CN105099912A - Multipath data scheduling method and device - Google Patents
Multipath data scheduling method and device Download PDFInfo
- Publication number
- CN105099912A CN105099912A CN201510482482.3A CN201510482482A CN105099912A CN 105099912 A CN105099912 A CN 105099912A CN 201510482482 A CN201510482482 A CN 201510482482A CN 105099912 A CN105099912 A CN 105099912A
- Authority
- CN
- China
- Prior art keywords
- paths
- data
- path
- judged result
- data dispatch
- 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
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a multipath data scheduling method and device. The method comprises the steps that S1: at least two paths included between a transmitting end and a receiving end are confirmed; S2: existence that the difference value of the I/O quantity of one path and the I/O quantity of another path is not less than the average I/O quantity of all the paths is judged; and if the judgment result is yes, step S3 is performed, or step S4 is performed; S3: data are scheduled to the path with the minimum I/O quantity; and S4 data polling is scheduled to all the paths. According to the scheme, data scheduling resources can be saved.
Description
Technical field
The present invention relates to field of computer technology, particularly a kind of data dispatching method of multipath and device.
Background technology
MPIO (MultiPathI/O, multi-route management) be visit the network storage equipment by one and above physical link, and the modes such as fault-tolerant, traffic load balancing and fine-grained I/O scheduling strategy can be used, for network storage application provides higher availability and performance advantage.
At present, when carrying out transfer of data, the data dispatch of multipath can be realized in the following way: the mode adopting poll, sends to each path respectively by the packet received successively, with the packet making each paths be transmitted as its distribution.
But, in actual applications, for different network paths, there is different bandwidth sum transmission characteristics, if there is the poor path of transmission quality in the network path of scheduling, transfer of data on the path easily causes the problem such as time-out, mistake, packet loss, re-transmission of packet, thus affects overall transfer performance.
Summary of the invention
In view of this, the invention provides a kind of data dispatching method and device of multipath, to solve the problem that data dispatch mode of the prior art affects overall transfer performance.
Embodiments provide a kind of data dispatching method of multipath, comprising:
S1: determine at least two paths included between transmitting terminal and receiving terminal;
S2: judge whether to deposit the average I/O that difference that I/O amount on one path and the I/O on another paths measure is not less than all paths and measure; If exist, then perform S3, otherwise perform S4;
S3: data dispatch is measured minimum path to I/O;
S4: give each paths by data polling dispatching.
Preferably, described S2, comprising:
The difference judging whether to deposit the I/O degree of depth on the I/O degree of depth on one path and another paths is not less than the first judged result of the average I/O degree of depth in all paths, and the difference judging whether to deposit the I/O task amount on I/O task amount on one path and another paths is not less than the second judged result of the average I/O task amount in all paths;
Described first judged result and described second judged result include do not exist time, then perform S4;
Described first judged result and/or described second judged result comprise exist time, then perform S3.
Preferably, comprise further:
Foundation is used for traversal physical disks state and the separate threads for data dispatch in real time, and according to traveling through the time interval of physical disks state in real time, and set the time threshold that described separate threads upgrades data dispatch mode.
Preferably, before S2, comprise further:
System initialization, data polling dispatching is adopted to carry out data dispatch to the mode of each paths, and utilize Start_Routine to start described separate threads, start to start timer when described separate threads starts and carry out timing, when described timer reaches described time threshold, upgrade data dispatch mode.
Preferably, the time threshold of the described separate threads of described setting comprises 60 seconds.
Embodiments provide a kind of data scheduling device of multipath, comprising:
Determining unit, for determining at least two paths included between transmitting terminal and receiving terminal;
Judging unit, the average I/O that the difference measured for judging whether to deposit I/O amount on one path and the I/O on another paths is not less than all paths measures; If exist, then trigger data scheduling unit performs corresponding operating, otherwise triggers polling dispatching unit execution corresponding operating;
Described data scheduling unit, for measuring minimum path by data dispatch to I/O;
Described polling dispatching unit, for giving each paths by data polling dispatching.
