInfo
- Publication number
- CN106021046A CN106021046A CN201610318991.7A CN201610318991A CN106021046A CN 106021046 A CN106021046 A CN 106021046A CN 201610318991 A CN201610318991 A CN 201610318991A CN 106021046 A CN106021046 A CN 106021046A
- Authority
- CN
- China
- Prior art keywords
- hard disk
- disk groups
- pretest
- group
- throughput
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2247—Verification or detection of system hardware configuration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2205—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using arrangements specific to the hardware being tested
- G06F11/2221—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using arrangements specific to the hardware being tested to test input/output devices or peripheral units
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing For Digital Recording And Reproducing (AREA)
Abstract
The invention provides a hard disk performance comparison method, device and server. The method is applied to the server, and comprises the following steps: determining a target RAID card through forming at least two same hard disks into a pretest hard disk group, and defining a data block size; determining at least two pretest hard disk groups, each of which serves as the current pretest hard disk group in turn, and circularly executing N1 to N4, N1: mounting the current preset hard disk group onto the target RAID card, N2: controlling the current pretest hard disk group to transmit data through the target RAID card according to the data block size, N3: monitoring the throughput rate of the current pretest hard disk group, and N4: dismounting the current pretest hard disk group from the target RAID card; and when the throughput rate of each pretest hard disk group is monitored, comparing the throughput rates of the pretest hard disk groups through a chart. According to the hard disk performance comparison method, device and server, the automatic performance comparison between different hard disks is realized.
Description
Technical field
The present invention relates to field of computer technology, contrast the method for hard disk performance, device particularly to a kind of
And server.
Background technology
Along with the development of computer technology, Informatization Service and the most powerful cloud computing service pair
The performance requirement of server is more and more higher.In the server, hard disk is as storage device, and its performance is direct
Affect stability and the safety of server storage, then, during Server development, it is often necessary to
Contrast the performance that different hard disks shows in the server, with selected performance preferably hard disk.
At present, the mode of the different hard disk performance of contrast mainly, needs technical staff to pass through order and obtains hard
Dish running log, after obtaining hard disk running log, in addition it is also necessary to expends the time that technical staff is longer,
Artificially to screen, to contrast different hard disk running log, reach to contrast the purpose of different hard disk performance,
The most whole comparison process is required to the participation of technical staff, and can not automatically contrast different hard disk performance.
Summary of the invention
Embodiments provide and a kind of contrast the method for hard disk performance, device and server, it is achieved that
Automatically the different hard disk performance of contrast.
A kind of method contrasting hard disk performance, is applied to server, will at least two pieces of same hard disk compositions
One group of pretest hard disk groups, determines target RAID card, defines data block size, also includes:
Determine that at least two group pretest hard disk groups, each group of pretest hard disk groups are tried as current predictive successively
Hard disk groups, circulation execution N1 to N4:
N1: described current predictive examination hard disk groups is mounted in described target RAID card；
N2: according to described data block size, controls described current predictive examination hard disk groups by described target
RAID card transmission data；
N3: monitor the throughput of described current predictive examination hard disk groups；
N4: described current predictive examination hard disk groups is hung with described target RAID card solution；
When monitoring the throughput of each group of pretest hard disk groups, contrast each group of pretest by chart hard
The throughput of dish group.
Preferably, described, described current predictive examination hard disk groups is mounted in described target RAID card it
Before, farther include: automatically identify all of disk identifier of hard disk in described current predictive examination hard disk groups；And from
Dynamic according to described target RAID card, described current predictive examination hard disk groups is carried out subregion；
Described described current predictive examination hard disk groups is mounted in described target RAID card, including: automatically
The drive that current predictive after described subregion is tried hard disk groups corresponding is mounted in described target RAID card.
Preferably, said method farther includes: arrange data form；
The described throughput being contrasted each group of pretest hard disk groups by chart, including:
In described data form, add up the data total amount of each group of pretest hard disk groups, data block size
And throughput；
With data block size as abscissa, with throughput as vertical coordinate, build two-dimensional coordinate system, same
In individual coordinate system, draw the curve of each group of pretest hard disk groups, forming curves figure, and export described song
Line chart.
Preferably, described throughput, including: read throughput, re-reading throughput, write throughput, manifolding
In throughput, random write throughput and random write throughput any one and multiple.
Preferably, said method is applied to Lunix system, realizes based on Iozone instrument.
