CN107066334A - Information processing method and processing system - Google Patents
Information processing method and processing system Download PDFInfo
- Publication number
- CN107066334A CN107066334A CN201710162192.XA CN201710162192A CN107066334A CN 107066334 A CN107066334 A CN 107066334A CN 201710162192 A CN201710162192 A CN 201710162192A CN 107066334 A CN107066334 A CN 107066334A
- Authority
- CN
- China
- Prior art keywords
- processing node
- node
- resource
- processing
- storage resource
- 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 OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
- G06F9/5016—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals the resource being the memory
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5094—Allocation of resources, e.g. of the central processing unit [CPU] where the allocation takes into account power or heat criteria
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The embodiment of the invention discloses a kind of information processing method and processing system.The processing system includes：It is multiple to handle nodes and handle node memory resource pool with described；Methods described includes：When detecting when crossing incident heat of the memory resource pool, it is determined that causing the corresponding first processing node of first storage resource for crossing incident heat；Frequency reducing instruction is sent to the first processing node, wherein, the frequency reducing instruction, the working frequency for reducing the processing node.
Description
Technical field
The present invention relates to electronic technology field, more particularly to a kind of information processing method and processing system.
Background technology
In information processing system, it is configured with multiple processing nodes and various is believed for handle that node provides
Resource needed for breath processing.Here resource may include Internet resources such as storage resource and Microsoft Loopback Adapter etc..
Generally there are two kinds of storage resource methods of salary distribution in described information processing system：
The first, static allocation；
Second, dynamically distributes.
Static allocation should not carry out resource allocation again in use, but this to may result in storage resource effectively sharp
It is low with rate；
Dynamically distributes can handle the current demand of node according to each, distribute resource；But dynamically distributes storage resource, this
The resource that sample handles node distribution each time is all uncertain, which results in temperature controlled uncontrollability, and then can be led
Cause in the information processing architecture of Resource dynamic allocation, the too high phenomenon of the temperature of some storage resources.
The content of the invention
In view of this, the embodiment of the present invention is expected to provide a kind of information processing method and processing system, at least partly solves
The problem of storage resource is overheated.
To reach above-mentioned purpose, the technical proposal of the invention is realized in this way：
First aspect of the embodiment of the present invention provides a kind of information processing method, applied in processing system, wherein, the place
Reason system includes：It is multiple to handle nodes and handle node memory resource pool with described；Methods described includes：
When detecting when crossing incident heat of the memory resource pool, it is determined that causing first storage resource for crossing incident heat
Corresponding first processing node；
Frequency reducing instruction is sent to the first processing node, wherein, the frequency reducing instruction, the work for reducing the processing node
Working frequency.
Based on such scheme, methods described also includes：
When for n-th processing the n-th storage resource of node distribution, cell system administrative unit (Pooled System
Management element, PSME) the n-th processing node and the corresponding relation of n-th storage resource are recorded, wherein,
The n is the positive integer less than N；The N is that the processing system includes the total number of the processing node；
It is described when detect the memory resource pool cross incident heat when, it is determined that cause it is described cross incident heat first storage
The corresponding first processing node of resource, including：
The corresponding relation is inquired about, it is determined that causing the first processing node.
Based on such scheme, it is described record it is described n-th processing node and n-th storage resource corresponding relation, including：
By the node identification of the described n-th processing node and the resource identification of n-th storage resource, correspondence is sent to default
Unit, wherein, the default unit includes substrate manager (Baseboard Management Controller, BMC), pipe
Manage controller (Management Controller, MC), Distant supervision and control unit (Remote Monitoring＆
Management, RMM) and resource pool administrative unit at least one；
The node identification of default unit correspondence storage the n-th processing node and the resource of n-th storage resource
Mark, forms the corresponding relation；
The inquiry corresponding relation, it is determined that cause the first processing node, including：
When detecting the incident heat excessively, corresponding relation described in the default unit local search determines described first
Handle node.
It is described when detecting when crossing incident heat of the memory resource pool based on such scheme, it is determined that causing the overheat
The corresponding first processing node of the first storage resource of event, including：
Receive default unit and send take described and cross incident heat, wherein, it is described cross incident heat and carry cause the overheat
The resource identification of first storage resource of event, wherein, the default unit include BMC, MC, Distant supervision and control unit and
At least one of resource pool administrative unit；
The PSME inquires about institute after the incident heat excessively is received according to the resource identification of first storage resource
State corresponding relation and determine the first processing node.