Preferably, described judging unit, difference for judging whether to deposit the I/O degree of depth on the I/O degree of depth on one path and another paths is not less than the first judged result of the average I/O degree of depth in all paths, and the difference judging whether to deposit the I/O task amount on I/O task amount on one path and another paths is not less than the second judged result of the average I/O task amount in all paths; Described first judged result and described second judged result include do not exist time, then trigger described data scheduling unit perform corresponding operating; Described first judged result and/or described second judged result comprise exist time, then trigger described polling dispatching unit perform corresponding operating.
Preferably, comprise further:
Pretreatment unit, for setting up for traveling through physical disks state and the separate threads for data dispatch in real time, and according to traveling through the time interval of physical disks state in real time, and sets the time threshold that described separate threads upgrades data dispatch mode.
Preferably, comprise further:
Initial treatment unit, for executive system initialization, data polling dispatching is adopted to carry out data dispatch to the mode of each paths, and utilize Start_Routine to start described separate threads, start to start timer when described separate threads starts and carry out timing, when described timer reaches described time threshold, upgrade data dispatch mode.
Preferably, described pretreatment unit, the time threshold for setting described separate threads comprises 60 seconds.
Embodiments provide a kind of data dispatching method and device of multipath, during by measuring at the average I/O judging to deposit I/O amount on one path and the difference measured of I/O on another paths and be not less than all paths, show that the I/O amount difference on some path is larger, therefore the mode by data dispatch measures minimum path to I/O can be adopted to carry out data dispatch, to improve the transmission performance of data dispatch entirety, the average I/O that I/O amount on one path and the difference measured of I/O on another paths be not less than all paths if do not deposit measures, then show that the I/O amount on path is more or less the same, can adopt and data polling dispatching is carried out data dispatch to the mode of each paths, thus data dispatch resource can be saved.
Accompanying drawing explanation
Fig. 1 is the method flow diagram that the embodiment of the present invention provides;
Fig. 2 is the method flow diagram that another embodiment of the present invention provides;
Fig. 3 is the MPIO framework architecture figure that the embodiment of the present invention provides;
Fig. 4 is the hardware structure figure of the device place equipment that the embodiment of the present invention provides;
Fig. 5 is the apparatus structure schematic diagram that the embodiment of the present invention provides;
Fig. 6 is the apparatus structure schematic diagram that another embodiment of the present invention provides.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described.Obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
As shown in Figure 1, embodiments provide a kind of data dispatching method of multipath, the method can comprise the following steps:
Step 101: determine at least two paths included between transmitting terminal and receiving terminal.
Step 102: judge whether to deposit the average I/O that difference that I/O amount on one path and the I/O on another paths measure is not less than all paths and measure; If exist, then perform step 103, otherwise perform step 104.
Step 103: data dispatch is measured minimum path to I/O.
Step 104: give each paths by data polling dispatching.
According to such scheme, during by measuring at the average I/O judging to deposit I/O amount on one path and the difference measured of I/O on another paths and be not less than all paths, show that the I/O amount difference on some path is larger, therefore the mode by data dispatch measures minimum path to I/O can be adopted to carry out data dispatch, to improve the transmission performance of data dispatch entirety, the average I/O that I/O amount on one path and the difference measured of I/O on another paths be not less than all paths if do not deposit measures, then show that the I/O amount on path is more or less the same, can adopt and data polling dispatching is carried out data dispatch to the mode of each paths, thus data dispatch resource can be saved.
Due in data dispatch process, in order to reduce resource consumption, can set up for traveling through physical disks state and the separate threads for data dispatch in real time, and according to traveling through the time interval of physical disks state in real time, and set the time threshold of described separate threads.
For ensureing the overall transfer performance in data dispatch process, can start to start timer when separate threads starts and carry out timing, when described timer reaches described time threshold, upgrade data dispatch mode, thus can detect at set intervals in data dispatch process and currently whether deposit the average I/O that I/O amount on one path and the difference measured of I/O on another paths be not less than all paths and measure, upgrade data dispatch mode.