A kind of device contrasting hard disk performance, is applied to server, including:
Determine unit, for determining the target RAID card of peripheral hardware and at least two group pretest hard disks of peripheral hardware
Group；
Carry monitoring means, is used for defining data block size, determines that peripheral hardware that unit determines is extremely by described
In few two groups of pretest hard disk groups, each group of pretest hard disk groups tries hard disk groups as current predictive successively, follows
Ring execution N1 to N4:
N1: described current predictive examination hard disk groups is mounted in the target RAID card of described peripheral hardware；
N2: according to described data block size, controls described current predictive examination hard disk groups by described peripheral hardware
Target RAID card transmission data；
N3: monitor the throughput of described current predictive examination hard disk groups；
N4: the target RAID card solution of described current predictive examination hard disk groups with described peripheral hardware is hung；
Contrast unit, for monitoring handling up of each group of pretest hard disk groups when described carry monitoring means
During rate, contrasted the throughput of each group of pretest hard disk groups by chart.
Preferably, described carry monitoring means, including: identify subelement, subregion subelement and carry
Unit, wherein,
Described identification subelement, for automatically identifying all of hard disk dish in described current predictive examination hard disk groups
Symbol；
Described subregion subelement, for automatically according to described target RAID card, tries described current predictive
Hard disk groups carries out subregion；
Described carry subelement, for automatically trying hard disk by the current predictive after described subregion subelement subregion
The drive that the described recognition unit of group correspondence identifies is mounted in described target RAID card.
Preferably, said apparatus farther includes:
Output unit, for exporting the chart that described contrast unit is formed.
Preferably, described contrast unit, it is further used for arranging data form, in described data form,
Add up the data total amount of each group of pretest hard disk groups, data block size and throughput；With data block size
For abscissa, with throughput as vertical coordinate, build two-dimensional coordinate system, in same coordinate system, draw
The curve of each group of pretest hard disk groups, forming curves figure, and export described curve chart.
A kind of server contrasting hard disk performance, including: above-mentioned any one contrast hard disk performance device,
Target RAID card and at least two group pretest hard disk groups, wherein,
In described at least two group pretest hard disk groups, each group of pretest hard disk groups is successively as current predictive
Examination hard disk groups is connected with described target RAID card, defines for the device according to described contrast hard disk performance
Data block size, received the data of a given data total amount by described target RAID card, and accept institute
State control and the monitoring of the device of contrast hard disk performance.
Embodiments provide and a kind of contrast the method for hard disk performance, device and server, the method
It is applied to server, by least two pieces of same hard disks are formed one group of pretest hard disk groups, determines mesh
Mark RAID card, defines data block size, determines at least two group pretest hard disk groups, each group of pretest
Hard disk groups tries hard disk groups as current predictive successively, and circulation performs: current predictive is tried hard disk groups and is mounted to
In target RAID card；According to data block size, control current predictive examination hard disk groups by target RAID
Card transmission data；The throughput of monitoring current predictive examination hard disk groups；Current predictive is tried hard disk groups and target
RAID card solution is hung；Achieve the throughput automatically monitoring all pretest hard disk groups, each when monitoring
When organizing the throughput of pretest hard disk groups, contrasted the throughput of each group of pretest hard disk groups by chart,
In the embodiment of the present invention, the process of the process and contrast that monitor the throughput of each hard disk groups all can be automatic
Complete, and without the participation of technical staff, it is achieved that the different hard disk performance of contrast automatically.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to reality
Execute the required accompanying drawing used in example or description of the prior art to be briefly described, it should be apparent that below,
Accompanying drawing in description is some embodiments of the present invention, for those of ordinary skill in the art, not
On the premise of paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the flow chart of a kind of method contrasting hard disk performance that one embodiment of the invention provides；
Fig. 2 is the flow chart of a kind of method contrasting hard disk performance that another embodiment of the present invention provides；
Fig. 3 is the curve chart of the contrast hard disk performance result that one embodiment of the invention provides；
Fig. 4 is the structural representation of the device place framework of the contrast hard disk performance that the embodiment of the present invention provides；
Fig. 5 is the structural representation of a kind of device contrasting hard disk performance that one embodiment of the invention provides；
Fig. 6 is the structural representation of a kind of device contrasting hard disk performance that another embodiment of the present invention provides；
Fig. 7 is the structural representation of a kind of device contrasting hard disk performance that further embodiment of this invention provides；
Fig. 8 is the structural representation of the server of the contrast hard disk performance that one embodiment of the invention provides.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with this
Accompanying drawing in bright embodiment, is clearly and completely described the technical scheme in the embodiment of the present invention,
Obviously, described embodiment is a part of embodiment of the present invention rather than whole embodiments, based on
Embodiment in the present invention, those of ordinary skill in the art are institute on the premise of not making creative work
The every other embodiment obtained, broadly falls into the scope of protection of the invention.