Based on such scheme, methods described also includes：
The node identification of described first processing node is sent to universal resource management (Generic Asset by the PSME
Management, GAM) module；
It is described to send frequency reducing instruction to the first processing node, including：
The GAM modules send frequency reducing instruction to the described first processing node.
Based on such scheme, methods described also includes：
The node identification of described first processing node is sent to the default unit by the PSME；
It is described to send frequency reducing instruction to the first processing node, including：
The default unit sends frequency reducing instruction to the described first processing node.
It is described when detecting when crossing incident heat of the memory resource pool based on such scheme, it is determined that causing the overheat
The corresponding first processing node of the first storage resource of event, including：
When detecting when crossing incident heat of the memory resource pool, preset unit and sent resource carrying to the PSME
The inquiry request of the resource identification of the first storage resource is stated, wherein, the default unit includes BMC, MC, Distant supervision and control
At least one of unit and resource pool administrative unit；
Receive the inquiry for the node identification for carrying the first processing node that the PSME is returned based on the inquiry request
Response；
It is described to send frequency reducing instruction to the first processing node, including：
The default unit sends the frequency reducing according to the node identification, to the described first processing node and instructed.
Second aspect of the embodiment of the present invention provides a kind of processing system, including：
Multiple processing nodes；
Bus subsystem, is connected with the processing node；
Memory resource pool, is connected by the bus subsystem with the processing node；
Cooling subsystem, including be arranged on the memory resource pool position and cool down the first cold of the memory resource pool
But subsystem；
Subsystem is managed, is connected respectively with the bus subsystem, memory resource pool, cooling subsystem and the processing node
Connect, for described when detecting the incident heat excessively of the memory resource pool when detecting, it is determined that causing the incident heat excessively
The corresponding first processing node of first storage resource；Frequency reducing instruction is sent to the first processing node, wherein, the frequency reducing instruction,
Working frequency for reducing the processing node.
Based on such scheme, the management subsystem includes：
PSME, for when for n-th processing the n-th storage resource of node distribution, the n-th processing node and described n-th to be deposited
The corresponding relation of resource is stored up, wherein, the n is the positive integer less than N；The N is that the processing system includes the processing section
The total number of point.
Based on such scheme, the management subsystem also includes：
Default unit, the default unit includes：At least one of BMC, MC, RMM and resource pool administrative unit；
The PSEM, is additionally operable to the resource mark by the node identification of the described n-th processing node and n-th storage resource
Know, correspondence is sent to default unit；
The default unit, the node identification and n-th storage resource of the n-th processing node are stored for correspondence
Resource identification, forms the corresponding relation, and when detecting the incident heat excessively, corresponding relation described in local search determines institute
State the first processing node.
Information processing method provided in an embodiment of the present invention and processing system, can be when detecting incident heat, it is determined that leading
Caused the corresponding processing node of storage resource of incident heat.Instructed by sending frequency reducing to the processing node, so that at this
The frequency reduction of the node orientation storage resource is managed, so that the temperature of the storage resource is reduced, so that it is each to solve processing system
Plant the problem of memory resource pool part storage resource is overheated.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the first information processing method provided in an embodiment of the present invention；
Fig. 2 is the schematic flow sheet of second of information processing method provided in an embodiment of the present invention；
Fig. 3 is the schematic flow sheet of the third information processing method provided in an embodiment of the present invention；
Fig. 4 is the schematic flow sheet of the 4th kind of information processing method provided in an embodiment of the present invention；
Fig. 5 is the schematic flow sheet of the 5th kind of information processing method provided in an embodiment of the present invention；
Fig. 6 is the schematic flow sheet of the 6th kind of information processing method provided in an embodiment of the present invention；
Fig. 7 is a kind of structural representation of processing system provided in an embodiment of the present invention.
Embodiment
Technical scheme is further elaborated below in conjunction with Figure of description and specific embodiment.
The present embodiment provides a kind of information processing method, applied in processing system, wherein, the processing system includes：
It is multiple to handle nodes and handle node memory resource pool with described.Processing system described in the present embodiment includes multiple processing sections
Point, multiple storage resources.But storage resource is integrated foring resource pool, the processing node by bus pond internal bus,
It may be connected to the memory resource pool.Each described processing node can use the storage in the memory resource pool to provide
Source.
As shown in figure 1, methods described includes：
Step S110：When detecting when crossing incident heat of the memory resource pool, it is determined that causing described to cross the of incident heat
The corresponding first processing node of one storage resource；
Step S120：Frequency reducing instruction is sent to the first processing node, wherein, the frequency reducing instruction, for reducing the place
Manage the working frequency of node.