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with drawings and the specific embodiments, the present invention is described in further detail.
As shown in Figure 2, embodiments provide a kind of data dispatching method of multipath, the method can comprise the following steps:
Step 201: system initialization DSM context mechanism body, the data dispatch mode of acquiescence is adopted to carry out data dispatch after initialization, and utilize Start_Routine to start separate threads, start to start timer when separate threads starts and carry out timing, when timer reaches setting-up time threshold value, perform step 202.
First, the application scenarios of the present embodiment once is simply described.As shown in Figure 3, for the system configuration schematic diagram of MPIO framework, main frame Server is comprised at MPIO framework, Server is connected with switch SAN by HBA (host bus adaptor) card, and be connected with controller Controller by SAN, Controller is that disk array RAIDarray is connected, this disk array as bottom memory device, for the data in storage system.
Wherein, between Server and disk array, comprise at least two paths, suppose to comprise 3 paths, such as, L
1, L
2, L
3by utilizing this three paths, map to one of main frame piece of disk from bottom memory device, after reporting HBA card by the mulitpath of network communication equipment, these all need the filter operation of filtration drive from the physical disks that every paths reports up, its concrete function be exactly judge the disk that reports up whether support by DSM (DeviceSpecificModules).If support that the class just loading MPIO drives Mpdev.sys; Otherwise, directly load Disk.sys.If DSM supported, then have bus driver to be that these never generate a virtual disk with the physical disks on path, this virtual disk is just mapped with multiple physical disks, forms the relation of one-to-many.For upper layer application, this virtual disk is just the same with common local disk.Certainly, the coordinated of normal need of work Mpio.sys and DSM of this virtual disk could complete smoothly.
When carrying out data and reporting transmission, this three paths can be utilized to carry out data dispatch, to realize optimum transfer of data.Because the transmission performance in different path is different, throughput in transmitting procedure is also different, therefore, in order to realize realizing optimum transfer of data in data transmission procedure, the present embodiment by the configuration of procotol, can realize the selection of different pieces of information scheduling mode in transmitting procedure.
In the present embodiment, first need to carry out system initialization to DSM context mechanism body, start to carry out data dispatch after showing initialization.
In the present embodiment, the data dispatch mode of acquiescence can be pre-set, to make after DSM initialization, the data dispatch mode of this acquiescence can be adopted to carry out data dispatch.Wherein, the scheduling that following three kinds of data dispatch modes realize data in the present embodiment, can be comprised, 1, Round_Robin, give each paths by data successively polling dispatching; 2, Least_Number_IO, gives the path of the minimum I/O degree of depth by data dispatch; 3, Least_Task_IO, gives the path of minimum I/O task amount by data dispatch.
Such as, the data dispatch mode of this acquiescence can be any one in above-mentioned three kinds of data dispatch modes.In the present embodiment, consider the transmission performance of entire system during data dispatch, and avoid the waste of excess resource, Round_Robin data dispatch mode by default can be adopted.
In the present embodiment, also need to set up separate threads, for carrying out data dispatch way choice and carrying out corresponding data dispatch according to the data dispatch mode selected.In order to save system resource, can will be used for traveling through in real time the thread of physical disks state as separate threads.In the present embodiment, separate threads, as the executive agent of data dispatch, realizes the scheduling to data in bottom memory device.
Further, because separate threads needs traversal physical disks state in real time, and traversal physical disks state completes and comprises a time interval, therefore can according to this time interval, setting separate threads upgrades the time threshold of data dispatch mode, and to make when reaching this time threshold, separate threads can upgrade data dispatch mode to carry out data dispatch, wherein, this time threshold is equal with this time interval.Such as, this time threshold can say 60s second.When separate threads starts, namely start to start timer and carry out timing, when timer reaches time threshold, point out.