As it is shown in figure 1, embodiments provide a kind of method contrasting hard disk performance, it is applied to clothes
Business device, the method may comprise steps of:
Step 101: at least two pieces of same hard disks are formed one group of pretest hard disk groups, determines target
RAID card, defines data block size；
Step 102: determine at least two group pretest hard disk groups, at least two group pretest hard disk groups really
Settled front pretest hard disk groups；
Step 103: current predictive is tried hard disk groups and is mounted in target RAID card；
Step 104: according to data block size, controls current predictive examination hard disk groups by target RAID card
Transmission data；
Step 105: the throughput of monitoring current predictive examination hard disk groups, it may be judged whether yet suffer from not supervised
The pretest hard disk groups surveyed, if it is, perform step 106, otherwise, performs step 107；
Step 106: current predictive is tried hard disk groups and hangs with target RAID card solution, and by next group prediction
Examination hard disk groups tries hard disk groups as current predictive, performs step 103；
Step 107: when monitoring the throughput of each group of pretest hard disk groups, each by chart contrast
The throughput of group pretest hard disk groups.
In the embodiment shown in fig. 1, hard by least two pieces of same hard disks are formed one group of pretest
Dish group, determines target RAID card, defines data block size, determines at least two group pretest hard disk groups,
Each group of pretest hard disk groups tries hard disk groups as current predictive successively, and circulation performs: tried by current predictive
Hard disk groups is mounted in target RAID card；According to data block size, control current predictive examination hard disk groups and lead to
Cross target RAID card transmission data；The throughput of monitoring current predictive examination hard disk groups；Current predictive is tried
Hard disk groups is hung with target RAID card solution；Achieve the throughput automatically monitoring all pretest hard disk groups,
When monitoring the throughput of each group of pretest hard disk groups, contrast each group of pretest hard disk groups by chart
Throughput, in embodiments of the present invention, monitor the process of the throughput of each hard disk groups and contrast
Process all can be automatically performed, and without the participation of technical staff, it is achieved that the different hard disk performance of contrast automatically.
In an embodiment of the invention, in order to improve the automatization of contrast further, ensure contrast simultaneously
Accuracy, after step 102, before step 103, farther include: automatically run following
Identify script, identify all of disk identifier of hard disk in current predictive examination hard disk groups；And automatically run following subregion
Script, according to target RAID card, carries out subregion to current predictive examination hard disk groups；
Identify script, including:
Subregion script, including:
function fdisk_disk()
{
for disk in`cat/root/disk.lst`
do
If [$ disk=/dev/sda]
then
echo-e"fdisk$disk now..."
parted–s$disk mkpart$disk"3"60gb 100gb
else
echo-e"fdisk$disk now..."
parted-s$disk mklabel gpt mkpart$disk"1"1 100gb
echo-e"Done"
fi
done
}；
The detailed description of the invention of step 103, including: automatically run following carry script, after subregion
The drive that current predictive tries hard disk groups corresponding is mounted in target RAID card；
Carry script, including:
In an embodiment of the invention, in order to make comparing result more directly perceived, after step 106,
Farther include: by following order output graph results；
This order, including:
iozone-s 10240m-I-f/mnt/sdb1/iozone_cp.tmp-r 4k-r 16k-r 32k-r 64k-r
128k-r 256k-r 512k-i 0-i 1-i 2>>test_result_sdb1.txt。
In an embodiment of the invention, in order to improve the intuitive of comparing result, said method further
Farther include: data form is set；The detailed description of the invention of step 106, including: at data form
In, add up the data total amount of each group of pretest hard disk groups, data block size and throughput；With data block
Size is abscissa, with throughput as vertical coordinate, builds two-dimensional coordinate system, in same coordinate system,
Draw the curve of each group of pretest hard disk groups, forming curves figure, and output curve diagram.
In an embodiment of the invention, in order to ensure the accuracy of comparing result, the inventive method carries
And throughput, including: read throughput, re-reading throughput, write throughput, manifolding throughput, random
Read any one in throughput and random write throughput with multiple.
In an embodiment of the invention, in order to ensure the accuracy of contrast, said method farther includes:
Automatically run following formatting script, each pretest hard disk groups is formatted；
Formatting script, including:
In an embodiment of the invention, in order to ensure the reliability of said method, said method is applied to
Lunix system, realizes based on Iozone instrument.
For making the object, technical solutions and advantages of the present invention clearer, below to contrast two kinds of hard disks
As a example by energy (hard disk 1 and hard disk 2), the method that embodiment of the present invention offer contrasts hard disk performance is made into one
Step ground describes in detail, as in figure 2 it is shown, the method is applied to server, may comprise steps of:
Step 200: data form is set；
The data form that this step is arranged is mainly that the throughput of subsequent statistical pretest hard disk groups is prepared,
Throughput by management of data tables pretest hard disk groups.
Step 201: at least two pieces of hard disk 1 predicted compositions are tried hard disk groups 1, and at least two pieces of hard disks 2 form
Pretest hard disk groups 2, determines target RAID card, defines data block size；
In general, a hard disk groups includes at least two pieces of hard disks, in order to contrast hard exactly
The performance of dish, in this step, hard disk composition pretest hard disk groups mutually of the same race, and in existing server,
Usually by hard disk groups and RAID card carry, realize data storage.