The present embodiment described information processing method, had incident heat, overheat here when detecting memory resource pool
Event refers at least part storage resource in memory resource pool because excessively being read and write, and causes overheat.Here overheat is
The temperature for referring to the storage resource is higher than preset temperature.When storage resource is overheated, it will usually cause information to lose and/or store
The problem of service life of resource is too short.
In the present embodiment when detecting incident heat, it will can determine whether to carry out the first storage resource currently overheated first
First processing node of the processing such as read-write operation.The storage resource of frequent visit first of first processing node, so as to can cause
The temperature of first storage resource remains high, in the present embodiment in order to lower the temperature of first storage resource, in this reality
Applying the step S120 of example can send frequency instruction to the described first processing node.Refer to when the described first processing node receives frequency reducing
After order, the working frequency of the first processing node can be reduced, is deposited so as to reduce the first processing node to described first
The visitation frequency of resource is stored up, so that first storage resource is reduced because the problem of frequently accessed caused temperature is too high,
So as to lower the temperature of first storage, so as to solve the problems of excessive heat.
Methods described also includes in the present embodiment：
When detecting the incident heat excessively, the current operating state of cooling subsystem in the processing system is detected；
The step S110 specifically may include：The maximum cooling power if the cooling subsystem has currently worked, really
Fixed first storage resource corresponding first handles node.Step is performed after the first processing node is determined
S120；
If the cooling subsystem does not operate in the maximum cooling power currently, the first storage resource institute is increased
In the current power of the cooling subsystem of position, the temperature of first storage resource is reduced by the cooling of the cooling subsystem
Degree, without carrying out frequency reducing to the described first processing node, so that place caused by reducing by the first unnecessary frequency reducing of processing node
The problem of response speed of reason system is slowly and resource utilization is not high.
In certain embodiments, as shown in Fig. 2 methods described also includes：
Step S101：When for n-th processing the n-th storage resource of node distribution, PSME records the n-th processing node and institute
The corresponding relation of the n-th storage resource is stated, wherein, the n is the positive integer less than N；The N is described in the processing system includes
Handle the total number of node.Node identification and the institute of the n-th processing node are recorded in the corresponding relation in the present embodiment
The resource identification of the n-th storage resource is stated, like this, can by inquiry of the storage resource according to the corresponding relation is inquired about
To determine the node identification of the corresponding processing node of the storage resource.The N is just whole not less than 2 in the present embodiment
Number.
The PSME can receive software management unit (POD) resource allocation request；PSME please according to the resource allocation
Ask, inquire about the resource status of currently stored resource, the resource status is returned into POD, POD according to the resource status of return,
For processing node distribution storage resource, notify PSME that corresponding storage resource is distributed into corresponding processing node.Like this,
PSME is known which storage resource is allocated to which processing node is used.The PSME just can be by recording the place
Manage the node identification of node and the resource identification of the storage resource forms the corresponding relation.For example, the POD is according to described
Resource status responds the resource allocation request, is n-th of processing node distribution storage resource, distributes to the n-th processing section
The storage resource of point is referred to as n-th storage resource in the present embodiment.After storage resource distribution is completed, the PSME
Or the functional entity in other processing systems, the node identification and n-th storage resource of the n-th processing node can be recorded
Resource identification, forms the corresponding relation, facilitates corresponding relation described in subsequent query.
In the operation of aftertreatment systems, the processing node shutdown or startup can all be detected by the PSME, institute
PSME is stated by sending releasing request to the POD, then the POD can unbind the processing node and the storage resource,
So as to discharge the storage resource.
Methods described also includes：The PSME can also update the corresponding relation, for example according to the resource release operations
Unbind the node identification of some processing nodes and the corresponding relation of resource identification.
The storage resource can be dynamically distributes in the present embodiment, and the corresponding relation also can be according to storage resource
Current allocation status, dynamic updates；So as to solve the part storage resource occurred during dynamically distributes storage resource because of frequently quilt
Problems of excessive heat caused by accessing.
The step S110 may include：
The corresponding relation is inquired about, it is determined that causing the first processing node.
The executive agent of the corresponding relation is inquired about in the present embodiment, can be the PSME or other storages
There is the functional entity of the corresponding relation.