Step 202: data dispatch mode is upgraded at random, and after judging that data dispatch mode upgrades, current data dispatch mode, if current data dispatch mode is Round_Robin, so performs step 203; If current data dispatch mode is Least_Number_IO, so perform step 208; If current data dispatch mode is Least_Task_IO, so perform step 213.
In the present embodiment, in order to ensure in data dispatch process can the optimal selection of keeping system overall performance, can upgrade data scheduling mode according to the time threshold of setting, and the data dispatch mode after upgrading is random data dispatch mode, and when current data dispatch mode is different, follow-up data dispatch way choice is not identical yet, therefore, needs to perform different data dispatch steps according to different data dispatch modes.
Step 203: judge whether applicable data dispatch mode Least_Number_IO, if be applicable to, then performs step 204, otherwise performs step 205.
Wherein, when current data scheduling mode is Round_Robin, according to three paths L included in Fig. 3
1, L
2and L
3, when often obtaining data waiting for transmission, the data that this band is transmitted successively polling dispatching to L
1, L
2and L
3, to make the I/O degree of depth that each paths transmits identical.
In the present embodiment, applicable data dispatch mode Least_Number_IO can be judged whether in the following way: the difference detecting the I/O degree of depth on the I/O degree of depth of whether depositing on one path and another paths is not less than the average I/O degree of depth in all paths, if, then show that on some path, its I/O degree of depth difference is larger, need to select Least_Number_IO to alleviate and eliminate the balance phenomenon of this I/O degree of depth between some path, so just need to select Least_Number_IO by data dispatch to the minimum path of the I/O degree of depth.
Wherein, the I/O degree of depth to refer on path transmit the number of I/O data.
Such as, L
1on the I/O degree of depth be 20, L
2on the I/O degree of depth be 8, L
3on the I/O degree of depth be 2, the average I/O degree of depth in so all paths is (20+8+2)/3=10, and there is L
1-L
3, and L
1-L
2value be not less than the average I/O degree of depth, show L
1respectively with L
2, L
3on I/O degree of depth difference comparatively large, therefore, need to select Least_Number_IO by data dispatch to the minimum L of the I/O degree of depth
3, to make L
3carry out transfer of data.
Step 204: select Least_Number_IO to carry out data dispatch.
Step 205: judge whether applicable Least_Task_IO, if so, performs step 206, otherwise performs step 207.
In the present embodiment, applicable data dispatch mode Least_Task_IO can be judged whether in the following way: the difference detecting the I/O task amount on the I/O task amount whether deposited on one path and another paths is not less than the average I/O task amount in all paths, if, then show that on some path, its I/O task amount difference is larger, need to select Least_Task_IO to alleviate and eliminate the balance phenomenon of this I/OLeast_Task_IO between some path, so just need to select Least_Task_IO by data dispatch to the minimum path of I/OLeast_Task_IO.
Wherein, I/O task amount be according on path transmit the number of I/O data, and the data length of each I/O data is relevant, the stock number namely taken required for transmission on the path.
Such as, L
1on I/O task amount be 40, L
2on I/O task amount be 15, L
3on I/O task amount be 5, the average I/O task amount in so all paths is (40+15+5)/3=20, and there is L
1-L
3, and L
1-L
2value be not less than average I/O task amount, show L
1respectively with L
2, L
3on I/O task amount difference comparatively large, therefore, need to select Least_Task_IO by data dispatch to the minimum L of I/O task amount
3, to make L
3carry out transfer of data.
Step 206: select Least_Task_IO to carry out data dispatch.
Step 207: continue to use Round_Robin to carry out data dispatch.
When above-mentioned two situations all exist, illustrate that the I/O degree of depth of every paths is suitable on all paths with I/O task amount, therefore, continues to adopt Round_Robin selecting paths.
It should be noted that, when current data scheduling mode is Round_Robin, can first judge whether applicable Least_Number_IO, judging whether applicable Least_Task_IO, also can be first judge whether applicable Least_Task_IO, judging whether applicable Least_Number_IO, concrete restriction is not being done to this order.
Step 208: judge whether applicable Least_Task_IO, if so, performs step 209, otherwise performs step 210.