Step 202: determine pretest hard disk groups 1 and pretest hard disk groups 2, and at two groups of pretest hard disks
Group determining, current predictive tries hard disk groups；
Such as: in this step, it is first determined pretest hard disk groups 1 tries hard disk groups for current predictive, so
After, after pretest hard disk groups 1 is completed monitoring, determine that pretest hard disk groups 2 is hard for current predictive examination
Dish group.
Step 203: automatically run and identify script, identifies all of hard disk dish in current predictive examination hard disk groups
Symbol；
In this step, by identification script is stored in script file, and script file can be deposited
Storage is arrived under the catalogue of server, and Run Script file under this catalogue, it is achieved automatically runs and identifies script.
This identification script, including:
When current predictive examination hard disk groups is pretest hard disk groups 1, all in identification prediction examination hard disk groups 1
The disk identifier of hard disk of hard disk 1.
Step 204: automatically run subregion script, according to target RAID card, tries hard disk to current predictive
Group carries out subregion；
The process of this subregion is primarily to meet the demand of RAID card, and its subregion script also can be stored
In script file, and realize automatically running subregion script by Run Script file；
This subregion script, including:
function fdisk_disk()
{
for disk in`cat/root/disk.lst`
do
If [$ disk=/dev/sda]
then
echo-e"fdisk$disk now..."
parted–s$disk mkpart$disk"3"60gb 100gb
else
echo-e"fdisk$disk now..."
parted-s$disk mklabel gpt mkpart$disk"1"1 100gb
echo-e"Done"
fi
done
}。
Step 205: automatically run carry script, the current predictive after subregion is tried the dish that hard disk groups is corresponding
Symbol is mounted in target RAID card；
The carry script of this step still can be stored in script file, and by running under server directory
Script file realizes the automatic operation of carry script；
This carry script, including:
Step 206: current predictive examination hard disk groups is formatted；
The process that this step realizes, can be realized by formatting script in script file.
This formatting script, including:
Step 207: according to data block size, controls current predictive examination hard disk groups by target RAID card
Transmission data；
In order to contrast hard disk performance more accurately, data block size in this step, including: 4KB,
8KB, 16KB, 32KB, 64KB, 128KB, 256KB and 512KB, i.e. by multiple data block
Size is transmitted data, the most enough demonstrates hard disk performance more accurately.
Step 208: the throughput of monitoring current predictive examination hard disk groups, adds up each group of pretest hard disk groups
Data total amount, data block size and throughput；
Such as: when current predictive examination hard disk groups is pretest hard disk groups 1, testing result write step 200
In the form arranged, it was predicted that shown in the following Table I of monitoring result of examination hard disk groups 1:
Table I
When current predictive examination hard disk groups is pretest hard disk groups 2, testing result write step 200 is arranged
In form, it was predicted that shown in the following Table II of monitoring result of examination hard disk groups 2:
Table II
Step 209: judge whether to yet suffer from the pretest hard disk groups of the most monitored mistake, if it is,
Perform step 210, otherwise, perform step 211；
Such as: when current predictive examination hard disk groups is pretest hard disk groups 1, the monitoring of this step is prediction
The throughput of examination hard disk groups 1, the monitoring order be given according to preceding step 202, it was predicted that examination hard disk groups 2
The most monitored, then perform step 209；When current predictive examination hard disk groups is pretest hard disk groups 2,
What this step was monitored is the throughput of pretest hard disk groups 2, and the monitoring be given according to preceding step 202 is suitable
Sequence, all pretest hard disk groups are the most monitored, then perform step 210.And in order to improve the accurate of monitoring
Property, the throughput of this step monitoring, including: read throughput, re-reading throughput, write throughput, manifolding
In throughput, random write throughput and random write throughput any one and multiple.
Step 210: current predictive is tried hard disk groups and hangs with target RAID card solution, and by next group prediction
Examination hard disk groups tries hard disk groups as current predictive, performs step 203.
Such as: when current predictive examination hard disk groups is pretest hard disk groups 1, to pretest hard disk groups 1
After completing to monitor throughput, pretest hard disk groups 1 is hung with target RAID card solution, and by pretest
Hard disk groups 2 tries hard disk groups as current predictive.