In certain embodiments, it is described to record the corresponding relation and may include：
The node identification of described n-th processing node and the resource identification of n-th storage resource, correspondence are sent to by PSME
Default unit, wherein, the default unit includes at least one of BMC, MC, RMM and resource pool administrative unit；
The node identification of default unit correspondence storage the n-th processing node and the resource of n-th storage resource
Mark, forms the corresponding relation.
The step S110 may include：
When detecting the incident heat excessively, corresponding relation described in the default unit local search determines described first
Handle node.
The PSME, can be by the section of corresponding processing node when the distribution of storage resource is carried out in the present embodiment
Point identification and distribute the resource identification of storage resource of the processing node and be sent to default unit, before default unit here is
State one kind of functional entity.Like this, can just the corresponding relation be locally stored in the default unit.In the present embodiment
Described in preset unit can for detection or formed it is described cross incident heat functional entity.If like this, when the default list
First temperature by detecting the storage resource of each in memory resource pool, it was found that have the phenomenon that temperature is too high, form the mistake
After incident heat, without determining the first processing node when the PSME, but described first can be voluntarily determined
Node is handled, is timely instructed by sending frequency reducing to the described first processing node, the first processing node can be reduced
Working frequency, so that by reducing the visitation frequencies such as the read-write to the first storage resource, the temperature of the first storage resource of rapid reduction
Degree, reduces the duration of overheat；Obviously the processing speed of overheat can be lifted.
Default unit described in the present embodiment may include：BMC, MC, RMM and resource pool unit etc..
The BMC, it may also be used for carry out the servomechanism management in the processing system and monitor.
The MC, it may also be used for equipment control and monitoring.Here equipment can be the various equipment in the processing system.
The RMM is properly termed as RMC again, is a kind of Software Management services unit of standard interface, it can be used for management of
And in monitoring cabinet all devices temperature, can be also used for the power management in processing system.
The resource pool unit, can be the functional entity that resource pool aspect monitoring management is carried out to each resource pool.
In a word, these default units may detect that the main equipment for crossing incident heat.Deposited by these default units
Store up the corresponding relation, then described cross incident heat once detecting, it is possible to by local search it is easy quick determine it is described
First processing node；It can also reduce simultaneously because needing to handle node to PSME inquiries first, it is necessary to sent out to the PSME
Send the transmission and the increase of information interaction times for the data volume that the resource identification of the first storage resource brings.
The condition notification that storage resource can be also released by the PSME in certain embodiments to the default unit,
So as to which the default unit can update the corresponding relation, it is ensured that depositing in the corresponding relation according to prime P SME notice
The corresponding relation stored up between resource and processing node is correct.
In certain embodiments, the step S110 may include：
PSME, which receives default unit and sends take described, crosses incident heat, wherein, it is described cross incident heat carry cause it is described
The resource identification of the first storage resource of incident heat is crossed, wherein, the default unit includes BMC, MC, Distant supervision and control list
At least one of member and resource pool administrative unit；
The PSME inquires about institute after the incident heat excessively is received according to the resource identification of first storage resource
State corresponding relation and determine the first processing node.
In the present embodiment, what the default unit of PSME receptions was reported crosses incident heat, and this is crossed in incident heat and carried
State the resource identification for the first storage resource for causing incident heat that default unit is determined.PSME is receiving the overheat thing
It is inquiry foundation using the resource identification after part, it will extract the resource identification, inquiry is in progress resource allocation
The corresponding relation of record, so that it is determined that going out the node identification of the first processing node of currently used first storage resource.One
Denier first processing node node identification determine, to first processing node send frequency reducing instruction executive agent be known that to
Which processing connects the frequency reducing quality of node transmission.
" first " in the first storage resource and the first processing node all only refers in the present embodiment, does not indicate that described
The special storage resource of some in processing system or processing node.First storage resource is allocated to the first processing section
Point, therefore the first processing node, by after frequency reducing, the accessed frequency of first storage resource will be reduced, so as to reduce institute
State the temperature of the first storage resource.
In certain embodiments, methods described also includes：
The node identification of described first processing node is sent to GAM modules by the PSME；
The step S120 may include：
The GAM modules send frequency reducing instruction to the described first processing node.
The node identification of the inquire first processing node is sent to GAM modules by the PSME in the present embodiment, this
In GAM modules can to first processing node send frequency reducing instruction.The frequency reducing instruction can be by described in the present embodiment
Default unit is sent to the processing node of prime number first.