Step 209: select Least_Task_IO to carry out data dispatch.
When current data dispatching algorithm is Least_Number_IO, can first judge whether applicable Least_Task_IO, if be applicable to Least_Task_IO, then select Least_Task_IO to carry out data dispatch.
Step 210: judge whether applicable Least_Number_IO, if so, performs step 211, otherwise performs step 212.
Step 211: continue to use Least_Number_IO.
Step 212: select Round_Robin to carry out data dispatch.
It should be noted that, current data scheduling be Least_Number_IO time, can first judge whether applicable Least_Task_IO, after judge whether applicable Least_Number_IO; Also can first judge whether applicable Least_Number_IO, after judge whether applicable Least_Task_IO.The present embodiment does not do concrete restriction to this.
Step 213: judge whether applicable Least_Number_IO, if so, performs step 214; Otherwise, perform step 215.
Step 214: select Least_Number_IO to carry out data dispatch.
Step 215: judge whether applicable Least_Task_IO, if so, performs step 216; Otherwise, perform step 217.
Step 216: continue to use Least_Task_IO to carry out data dispatch.
Step 217: select Round_Robin to carry out data dispatch, and perform step.
Needs illustrate, when current data dispatch mode is Least_Task_IO, can first judge whether applicable Least_Number_IO, judge whether applicable Least_Task_IO; Also can first judge whether applicable Least_Task_IO, judge whether applicable Least_Number_IO.The present embodiment does not do concrete restriction to this.
In the present embodiment, separate threads is when determining that timer reaches time threshold, data scheduling mode is upgraded, and continue when upgrading to use timer to carry out timing, in any one step above-mentioned, once determine that timer reaches time threshold, then can turn back to step 202 and continue to perform.
According to this programme, after determining the data dispatch mode used, corresponding data dispatch mode just can be utilized to carry out the selection of optimal path: if Round_Robin, then poll issues I/O data successively in respective paths, not consider the I/O degree of depth on path and I/O task amount; If Least_Number_IO, then on the minimum path of the I/O degree of depth, issue current I/O data; If Least_Task_IO, then on the minimum path of I/O task amount, issue current I/O.By intelligent selection data dispatch mode, with the transformation task selecting optimal path to carry out I/O data, realize intelligentized I/O optimal route selection function, avoid because unicity operates the affected problem of entire system performance brought, improve data transmission throughput.
As shown in Figure 4, Figure 5, a kind of data scheduling device of multipath is embodiments provided.Device embodiment can pass through software simulating, also can be realized by the mode of hardware or software and hardware combining.Say from hardware view; as shown in Figure 4; for a kind of hardware structure diagram of the data scheduling device place equipment of embodiment of the present invention multipath; except the processor shown in Fig. 4, internal memory, network interface and nonvolatile memory; in embodiment, the equipment at device place can also comprise other hardware usually, as the forwarding chip etc. of responsible process message.For software simulating, as shown in Figure 5, as the device on a logical meaning, be by the CPU of its place equipment, computer program instructions corresponding in nonvolatile memory is read operation in internal memory to be formed.The data scheduling device of the multipath that the present embodiment provides comprises:
Determining unit 501, for determining at least two paths included between transmitting terminal and receiving terminal;
Judging unit 502, the average I/O that the difference measured for judging whether to deposit I/O amount on one path and the I/O on another paths is not less than all paths measures; If exist, then trigger data scheduling unit 503 performs corresponding operating, otherwise triggering polling dispatching unit 504 performs corresponding operating;
Described data scheduling unit 503, for measuring minimum path by data dispatch to I/O;
Described polling dispatching unit 504, for giving each paths by data polling dispatching.
Further, described judging unit 502, difference for judging whether to deposit the I/O degree of depth on the I/O degree of depth on one path and another paths is not less than the first judged result of the average I/O degree of depth in all paths, and the difference judging whether to deposit the I/O task amount on I/O task amount on one path and another paths is not less than the second judged result of the average I/O task amount in all paths; Described first judged result and described second judged result include do not exist time, then trigger described data scheduling unit perform corresponding operating; Described first judged result and/or described second judged result comprise exist time, then trigger described polling dispatching unit perform corresponding operating.