Step 211: with data block size as abscissa, with throughput as vertical coordinate, builds two-dimensional coordinate
System；
Step 212: in same coordinate system, draws the curve of each group of pretest hard disk groups, is formed
Curve chart；
Number in the form that the detailed process of step 211 and step 212 is mainly given according to step 208
According to, draw contrast chart as shown in Figure 3, wherein, Fig. 3-1 is pretest hard disk groups 1 and pretest
Hard disk groups 2 reads the comparing result of throughput；Fig. 3-2 is pretest hard disk groups 1 and pretest hard disk groups 2
The comparing result of re-reading throughput；Fig. 3-3 writes handle up for pretest hard disk groups 1 and pretest hard disk groups 2
The comparing result of rate；Fig. 3-4 makes carbon copies the right of throughput for pretest hard disk groups 1 and pretest hard disk groups 2
Compare result；Fig. 3-5 is the contrast knot of pretest hard disk groups 1 and pretest hard disk groups 2 random write throughput
Really；Fig. 3-6 is pretest hard disk groups 1 and the comparing result of pretest hard disk groups 2 random write throughput；
Can find out intuitively from comparing result, it was predicted that in examination hard disk groups 2, the performance of hard disk 2 is than pretest hard disk
In group 1, hard disk 1 performance is strong.What deserves to be explained is, in order to more directly provide hard disk performance,
In the comparing result shown in Fig. 3, also data in Table I and Table II can be corresponded to each point in Fig. 3
Figure, i.e. the data that in Fig. 3, each component is corresponding show together with Fig. 3.
Step 213: output formats result and curve chart.
This step is mainly realized by following order:
iozone-s 10240m-I-f/mnt/sdb1/iozone_cp.tmp-r 4k-r 16k-r 32k-r 64k-r
128k-r 256k-r 512k-i 0-i 1-i 2>>test_result_sdb1.txt。
As shown in Figure 4, Figure 5, a kind of device contrasting hard disk performance is embodiments provided.Dress
Put embodiment to be realized by software, it is also possible to realize by the way of hardware or software and hardware combining.
For hardware view, as shown in Figure 4, the device of the contrast hard disk performance provided for the embodiment of the present invention
A kind of hardware structure diagram of place equipment, except the processor shown in Fig. 4, internal memory, network interface, with
And outside nonvolatile memory, in embodiment, the equipment at device place generally can also include other hardware,
Forwarding chip such as responsible process message etc..As a example by implemented in software, as it is shown in figure 5, as one
Device on logical meaning, is that the CPU by its place equipment is by meter corresponding in nonvolatile memory
Calculation machine programmed instruction reads and runs formation in internal memory.A kind of contrast hard disk performance that the present embodiment provides
Device, be applied to server, including:
Determine unit 501, for determining the target RAID card of peripheral hardware and at least two group pretests of peripheral hardware
Hard disk groups；
Carry monitoring means 502, is used for defining data block size, the peripheral hardware that will determine that unit 501 determines
At least two group pretest hard disk groups in each group of pretest hard disk groups try hard disk groups as current predictive successively,
Circulation execution N1 to N4:
N1: described current predictive examination hard disk groups is mounted in the target RAID card of described peripheral hardware；
N2: according to described data block size, controls described current predictive examination hard disk groups by described peripheral hardware
Target RAID card transmission data；
N3: monitor the throughput of described current predictive examination hard disk groups；
N4: the target RAID card solution of described current predictive examination hard disk groups with described peripheral hardware is hung；
Contrast unit 503, for monitoring each group of pretest hard disk groups when carry monitoring means 502
During throughput, contrasted the throughput of each group of pretest hard disk groups by chart.
As shown in Figure 6, in an alternative embodiment of the invention, carry monitoring means 502, including: identify
Subelement 601, subregion subelement 602 and carry subelement 603, wherein,
Identify subelement 601, for automatically running following identification script, identify current predictive examination hard disk groups
In all of disk identifier of hard disk；
Identify script, including:
Subregion subelement 602, for automatically running following subregion script, according to target RAID card, right
Current predictive examination hard disk groups carries out subregion；
Subregion script, including:
function fdisk_disk()
{
for disk in`cat/root/disk.lst`
do
If [$ disk=/dev/sda]
then
echo-e"fdisk$disk now..."
parted–s$disk mkpart$disk"3"60gb 100gb
else
echo-e"fdisk$disk now..."
parted-s$disk mklabel gpt mkpart$disk"1"1 100gb
echo-e"Done"
fi
done
}；
Carry subelement 603, for automatically running following carry script, by subregion subelement 602 subregion
After corresponding the identifying of current predictive examination hard disk groups the drive that identifies of subelement 601 is mounted to target
In RAID card；
Carry script, including:
As it is shown in fig. 7, in still another embodiment of the process, said apparatus farther includes:
Output unit 701, for the chart formed by following order output contrast unit 503；
This order, including: iozone-s 10240m-I-f/mnt/sdb1/iozone_cp.tmp-r 4k-r 16k
-r 32k-r 64k-r 128k-r 256k-r 512k-i 0-i 1-i 2>>test_result_sdb1.txt。
In an alternative embodiment of the invention, contrast unit 503, be further used for arranging data form,
In described data form, add up the data total amount of each group of pretest hard disk groups, data block size and handle up
Rate；With data block size as abscissa, with throughput as vertical coordinate, build two-dimensional coordinate system, same
In individual coordinate system, draw the curve of each group of pretest hard disk groups, forming curves figure, and export described song
Line chart.