The GAM modules can be a PSME module in the present embodiment；The nucleus module of the PSME determines institute
After the node identification for stating the first processing node, the node identification, the GAM modules formation drop are sent to the GAM modules
Frequency instruction is sent to the first processing node.
In certain embodiments, methods described also includes：
The node identification of described first processing node is sent to the default unit by the PSME；
The step S120 can, including：
The default unit sends frequency reducing instruction to the described first processing node.
The PSME itself does not form frequency reducing instruction in the present embodiment, but directly by the described first processing node
Node identification is sent to the default unit, and the frequency reducing instruction is formed after unit receives the node identification by presetting,
It is sent to the first processing node.
In further embodiments, the step S110 may include：
When detecting when crossing incident heat of the memory resource pool, preset unit and sent resource carrying to the PSME
The inquiry request of the resource identification of the first storage resource is stated, wherein, the default unit includes BMC, MC, Distant supervision and control
At least one of unit and resource pool administrative unit；
Receive the inquiry for the node identification for carrying the first processing node that the PSME is returned based on the inquiry request
Response.
Default unit described in the present embodiment can send inquiry request after incident heat was detected to PSME, this
In inquiry request be ask PSME inquiry overheat the first storage resource it is corresponding first processing node.In the present embodiment
First storage resource is allocated to the first processing node, and the node identification and first that PSME forms the first processing node is deposited
Store up the corresponding relation of the resource identification of resource.
Default unit described in the present embodiment is to send to cause the mistake to the PSME by special inquiry request
The resource identification of first storage resource of incident heat.
The step S120 may include：The default unit is according to the node identification, to the described first processing node hair
The frequency reducing is sent to instruct.
The default unit can form frequency reducing instruction and be sent to the after the node identification that the PSME is sent is received
One processing node, so as to promote the first processing node frequency reducing, so as to reduce the temperature of first storage resource, solves the mistake
Incident heat.
Several specific examples are provided below in conjunction with above-mentioned any embodiment：
Example one：
As shown in figure 3, this example provides a kind of information processing method, to handle the corresponding relation of previous embodiment offer,
Including：
Step S1：POD sends resource status to the nucleus module of the PSME and collects request；
Step S2：PSME returns to resource state information to POD；
Step S3：POD indicates storage resource corresponding to processing node distribution according to the resource state information；
Step S4：PSME nucleus module records the node identification of the processing node and the resource mark of the storage resource
Know, form corresponding relation；
Step S5：The GAM modules of the PSME notify the corresponding relation to scheduled unit the scheduled unit includes
RMM, BMC or MC or resource pool unit etc..
Step S6：Processing node is closed, and the nucleus module request POD of the PSME discharges corresponding storage resource；
Step S7：POD sends to PSME nucleus module and unbinds instruction；
Step S8：PSME discharges corresponding storage resource, and notifies the default unit.
As shown in figure 4, this example is based on aforementioned information processing method, including：
Step S11：Default unit detected incident heat；
Step S12：Default unit local search corresponding record, determining caused the corresponding place of storage resource of incident heat
Manage node；
Step S13：Default unit gives the processing node determined to send frequency reducing instruction.
Example two：
As shown in figure 5, this example provides a kind of information processing method, it is characterised in that including：
Step S21：RMM, BMC, BC or resource pool unit were detected after incident heat, and the overheat reporting events are given
GAM modules；
Step S22：Nucleus module of the GAM modules by the overheat reporting events to PSME；
Step S23：The nucleus module of the PSME is by the overheat reporting events to POD；
Step S24：The corresponding relation of the PSME nucleus modules local search resource identification and node identification, which is determined, leads
The node identification of the corresponding processing node of storage resource of overheat is caused, the node identification is returned into GAM modules；
Step S25：GAM modules send frequency reducing instruction to described RMM, BMC, BC or resource pool unit.
Example three：
As shown in fig. 6, this example provides a kind of information processing method, it is characterised in that including：
Step S31：RMM, BMC, BC or resource pool unit were detected after incident heat, and the overheat reporting events are given
GAM modules；
Step S32：Nucleus module of the GAM modules by the overheat reporting events to PSME；
Step S33：The nucleus module of the PSME is by the overheat reporting events to POD；
Step S34：Described RMM, BMC, BC or resource pool unit send inquiry request to PSME nucleus module；
Step S35：The corresponding relation of the PSME nucleus modules local search resource identification and node identification, which is determined, leads
Cause overheat storage resource it is corresponding processing node node identification, by the node identification return to described RMM, BMC, BC or
Resource pool unit；
Step S36：Described RMM, BMC, BC or resource pool unit send frequency reducing to corresponding processing node and instructed.