As shown in Figure 6, the data scheduling device of this multipath may further include:
Pretreatment unit 601, for setting up for traveling through physical disks state and the separate threads for data dispatch in real time, and according to traveling through the time interval of physical disks state in real time, and sets the time threshold that described separate threads upgrades data dispatch mode.
Comprise further:
Initial treatment unit 602, for executive system initialization, data polling dispatching is adopted to carry out data dispatch to the mode of each paths, and utilize Start_Routine to start described separate threads, start to start timer when described separate threads starts and carry out timing, when described timer reaches described time threshold, upgrade data dispatch mode.
Further, described pretreatment unit 601, the time threshold for setting described separate threads comprises 60 seconds.
To sum up, the embodiment of the present invention at least can realize following beneficial effect:
1, during by measuring at the average I/O judging to deposit I/O amount on one path and the difference measured of I/O on another paths and be not less than all paths, show that the I/O amount difference on some path is larger, therefore the mode by data dispatch measures minimum path to I/O can be adopted to carry out data dispatch, to improve the transmission performance of data dispatch entirety, the average I/O that I/O amount on one path and the difference measured of I/O on another paths be not less than all paths if do not deposit measures, then show that the I/O amount on path is more or less the same, can adopt and data polling dispatching is carried out data dispatch to the mode of each paths, thus data dispatch resource can be saved.By intelligent selection data dispatch mode, with the transformation task selecting optimal path to carry out I/O data, realize intelligentized I/O optimal route selection function, avoid because unicity operates the affected problem of entire system performance brought, improve data transmission throughput.
The content such as information interaction, implementation between each unit in the said equipment, due to the inventive method embodiment based on same design, particular content can see in the inventive method embodiment describe, repeat no more herein.
It should be noted that, in this article, the relational terms of such as first and second and so on is only used for an entity or operation to separate with another entity or operating space, and not necessarily requires or imply the relation that there is any this reality between these entities or operation or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, article or equipment and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, article or equipment.When not more restrictions, the key element " being comprised a 〃 〃 〃 〃 〃 〃 " limited by statement, and be not precluded within process, method, article or the equipment comprising described key element and also there is other identical factor.
One of ordinary skill in the art will appreciate that: all or part of step realizing said method embodiment can have been come by the hardware that program command is relevant, aforesaid program can be stored in the storage medium of embodied on computer readable, this program, when performing, performs the step comprising said method embodiment; And aforesaid storage medium comprises: ROM, RAM, magnetic disc or CD etc. various can be program code stored medium in.
Finally it should be noted that: the foregoing is only preferred embodiment of the present invention, only for illustration of technical scheme of the present invention, be not intended to limit protection scope of the present invention.All any amendments done within the spirit and principles in the present invention, equivalent replacement, improvement etc., be all included in protection scope of the present invention.
Claims (10)
1. a data dispatching method for multipath, is characterized in that, comprising:
S1: determine at least two paths included between transmitting terminal and receiving terminal;
S2: judge whether to deposit the average I/O that difference that I/O amount on one path and the I/O on another paths measure is not less than all paths and measure; If exist, then perform S3, otherwise perform S4;
S3: data dispatch is measured minimum path to I/O;
S4: give each paths by data polling dispatching.
2. method according to claim 1, is characterized in that, described S2, comprising:
The difference judging whether to deposit the I/O degree of depth on the I/O degree of depth on one path and another paths is not less than the first judged result of the average I/O degree of depth in all paths, and the difference judging whether to deposit the I/O task amount on I/O task amount on one path and another paths is not less than the second judged result of the average I/O task amount in all paths;
Described first judged result and described second judged result include do not exist time, then perform S4;
Described first judged result and/or described second judged result comprise exist time, then perform S3.