The contents such as the information between each unit in said apparatus is mutual, execution process, due to the present invention
Embodiment of the method is based on same design, and particular content can be found in the narration in the inventive method embodiment, this
Place repeats no more.
As shown in Figure 8, the embodiment of the present invention provides a kind of server contrasting hard disk performance, including: on
State any one contrast device 801 of hard disk performance, target RAID card 802 and at least two group pretests
Hard disk groups 803, wherein,
In at least two group pretest hard disk groups 803, each group of pretest hard disk groups 803 is successively as current
Pretest hard disk groups is connected with target RAID card 802, for the device 801 according to contrast hard disk performance
The data block size of definition, is received the data of a given data total amount, and connects by target RAID card 802
It is subject to control and the monitoring of the device 801 of contrast hard disk performance.
According to such scheme, various embodiments of the present invention, at least have the advantages that
1., by least two pieces of same hard disks are formed one group of pretest hard disk groups, determine target RAID
Card, defines data block size, determines at least two group pretest hard disk groups, and each group of pretest hard disk groups depends on
Secondary as current predictive examination hard disk groups, circulation performs: current predictive is tried hard disk groups and is mounted to target RAID
On card；According to data block size, control current predictive examination hard disk groups and transmit data by target RAID card；
The throughput of monitoring current predictive examination hard disk groups；Current predictive tries hard disk groups hang with target RAID card solution；
Achieve the throughput automatically monitoring all pretest hard disk groups, when monitoring each group of pretest hard disk groups
Throughput time, contrasted the throughput of each group of pretest hard disk groups by chart, in embodiments of the present invention,
The process of the process and contrast that monitor the throughput of each hard disk groups all can be automatically performed, and without technology
The participation of personnel, it is achieved that the different hard disk performance of contrast automatically.
2. by identification script, subregion script, carry script and the formatting script in script file,
Can the disk identifier of hard disk of identification prediction hard disk groups automatically, and prediction hard disk groups is carried out subregion, by hard for prediction
Dish group is mounted in target RAID card realize the normal work of prediction hard disk groups, simultaneously to prediction hard disk groups
Formatting, whole process can be realized by script, further ensures the different hard disk performance of contrast
Automatization.
3., by arranging data form, in data form, add up the data of each group of pretest hard disk groups
Total amount, data block size and throughput；With data block size as abscissa, with throughput as vertical coordinate,
Build two-dimensional coordinate system, in same coordinate system, draw the curve of each group of pretest hard disk groups, shape
Becoming curve chart, and output curve diagram, this curve chart can compare intuitively and show comparing result accurately.
4. the embodiment of the present invention statistics throughput include, read throughput, re-reading throughput, write throughput,
In manifolding throughput, random write throughput and random write throughput any one and multiple, i.e. by many
Individual angle contrasts, so that comparing result is more accurate.
It should be noted that in this article, the relational terms of such as first and second etc be used merely to by
One entity or operation separate with another entity or operating space, and not necessarily require or imply this
Relation or the order of any this reality is there is between a little entities or operation.And, term " includes ",
" comprise " or its any other variant is intended to comprising of nonexcludability, so that include that one is
The process of row key element, method, article or equipment not only include those key elements, but also include the brightest
Other key elements really listed, or also include intrinsic for this process, method, article or equipment
Key element.In the case of there is no more restriction, statement " include one " and limit
Key element, it is not excluded that there is also another in including the process of described key element, method, article or equipment
Outer same factor.
One of ordinary skill in the art will appreciate that: realize all or part of step of said method embodiment
Can be completed by the hardware that programmed instruction is relevant, aforesaid program can be stored in embodied on computer readable
Storage medium in, this program upon execution, performs to include the step of said method embodiment；And it is aforementioned
Storage medium include: various Jie that can store program code such as ROM, RAM, magnetic disc or CD
In matter.
Last it should be understood that the foregoing is only presently preferred embodiments of the present invention, it is merely to illustrate this
The technical scheme of invention, is not intended to limit protection scope of the present invention.All spirit in the present invention and former
Any modification, equivalent substitution and improvement etc. done within then, are all contained in protection scope of the present invention.
Claims (10)
1. the method contrasting hard disk performance, it is characterised in that be applied to server, by least two pieces
Same hard disk forms one group of pretest hard disk groups, determines target RAID card, defines data block size,
Also include:
Determine that at least two group pretest hard disk groups, each group of pretest hard disk groups are tried as current predictive successively
Hard disk groups, circulation execution N1 to N4:
N1: described current predictive examination hard disk groups is mounted in described target RAID card；
N2: according to described data block size, controls described current predictive examination hard disk groups by described target
RAID card transmission data；
N3: monitor the throughput of described current predictive examination hard disk groups；
N4: described current predictive examination hard disk groups is hung with described target RAID card solution；
When monitoring the throughput of each group of pretest hard disk groups, contrast each group of pretest by chart hard
The throughput of dish group.