As shown in fig. 7, the present embodiment provides a kind of processing system, including：
Multiple processing nodes 110；
Bus subsystem 120, is connected with the processing node 110；
Memory resource pool 130, is connected by the bus subsystem 120 with the processing node 110；
Cooling subsystem 140, at least cools down the memory resource pool including being arranged on the memory resource pool position
The first cooling subsystem 141；
Subsystem 150 is managed, respectively with the bus subsystem 120, memory resource pool 130, cooling subsystem 140 and institute
State processing node 110 to connect, for described when detecting when crossing incident heat of the memory resource pool when detecting, it is determined that causing
First storage resource for crossing incident heat corresponding first handles node；Frequency reducing instruction is sent to the first processing node, wherein,
The frequency reducing instruction, the working frequency for reducing the processing node.
First storage resource is the part resource in the resource pool in the present embodiment, the first processing node
For one in the multiple processing node.
Subsystem 150 is managed in the present embodiment, can be detected incident heat, when detecting incident heat, be determined and lead
Some storage resource or a certain region is caused to store the processing node of overheat.In order to reduce the problems of excessive heat of correspondence storage resource,
Frequency reducing instruction can be sent to the processing node determined in the present embodiment.So that corresponding processing node carries out down conversion process.
In certain embodiments, if the management subsystem 150 is found, although detected incident heat, but current institute
State cooling subsystem 140 and be the maximum cooling power of work, then the maximum cooling power of the cooling subsystem is lifted, by cold
But the cooling to storage resource is realized in the cooling of system.If the management subsystem 150 is found, incident heat was detected and described
Cooling subsystem has worked maximum cooling power, it is determined that go out the first processing node, described by frequency reducing instruction reduction
The working frequency of first processing node.
Described in the present embodiment to manage subsystem 150, it is the processing node distribution storage resource to be additionally operable to dynamic, and
Dynamic updates the node identification of the processing node and is the corresponding relation between the resource identification of its allocated storage resource,
So that it is guaranteed that when part storage resource is overheated in memory resource pool 130, corresponding processing node can be navigated to, so as to pass through
The working frequency of reduction processing node, reaches the purpose cooled to the storage resource.
In certain embodiments, the management subsystem includes：
PSME, for when for n-th processing the n-th storage resource of node distribution, the n-th processing node and described n-th to be deposited
The corresponding relation of resource is stored up, wherein, the n is the positive integer less than N；The N is that the processing system includes the processing section
The total number of point.
In further embodiments.The management subsystem also includes：
Default unit, the default unit includes：At least one of BMC, MC, RMM and resource pool administrative unit；
The PSEM, is additionally operable to the resource mark by the node identification of the described n-th processing node and n-th storage resource
Know, correspondence is sent to default unit；
The default unit, the node identification and n-th storage resource of the n-th processing node are stored for correspondence
Resource identification, forms the corresponding relation, and when detecting the incident heat excessively, corresponding relation described in local search determines institute
State the first processing node.
The processing system that the present embodiment is provided, can be the information processing method that is provided applied to any one foregoing embodiment
System, can by aforementioned operation, reduce storage resource hot-spot phenomenon.
, can be by it in several embodiments provided herein, it should be understood that disclosed apparatus and method
Its mode is realized.Apparatus embodiments described above are only schematical, for example, the division of the unit, is only
A kind of division of logic function, can have other dividing mode, such as when actually realizing：Multiple units or component can be combined, or
Another system is desirably integrated into, or some features can be ignored, or do not perform.In addition, shown or discussed each composition portion
Coupling point each other or direct-coupling or communication connection can be the INDIRECT COUPLINGs of equipment or unit by some interfaces
Or communication connection, can be electrical, machinery or other forms.
The above-mentioned unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can positioned at a place, can also be distributed to multiple network lists
In member；Part or all of unit therein can be selected to realize the purpose of this embodiment scheme according to the actual needs.
In addition, each functional unit in various embodiments of the present invention can be fully integrated into a processing module, also may be used
Be each unit individually as a unit, can also two or more units it is integrated in a unit；It is above-mentioned
Integrated unit can both be realized in the form of hardware, it would however also be possible to employ hardware adds the form of SFU software functional unit to realize.