3. method according to claim 1 and 2, is characterized in that, comprises further:
Foundation is used for traversal physical disks state and the separate threads for data dispatch in real time, and according to traveling through the time interval of physical disks state in real time, and set the time threshold that described separate threads upgrades data dispatch mode.
4. method according to claim 3, is characterized in that, before S2, comprises further:
System initialization, data polling dispatching is adopted to carry out data dispatch to the mode of each paths, and utilize Start_Routine to start described separate threads, start to start timer when described separate threads starts and carry out timing, when described timer reaches described time threshold, upgrade data dispatch mode.
5. method according to claim 3, is characterized in that, the time threshold of the described separate threads of described setting comprises 60 seconds.
6. a data scheduling device for multipath, is characterized in that, comprising:
Determining unit, for determining at least two paths included between transmitting terminal and receiving terminal;
Judging unit, the average I/O that the difference measured for judging whether to deposit I/O amount on one path and the I/O on another paths is not less than all paths measures; If exist, then trigger data scheduling unit performs corresponding operating, otherwise triggers polling dispatching unit execution corresponding operating;
Described data scheduling unit, for measuring minimum path by data dispatch to I/O;
Described polling dispatching unit, for giving each paths by data polling dispatching.
7. the data scheduling device of multipath according to claim 6, it is characterized in that, described judging unit, difference for judging whether to deposit the I/O degree of depth on the I/O degree of depth on one path and another paths is not less than the first judged result of the average I/O degree of depth in all paths, and the difference judging whether to deposit the I/O task amount on I/O task amount on one path and another paths is not less than the second judged result of the average I/O task amount in all paths; Described first judged result and described second judged result include do not exist time, then trigger described data scheduling unit perform corresponding operating; Described first judged result and/or described second judged result comprise exist time, then trigger described polling dispatching unit perform corresponding operating.
8. the data scheduling device of the multipath according to claim 6 or 7, is characterized in that, comprises further:
Pretreatment unit, for setting up for traveling through physical disks state and the separate threads for data dispatch in real time, and according to traveling through the time interval of physical disks state in real time, and sets the time threshold that described separate threads upgrades data dispatch mode.
9. the data scheduling device of multipath according to claim 8, is characterized in that, comprises further:
Initial treatment unit, for executive system initialization, data polling dispatching is adopted to carry out data dispatch to the mode of each paths, and utilize Start_Routine to start described separate threads, start to start timer when described separate threads starts and carry out timing, when described timer reaches described time threshold, upgrade data dispatch mode.
10. the data scheduling device of multipath according to claim 8, is characterized in that, described pretreatment unit, and the time threshold for setting described separate threads comprises 60 seconds.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510482482.3A CN105099912A (en) | 2015-08-07 | 2015-08-07 | Multipath data scheduling method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510482482.3A CN105099912A (en) | 2015-08-07 | 2015-08-07 | Multipath data scheduling method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105099912A true CN105099912A (en) | 2015-11-25 |
Family
ID=54579504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510482482.3A Pending CN105099912A (en) | 2015-08-07 | 2015-08-07 | Multipath data scheduling method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105099912A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220124A (en) * | 2017-05-26 | 2017-09-29 | 郑州云海信息技术有限公司 | A kind of routing resource and device |
| CN111049927A (en) * | 2019-12-24 | 2020-04-21 | 珠海大横琴科技发展有限公司 | File storage method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040267980A1 (en) * | 2003-06-26 | 2004-12-30 | International Business Machines Corporation | Method, system, and program for maintaining and swapping paths in an MPIO environment |
| CN101345770A (en) * | 2008-08-22 | 2009-01-14 | 杭州华三通信技术有限公司 | Load equalization implementing method, storage control equipment and memory system |
| CN102546823A (en) * | 2012-02-18 | 2012-07-04 | 南京云创存储科技有限公司 | File storage management system of cloud storage system |
| CN103023804A (en) * | 2012-12-18 | 2013-04-03 | 北京星网锐捷网络技术有限公司 | Method, device and network equipment for polymerization chain self-adaption flow load balance |
| CN104202349A (en) * | 2009-12-31 | 2014-12-10 | 华为技术有限公司 | Method, device and system of scheduling of distributed cache resources |
| CN104270322A (en) * | 2014-10-30 | 2015-01-07 | 中电海康集团有限公司 | Self-adaptive load balance scheduling mechanism for internet-of-things device access processing platform |
-
2015
- 2015-08-07 CN CN201510482482.3A patent/CN105099912A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040267980A1 (en) * | 2003-06-26 | 2004-12-30 | International Business Machines Corporation | Method, system, and program for maintaining and swapping paths in an MPIO environment |
| CN101345770A (en) * | 2008-08-22 | 2009-01-14 | 杭州华三通信技术有限公司 | Load equalization implementing method, storage control equipment and memory system |
| CN104202349A (en) * | 2009-12-31 | 2014-12-10 | 华为技术有限公司 | Method, device and system of scheduling of distributed cache resources |
| CN102546823A (en) * | 2012-02-18 | 2012-07-04 | 南京云创存储科技有限公司 | File storage management system of cloud storage system |
| CN103023804A (en) * | 2012-12-18 | 2013-04-03 | 北京星网锐捷网络技术有限公司 | Method, device and network equipment for polymerization chain self-adaption flow load balance |
| CN104270322A (en) * | 2014-10-30 | 2015-01-07 | 中电海康集团有限公司 | Self-adaptive load balance scheduling mechanism for internet-of-things device access processing platform |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220124A (en) * | 2017-05-26 | 2017-09-29 | 郑州云海信息技术有限公司 | A kind of routing resource and device |
| CN107220124B (en) * | 2017-05-26 | 2021-01-12 | 苏州浪潮智能科技有限公司 | Path selection method and device |
| CN111049927A (en) * | 2019-12-24 | 2020-04-21 | 珠海大横琴科技发展有限公司 | File storage method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102111337B (en) | Method and system for task scheduling | |
| CN103763130B (en) | Management method, the device and system of large-scale cluster | |
| CN104135741A (en) | Method of Bluetooth low energy communication, Bluetooth devices and system | |
| CN111722786A (en) | Storage system based on NVMe equipment | |
| CN107070752B (en) | Testing method and testing system for long connection capacity | |
| CN103746933A (en) | Node distribution method and control center | |
| CN109618174A (en) | A kind of live data transmission method, device, system and storage medium | |
| CN104142871A (en) | Data backup method and device and distributed file system | |
| WO2023174037A1 (en) | Resource scheduling method, apparatus and system, device, medium, and program product | |
| CN106412030A (en) | Storage resource selecting method, device and system | |
| CN104811431A (en) | Data packet processing method and device based on parallel protocol stack instance | |
| CN106412039A (en) | Distributed storage network integration method and system | |
| CN102625453B (en) | For the method and apparatus of the scheduling strategy in Dynamic Selection RF Resourse Distribute | |
| CN106445411A (en) | Data reading method and device and distributed storage system | |
| CN105099912A (en) | Multipath data scheduling method and device | |
| CN105718396B (en) | A kind of I of big data master transmissions2C bus units and its means of communication | |
| CN102143053B (en) | Method, device and system for transmitting data | |
| CN105242955A (en) | Virtual machine disk input and output scheduling method and system | |
| CN117667358A (en) | Container group scheduling method, system, electronic device, cluster and readable storage medium | |
| CN108924128A (en) | A kind of mobile terminal and its method for limiting, the storage medium of interprocess communication | |
| CN115840649B (en) | Method and device for partitioning capacity block type virtual resource allocation, storage medium and terminal | |
| CN104349506A (en) | Association management method, wireless access device and system | |
| CN116048413B (en) | IO request processing method, device and system for multipath storage and storage medium | |
| CN101986703A (en) | Video recording method, network video surveillance system and front end as well as scheduling server | |
| CN116909953A (en) | Multipath planning method, device and 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20151125 |