Method the most according to claim 1, it is characterised in that
Described, the examination of described current predictive before hard disk groups is mounted in described target RAID card, is entered one
Step includes: automatically identify all of disk identifier of hard disk in described current predictive examination hard disk groups；And automatically according to institute
State target RAID card, described current predictive examination hard disk groups is carried out subregion；
Described described current predictive examination hard disk groups is mounted in described target RAID card, including: automatically
The drive that current predictive after described subregion is tried hard disk groups corresponding is mounted in described target RAID card.
Method the most according to claim 1, it is characterised in that farther include: tables of data is set
Lattice；
The described throughput being contrasted each group of pretest hard disk groups by chart, including:
In described data form, add up the data total amount of each group of pretest hard disk groups, data block size
And throughput；
With data block size as abscissa, with throughput as vertical coordinate, build two-dimensional coordinate system, same
In individual coordinate system, draw the curve of each group of pretest hard disk groups, forming curves figure, and export described song
Line chart.
4. according to the arbitrary described method of claims 1 to 3, it is characterised in that described throughput, bag
Include:
Read throughput, re-reading throughput, write throughput, manifolding throughput, random write throughput and random
Write any one in throughput with multiple.
5. according to the arbitrary described method of claims 1 to 3, it is characterised in that be applied to Lunix
System, realizes based on Iozone instrument.
6. the device contrasting hard disk performance, it is characterised in that be applied to server, including:
Determine unit, for determining the target RAID card of peripheral hardware and at least two group pretest hard disks of peripheral hardware
Group；
Carry monitoring means, is used for defining data block size, determines that peripheral hardware that unit determines is extremely by described
In few two groups of pretest hard disk groups, each group of pretest hard disk groups tries hard disk groups as current predictive successively, follows
Ring execution N1 to N4:
N1: described current predictive examination hard disk groups is mounted in the target RAID card of described peripheral hardware；
N2: according to described data block size, controls described current predictive examination hard disk groups by described peripheral hardware
Target RAID card transmission data；
N3: monitor the throughput of described current predictive examination hard disk groups；
N4: the target RAID card solution of described current predictive examination hard disk groups with described peripheral hardware is hung；
Contrast unit, for monitoring handling up of each group of pretest hard disk groups when described carry monitoring means
During rate, contrasted the throughput of each group of pretest hard disk groups by chart.
Device the most according to claim 6, it is characterised in that described carry monitoring means, including:
Identification subelement, subregion subelement and carry subelement, wherein,
Described identification subelement, for automatically identifying all of hard disk dish in described current predictive examination hard disk groups
Symbol；
Described subregion subelement, for automatically according to described target RAID card, tries described current predictive
Hard disk groups carries out subregion；
Described carry subelement, for automatically trying hard disk by the current predictive after described subregion subelement subregion
The drive that the described recognition unit of group correspondence identifies is mounted in described target RAID card.
8. according to the arbitrary described device of claim 6 to 7, it is characterised in that farther include:
Output unit, for exporting the chart that described contrast unit is formed.
9. according to the arbitrary described device of claim 6 to 7, it is characterised in that described contrast unit,
It is further used for:
Arranging data form, in described data form, the data adding up each group of pretest hard disk groups are total
Amount, data block size and throughput；With data block size as abscissa, with throughput as vertical coordinate, structure
Build two-dimensional coordinate system, in same coordinate system, draw the curve of each group of pretest hard disk groups, formed
Curve chart, and export described curve chart.
10. the server contrasting hard disk performance, it is characterised in that including: claim 6 to 9
The arbitrary described device of contrast hard disk performance, target RAID card and at least two group pretest hard disk groups,
Wherein,
In described at least two group pretest hard disk groups, each group of pretest hard disk groups is successively as current predictive
Examination hard disk groups is connected with described target RAID card, defines for the device according to described contrast hard disk performance
Data block size, received the data of a given data total amount by described target RAID card, and accept institute
State control and the monitoring of the device of contrast hard disk performance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610318991.7A CN106021046A (en) | 2016-05-12 | 2016-05-12 | Hard disk performance comparison method, device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610318991.7A CN106021046A (en) | 2016-05-12 | 2016-05-12 | Hard disk performance comparison method, device and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106021046A true CN106021046A (en) | 2016-10-12 |
Family
ID=57100120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610318991.7A Pending CN106021046A (en) | 2016-05-12 | 2016-05-12 | Hard disk performance comparison method, device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106021046A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107145420A (en) * | 2017-05-03 | 2017-09-08 | 郑州云海信息技术有限公司 | Based on OpenPower framework automated disk method of testings |
| CN111049684A (en) * | 2019-12-12 | 2020-04-21 | 闻泰通讯股份有限公司 | Data analysis method, device, equipment and storage medium |
| CN111722879A (en) * | 2020-06-19 | 2020-09-29 | 浪潮电子信息产业股份有限公司 | USB flash disk identification method, Linux system, Linux equipment and readable storage medium |
| TWI710753B (en) * | 2019-09-12 | 2020-11-21 | 英業達股份有限公司 | Method for analyzing effect of noise on hard disk performance |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104317693A (en) * | 2014-10-30 | 2015-01-28 | 浪潮电子信息产业股份有限公司 | Method for automatically testing hard disk performance fluctuation |
| CN104765665A (en) * | 2015-04-14 | 2015-07-08 | 浪潮电子信息产业股份有限公司 | Method and device for testing hard disks |
| CN104809042A (en) * | 2015-04-27 | 2015-07-29 | 浪潮电子信息产业股份有限公司 | Iozone-based hard disk performance testing method |
| CN105138293A (en) * | 2015-09-11 | 2015-12-09 | 浪潮电子信息产业股份有限公司 | Disk performance evaluating method based on database |
-
2016
- 2016-05-12 CN CN201610318991.7A patent/CN106021046A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104317693A (en) * | 2014-10-30 | 2015-01-28 | 浪潮电子信息产业股份有限公司 | Method for automatically testing hard disk performance fluctuation |
| CN104765665A (en) * | 2015-04-14 | 2015-07-08 | 浪潮电子信息产业股份有限公司 | Method and device for testing hard disks |
| CN104809042A (en) * | 2015-04-27 | 2015-07-29 | 浪潮电子信息产业股份有限公司 | Iozone-based hard disk performance testing method |
| CN105138293A (en) * | 2015-09-11 | 2015-12-09 | 浪潮电子信息产业股份有限公司 | Disk performance evaluating method based on database |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107145420A (en) * | 2017-05-03 | 2017-09-08 | 郑州云海信息技术有限公司 | Based on OpenPower framework automated disk method of testings |
| CN107145420B (en) * | 2017-05-03 | 2020-02-07 | 郑州云海信息技术有限公司 | OpenPower architecture-based automatic disk test method |
| TWI710753B (en) * | 2019-09-12 | 2020-11-21 | 英業達股份有限公司 | Method for analyzing effect of noise on hard disk performance |
| CN111049684A (en) * | 2019-12-12 | 2020-04-21 | 闻泰通讯股份有限公司 | Data analysis method, device, equipment and storage medium |
| CN111722879A (en) * | 2020-06-19 | 2020-09-29 | 浪潮电子信息产业股份有限公司 | USB flash disk identification method, Linux system, Linux equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107193750B (en) | Script recording method and device | |
| US9501562B2 (en) | Identification of complementary data objects | |
| CN111563014A (en) | Interface service performance test method, device, equipment and storage medium | |
| CN106021046A (en) | Hard disk performance comparison method, device and server | |
| KR20150074020A (en) | Specifying and applying rules to data | |
| CN102075368A (en) | Method, device and system for diagnosing service failure | |
| US20100042353A1 (en) | System and method for testing working condition of led indicators on hard disk drives | |
| CN108139965A (en) | Management server and the management method using the management server | |
| US10977082B2 (en) | Resource allocation optimization support system and resource allocation optimization support method | |
| CN112688806A (en) | Method and system for presenting network assets | |
| CN108388490A (en) | A kind of method and system of test high-end server memory | |
| CN111400121A (en) | Server hard disk slot positioning and maintaining method | |
| CN106980572B (en) | Online debugging method and system for distributed system | |
| CN109284209A (en) | The automated testing method of different type Vdisk under a kind of Mcs system | |
| CN108897765A (en) | A kind of batch data introduction method and its system | |
| CN110278101A (en) | A kind of method for managing resource and equipment | |
| CN106899436A (en) | A kind of cloud platform failure predication diagnostic system | |
| CN109918385A (en) | Tripartite's account checking method, electronic device and readable storage medium storing program for executing | |
| CN112068979B (en) | Service fault determination method and device | |
| EP4152715A1 (en) | Method and apparatus for determining resource configuration of cloud service system | |
| CN105373446B (en) | It is a kind of based on the system self-repairing method drilled automatically and device | |
| CN115248782B (en) | Automatic testing method and device and computer equipment | |
| CN106886477A (en) | Threshold setting method and device are monitored in a kind of cloud system | |
| CN115309334A (en) | Disk management method, device, equipment and storage medium | |
| CN114218001A (en) | Fault repairing method and device, electronic equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161012 |