One of ordinary skill in the art will appreciate that：Realizing all or part of step of above method embodiment can pass through
Programmed instruction related hardware is completed, and foregoing program can be stored in a computer read/write memory medium, the program
Upon execution, the step of including above method embodiment is performed；And foregoing storage medium includes：It is movable storage device, read-only
Memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or
Person's CD etc. is various can be with the medium of store program codes.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of information processing method, it is characterised in that applied in processing system, wherein, the processing system includes：It is multiple
Handle node and handle node memory resource pool with described；Methods described includes：
When detecting when crossing incident heat of the memory resource pool, it is determined that causing the first storage resource correspondence for crossing incident heat
First processing node；
Frequency reducing instruction is sent to the first processing node, wherein, the frequency reducing instruction, the work frequency for reducing the processing node
Rate.
2. according to the method described in claim 1, it is characterised in that
Methods described also includes：
For n-th processing the n-th storage resource of node distribution when, cell system administrative unit PSME record it is described n-th processing node and
The corresponding relation of n-th storage resource, wherein, the n is the positive integer less than N；The N includes institute for the processing system
State the total number of processing node；
It is described when detect the memory resource pool cross incident heat when, it is determined that cause it is described cross incident heat the first storage resource
Corresponding first processing node, including：
The corresponding relation is inquired about, it is determined that causing the first processing node.
3. method according to claim 2, it is characterised in that
It is described record it is described n-th processing node and n-th storage resource corresponding relation, including：
The node identification of described n-th processing node and the resource identification of n-th storage resource, correspondence are sent to by the PSME
Default unit, wherein, the default unit includes substrate manager BMC, Management Controller MC, Distant supervision and control unit
At least one of RMM and resource pool administrative unit；
The node identification of default unit correspondence storage the n-th processing node and the resource identification of n-th storage resource,
Form the corresponding relation；
The inquiry corresponding relation, it is determined that cause the first processing node, including：
When detecting the incident heat excessively, corresponding relation described in the default unit local search determines first processing
Node.
4. method according to claim 2, it is characterised in that
It is described when detect the memory resource pool cross incident heat when, it is determined that cause it is described cross incident heat the first storage resource
Corresponding first processing node, including：
Receive default unit and send take described and cross incident heat, wherein, it is described cross incident heat and carry cause described to cross incident heat
The first storage resource resource identification, wherein, the default unit includes substrate manager BMC, Management Controller MC, long-range
At least one of monitoring and administrative unit and resource pool administrative unit；
The PSME inquires about described right after the incident heat excessively is received according to the resource identification of first storage resource
It should be related to and determine the first processing node.
5. method according to claim 4, it is characterised in that
Methods described also includes：
The node identification of described first processing node is sent to universal resource management GAM modules by the PSME；
It is described to send frequency reducing instruction to the first processing node, including：
The GAM modules send frequency reducing instruction to the described first processing node.
6. method according to claim 4, it is characterised in that
Methods described also includes：
The node identification of described first processing node is sent to the default unit by the PSME；
It is described to send frequency reducing instruction to the first processing node, including：
The default unit sends frequency reducing instruction to the described first processing node.
7. method according to claim 2, it is characterised in that
It is described when detect the memory resource pool cross incident heat when, it is determined that cause it is described cross incident heat the first storage resource
Corresponding first processing node, including：
When detecting when crossing incident heat of the memory resource pool, default unit sends resource to the PSME and carries described the
The inquiry request of the resource identification of one storage resource, wherein, the default unit includes substrate manager BMC, Management Controller
At least one of MC, Distant supervision and control unit and resource pool administrative unit；
Receive the inquiry response for the node identification for carrying the first processing node that the PSME is returned based on the inquiry request；
It is described to send frequency reducing instruction to the first processing node, including：
The default unit sends the frequency reducing according to the node identification, to the described first processing node and instructed.
8. a kind of processing system, it is characterised in that including：
Multiple processing nodes；
Bus subsystem, is connected with the processing node；
Memory resource pool, is connected by the bus subsystem with the processing node；
Cooling subsystem, including it is arranged on the first cooling that the memory resource pool position cools down the memory resource pool
System；
Subsystem is managed, is connected respectively with the bus subsystem, memory resource pool, cooling subsystem and the processing node,
For described when detecting the incident heat excessively of the memory resource pool when detecting, it is determined that causing the first of the incident heat excessively
The corresponding first processing node of storage resource；Frequency reducing instruction is sent to the first processing node, wherein, the frequency reducing instruction is used for
The working frequency of the reduction processing node.
9. processing system according to claim 8, it is characterised in that
The management subsystem includes：
Cell system administrative unit PSME, for for n-th processing the n-th storage resource of node distribution when, it is described n-th processing node and
The corresponding relation of n-th storage resource, wherein, the n is the positive integer less than N；The N includes institute for the processing system
State the total number of processing node.
10. processing system according to claim 9, it is characterised in that
The management subsystem also includes：
Default unit, the default unit includes：Substrate manager BMC, Management Controller MC, Distant supervision and control unit
At least one of RMM and resource pool administrative unit；
The PSEM, is additionally operable to the resource identification by the node identification of the described n-th processing node and n-th storage resource, right
Default unit should be sent to；
The default unit, the node identification of the n-th processing node and the resource of n-th storage resource are stored for correspondence
Mark, forms the corresponding relation, when detect it is described cross incident heat when, corresponding relation described in local search determines described the
One processing node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710162192.XA CN107066334A (en) | 2017-03-17 | 2017-03-17 | Information processing method and processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710162192.XA CN107066334A (en) | 2017-03-17 | 2017-03-17 | Information processing method and processing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107066334A true CN107066334A (en) | 2017-08-18 |
Family
ID=59620645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710162192.XA Pending CN107066334A (en) | 2017-03-17 | 2017-03-17 | Information processing method and processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107066334A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113326099A (en) * | 2021-06-25 | 2021-08-31 | 深信服科技股份有限公司 | Resource management method, device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101681450A (en) * | 2007-06-13 | 2010-03-24 | 佳能株式会社 | Calculation processing apparatus and control method thereof |
| CN103176748A (en) * | 2011-12-05 | 2013-06-26 | 希捷科技有限公司 | Environmental-based device operation |
| CN103403689A (en) * | 2012-07-30 | 2013-11-20 | 华为技术有限公司 | Resource failure management method, device and system |
-
2017
- 2017-03-17 CN CN201710162192.XA patent/CN107066334A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101681450A (en) * | 2007-06-13 | 2010-03-24 | 佳能株式会社 | Calculation processing apparatus and control method thereof |
| CN103176748A (en) * | 2011-12-05 | 2013-06-26 | 希捷科技有限公司 | Environmental-based device operation |
| CN103403689A (en) * | 2012-07-30 | 2013-11-20 | 华为技术有限公司 | Resource failure management method, device and system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113326099A (en) * | 2021-06-25 | 2021-08-31 | 深信服科技股份有限公司 | Resource management method, device, electronic equipment and storage medium |
| CN113326099B (en) * | 2021-06-25 | 2022-08-05 | 深信服科技股份有限公司 | Resource management method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101022363B (en) | Network storage equipment fault protecting method and device | |
| US7093011B2 (en) | Storage network system, managing apparatus, managing method and program | |
| CN101425022B (en) | Dynamic allocation of virtual machine devices | |
| US8103771B2 (en) | Distributing processing apparatus, method, and system | |
| US7904651B2 (en) | Storage device with disk power control based on logical storage area | |
| CN100424626C (en) | Method and system for power management in a distributed file system | |
| EP3070591A1 (en) | Cold and hot data identification threshold calculation method, apparatus and system | |
| CN101673192B (en) | Method for time-sequence data processing, device and system therefor | |
| CN109861878A (en) | The monitoring method and relevant device of the topic data of kafka cluster | |
| KR100489690B1 (en) | Method for procesing event and controlling real error and modeling database table | |
| DE60313040T2 (en) | UNIVERSAL MULTI-DRIVER FOR STORAGE SYSTEMS | |
| CN102763083A (en) | Computer system and its modification method | |
| JP4117656B2 (en) | Storage device for learning access patterns | |
| CN101019097A (en) | Method of managing a distributed storage system | |
| US9703666B2 (en) | Method, apparatus and software for managing the generation of process events by a software process | |
| CN107066334A (en) | Information processing method and processing system | |
| CN104504348B (en) | A kind of data guard method based on high availability storage system | |
| JPH11143779A (en) | Paging processing system for virtual storage device | |
| CN108089934A (en) | Cluster management method and cluster server | |
| US20090089432A1 (en) | Information processing system and control method thereof | |
| JP2005011331A (en) | Load balancing system and computer management program | |
| JP4342795B2 (en) | Supervisory control device | |
| WO2002027463A2 (en) | Virtual tape libraries | |
| CN114828579B (en) | Energy-saving control method of container data center and related equipment | |
| WO2002052444A2 (en) | Method and apparatus for distributing and reusing object identifiers |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |