WO2015123999A1 - 存储资源调度方法及存储计算系统 - Google Patents

存储资源调度方法及存储计算系统 Download PDF

Info

Publication number
WO2015123999A1
WO2015123999A1 PCT/CN2014/089540 CN2014089540W WO2015123999A1 WO 2015123999 A1 WO2015123999 A1 WO 2015123999A1 CN 2014089540 W CN2014089540 W CN 2014089540W WO 2015123999 A1 WO2015123999 A1 WO 2015123999A1
Authority
WO
WIPO (PCT)
Prior art keywords
task type
storage
computing system
module
computing
Prior art date
Application number
PCT/CN2014/089540
Other languages
English (en)
French (fr)
Inventor
王黎
Original Assignee
华为技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP14883281.9A priority Critical patent/EP3101870A4/en
Publication of WO2015123999A1 publication Critical patent/WO2015123999A1/zh
Priority to US15/245,807 priority patent/US10241835B2/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/0604—Improving or facilitating administration, e.g. storage management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/061—Improving I/O performance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0629—Configuration or reconfiguration of storage systems
    • G06F3/0631—Configuration or reconfiguration of storage systems by allocating resources to storage systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
    • G06F3/0659—Command handling arrangements, e.g. command buffers, queues, command scheduling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
    • G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Definitions

  • the embodiments of the present invention relate to computer technologies, and in particular, to a storage resource scheduling method and a storage computing system.
  • Service-Level Agreement refers to a mutually agreed agreement between the provider and the user on the quality and level of service, and expresses the quality of service (QoS) from the perspective of the user.
  • QoS quality of service
  • the storage resource is generally scheduled and managed in the following manner: the storage system and the computing system are relatively independent, and the storage system provides the storage unit to the computing system, and uses the storage unit as the granularity to the storage resource.
  • Manage Specifically, the computing unit in the computing system, such as a virtual machine (VM), corresponds to different storage units, and the SLA level is configured for each VM according to QoS, and the storage system optimizes and manages each storage unit according to the SLA level.
  • VM virtual machine
  • the SLA level is configured for each VM according to QoS
  • the storage system optimizes and manages each storage unit according to the SLA level.
  • only resources between different storage units can be processed and scheduled.
  • Embodiments of the present invention provide a storage resource scheduling method and a storage computing system.
  • an embodiment of the present invention provides a storage resource scheduling method, which is applicable to a storage computing system having a computing system and a storage system, where the computing system has at least one computing unit, and the storage system has at least one storage unit.
  • the method includes:
  • the computing system identifies the The task type of the computing unit
  • the computing system sends task type information to the storage system, where the task type information carries the task type;
  • the storage system acquires a scheduling policy of the task type according to the task type information
  • the storage system schedules the storage unit corresponding to the computing unit according to the scheduling policy.
  • the scheduling policy is specifically a storage service level of the task type, and the storage system stores a correspondence between the task type and the storage service level;
  • the storage system acquires a scheduling policy of the task type according to the task type information, including:
  • the storage system searches for the corresponding relationship according to the task type information, and determines a storage service level of the task type.
  • the task type information further carries a service level of the computing unit
  • the storage system acquires a scheduling policy of the task type according to the task type information, including:
  • the scheduling policy is specifically a performance indicator
  • the storage system acquires a scheduling policy of the task type according to the task type information, including:
  • the storage system generates the performance indicator for the task type according to the task type information.
  • the computing system Before the system sends the task type information, it also includes:
  • the computing system establishes a communication interface between the computing system and the storage system;
  • the computing system sends the task type information to the storage system, including:
  • the computing system transmits the task type information to the storage system through the communication interface.
  • the computing system Before the system sends the task type information, it also includes:
  • the computing system configures a configuration file for communication between the computing system and the storage system
  • the computing system sends the task type information to the storage system, including:
  • the computing system carries the task type information in the configuration file and sends the information to the storage system.
  • an embodiment of the present invention provides a storage resource scheduling method, which is applicable to a storage computing system having a computing system and a storage system, where the computing system has at least one computing unit, and the storage system has at least one storage unit.
  • the method includes:
  • the computing system identifies a task type of the computing unit
  • the computing system acquires a scheduling policy of the task type according to the task type
  • the computing system sends a scheduling policy of the task type to the storage system
  • the storage system schedules the storage unit corresponding to the computing unit according to the scheduling policy.
  • the scheduling policy is specifically a storage service level of the task type, and the computing system stores a correspondence between the task type and the storage service level;
  • the computing system acquires the scheduling policy of the task type according to the task type, and the computing system searches for the corresponding relationship according to the task type, and determines a storage service level of the task type.
  • the computing system acquires a scheduling policy of the task type according to the task type, including:
  • the computing system determines operation information corresponding to the task type; and according to the operation information, processes a service level of the computing unit to obtain a scheduling policy of the task type.
  • the scheduling policy is specifically a performance indicator
  • the computing system acquires a scheduling policy of the task type according to the task type, including:
  • the computing system generates the performance indicator for the task type according to the task type.
  • an embodiment of the present invention provides a storage computing system, including a computing system and a storage system, the computing system having at least one computing unit, the storage system having at least one storage unit, the computing system further including an identifier a module and a sending module, where the storage system further includes a task parsing module and a service quality module; wherein
  • the identifier module is configured to identify, for any one of the at least one computing unit, a task type of the computing unit;
  • the sending module is configured to send task type information to a task parsing module of the storage system, where the task type information carries the task type;
  • the task parsing module is configured to acquire a scheduling policy of the task type according to the task type information
  • the QoS module is configured to schedule, according to the scheduling policy that is parsed by the task parsing module, a storage unit corresponding to the computing unit.
  • the storage system when the scheduling policy is specifically a storage service level of the task type, the storage system further includes a storage module, configured to store the task type and the Corresponding relationship of storage service levels;
  • the task parsing module is configured to search the corresponding relationship stored by the storage module according to the task type information, and determine a storage service level of the task type.
  • the task parsing module is specifically configured to determine operation information corresponding to the task type according to the task type information, and process a service level of the computing unit according to the operation information to obtain a scheduling of the task type. Strategy.
  • the task parsing module is specifically configured to generate the performance indicator for the task type according to the task type information.
  • the computing system further includes: a communication interface establishing module;
  • the communication interface establishing module is configured to establish a communication interface between the computing system and the storage system;
  • the sending module is specifically configured to send the task type information to the storage system by using the communication interface established by the communication interface establishing module.
  • the computing system further includes: configuring Module
  • the configuration module is configured to configure a configuration file for communication between the computing system and the storage system;
  • the sending module is configured to carry the task type information in the configuration file configured by the configuration module, and send the information to the storage system.
  • an embodiment of the present invention provides a storage computing system, including a computing system and a storage system, the computing system having at least one computing unit, the storage system having at least one storage unit, the computing system further including identification a mapping module and a sending module, where the storage system further includes a quality of service module;
  • the identification mapping module is configured to identify, for any one of the at least one computing unit, a task type of the computing unit, and obtain a scheduling policy of the task type according to the task type;
  • the sending module is configured to send a scheduling policy of the task type to a quality of service module of the storage system
  • the QoS module is configured to schedule, according to the scheduling policy sent by the sending module, a storage unit corresponding to the computing unit.
  • the computing system when the scheduling policy is specifically a storage service level of the task type, the computing system further includes a storage module, configured to store the task type and the Corresponding relationship of storage service levels;
  • the identification mapping module determines, according to the task type, the storage service level of the task type according to the correspondence relationship stored by the storage module.
  • the identifying the mapping module is specifically used Determining operation information corresponding to the task type; processing, according to the operation information, a service level of the computing unit to obtain a scheduling policy of the task type.
  • the identifying mapping module is specifically configured to generate the performance for the task type according to the task type. index.
  • the computing system identifies the task type of the computing unit, the computing system sends the task type information to the storage system, and the task type information carries the task type; the storage system according to the task
  • the type information is configured to configure a scheduling policy for the task type.
  • the storage system schedules the storage unit corresponding to the computing unit according to the scheduling policy.
  • the computing system identifies the task type of the computing unit and obtains a scheduling policy based on the task type. Then, the scheduling policy is sent to the storage system, so that the storage system schedules the storage unit corresponding to the computing unit.
  • resource scheduling is performed for the task type, and scheduling management under different tasks of the same storage unit is implemented.
  • FIG. 1 is a schematic structural diagram of a storage computing system to which a storage resource scheduling method according to the present invention is applied;
  • Embodiment 1 of a storage resource scheduling method according to the present invention
  • FIG. 3 is another schematic structural diagram of a storage computing system to which the storage resource scheduling method of the present invention is applied;
  • Embodiment 4 is a flowchart of Embodiment 2 of a storage resource scheduling method according to the present invention.
  • FIG. 5 is a schematic diagram of a process of a third embodiment of a storage resource scheduling method according to the present invention.
  • Embodiment 1 of a storage computing system according to the present invention
  • Embodiment 7 is a schematic structural diagram of Embodiment 2 of a storage computing system according to the present invention.
  • Embodiment 3 of a storage computing system is a schematic structural diagram of Embodiment 3 of a storage computing system according to the present invention.
  • Embodiment 4 of a storage computing system is a schematic structural diagram of Embodiment 4 of a storage computing system according to the present invention.
  • Embodiment 9 is a schematic structural diagram of Embodiment 5 of a storage computing system according to the present invention.
  • Embodiment 6 is a schematic structural diagram of Embodiment 6 of a storage computing system according to the present invention.
  • Embodiment 7 of a storage computing system according to the present invention.
  • FIG. 12 is a schematic structural diagram of Embodiment 8 of a storage computing system according to the present invention.
  • FIG. 1 is a schematic structural diagram of a storage computing system to which a storage resource scheduling method according to the present invention is applied.
  • a storage computing system such as a cloud system, is generally composed of three major resources: a computing system, a storage system, and a network (not shown).
  • the computing system has at least one computing unit, such as a virtual machine (Virtual Machine, VM), etc., can run different applications on the computing unit, such as database, virtual device interface (VDI), mailbox service, etc.; physical device of the storage system can be server, network attached storage (Network Attached Storage, NAS A storage area network (Storage Area Networking, SAN) or the like, the storage system manages the storage resources by using a storage unit as a granularity, and the storage unit is, for example, a volume (volume, a file) or a host.
  • SAN Storage Area Networking
  • the computing storage system is divided into a computing system and a storage system from a logical point of view. However, in actual deployment, the computing system and the storage system may be deployed independently or in a virtualized manner.
  • Technology providing virtual services to the outside world, such as cloud hosting.
  • FIG. 2 is a flowchart of Embodiment 1 of a storage resource scheduling method according to the present invention. As described in detail in conjunction with FIG. 1 and FIG. 2, the embodiment includes the following steps:
  • the computing system identifies a task type of the computing unit.
  • an identification module is deployed on the computing system for identifying the task type of any computing unit of the computing system.
  • the identification module of the computing system identifies the task type of the VM, and the task includes an operation task or an application service of the VM, where the operation tasks include but are not limited to: VM startup, restart, creation, deletion, migration Or wake up, application services include but are not limited to: VM anti-virus, backup, or remote replication disaster recovery.
  • the identity module identifies the current task type of the VM.
  • the computing system sends task type information to the storage system, where the task type information carries the task type.
  • the computing system After the current task type of the VM is identified, the computing system sends the task type information carrying the task type to the storage system, where the task type information includes but is not limited to the ID of the VM (IDentity, ID), the operation task of the VM, or the application service. Types of.
  • the task type information may further include an SLA level of the VM and the like.
  • the storage system acquires a scheduling policy of the task type according to the task type information.
  • a task parsing module is configured on the storage system to parse the task type information sent by the computing system, and obtain a scheduling policy for the task type carried in the task type information.
  • the scheduling policy is, for example, an SLA level of a storage unit corresponding to the computing unit, a performance requirement of the storage unit, and the like.
  • the user can set or modify the scheduling policy of the task type of different computing units by using a configuration interface, a configuration command, a configuration file parameter, or a system default.
  • the storage system schedules, according to the scheduling policy, a storage unit corresponding to the computing unit.
  • a QoS module is configured on the storage system, and is configured to perform scheduling on a storage unit corresponding to the computing unit according to a scheduling policy. Specifically, the QoS module performs performance management and resource scheduling on the managed computing unit, such as a Lun, file, or host, according to a scheduling policy, to satisfy the user's service quality and service level.
  • the scheduling may include, but is not limited to, service migration, service restriction, traffic control, resource scheduling, and the like.
  • the storage resource scheduling method provided by the embodiment of the present invention, for any computing unit, the computing system identifies the task type of the computing unit, the computing system sends the task type information to the storage system, and the task type information carries the task type; the storage system obtains the task type information according to the task type information.
  • the scheduling type of the task type is scheduled according to the scheduling policy, and the storage unit corresponding to the computing unit is scheduled.
  • resource scheduling is performed for the task type, and scheduling management under different tasks of the same storage unit is realized.
  • the computing system establishes a communication interface between the computing system and the storage system, and the computing system sends the task type information to the storage system through the communication interface.
  • the communication interface can be configured between the computing system and the storage system through a specific protocol, and the task type information and the like are transmitted through the communication interface.
  • the computing system configures a configuration file that communicates between the computing system and the storage system, and the computing system carries the task type information in the configuration file and sends the configuration file to the storage.
  • task type information is passed through a configuration file such as XML.
  • the identification module, the task analysis module, the service quality module, and the like which are newly added to implement the present invention, can be flexibly deployed, and the present invention is not limited thereto.
  • both the identification module and the task resolution module can be deployed on the computing system side.
  • Figure 3 Please refer to Figure 3.
  • FIG. 3 is another schematic structural diagram of a storage computing system to which the storage resource scheduling method of the present invention is applied.
  • the identification module and the task analysis module are functionally integrated, and the two modules are combined into one “identification mapping module” and deployed on the computing system side.
  • the identification mapping module is configured to complete the operation task of the VM and the service type of the service application, and directly complete the acquisition of the scheduling policy of the storage unit corresponding to the computing unit on the computing system side, and then pass the message interface or configuration.
  • the scheduling policy is sent to the storage system, and the service quality module of the storage system performs corresponding performance management scheduling. Therefore, in this embodiment, the computing system side obtains the scheduling policy for the storage unit corresponding to the computing unit according to the task type, and does not need to send the task type information to the storage system.
  • an embodiment of the present invention further provides a storage resource scheduling method. See Figure 4 for details.
  • FIG. 4 is a flowchart of Embodiment 2 of a storage resource scheduling method according to the present invention.
  • the present embodiment is equally applicable to a storage computing system having a computing system and a storage system, the computing system having at least one computing unit having at least one storage unit, in conjunction with the detailed description of FIGS. 3 and 4, the present implementation Examples include the following steps:
  • the computing system identifies a task type of the computing unit.
  • an identification mapping module is disposed on the computing system for identifying the task type of any computing unit of the computing system.
  • the task type For the related description of the task type, refer to step 101 in Figure 2 above, and details are not described herein again.
  • the computing system acquires a scheduling policy of the task type according to the task type.
  • the scheduling system of the task type is obtained by the identification mapping module deployed on the computing system.
  • the scheduling policy of the task type is obtained by the identification mapping module deployed on the computing system.
  • the computing system sends a scheduling policy of the task type to the storage system.
  • the storage system schedules, according to the scheduling policy, a storage unit corresponding to the computing unit.
  • the computing system directly sends the scheduling policy to the storage system.
  • the storage system receives the scheduling policy, and the storage unit corresponding to the computing unit according to the scheduling policy. Schedule.
  • the storage resource scheduling method provided by the embodiment of the present invention, for any computing unit, the computing system identifies the task type of the computing unit, and acquires the scheduling policy according to the task type. Then, the scheduling policy is sent to the storage system, so that the storage system schedules the storage unit corresponding to the computing unit.
  • the method by sensing different tasks of the computing unit, resource scheduling is performed for the task type, and scheduling management under different tasks of the same storage unit is realized.
  • FIG. 5 is a schematic diagram of a process of a third embodiment of a storage resource scheduling method according to the present invention.
  • the computing unit is specifically a VM, and the VM1 and the VM2 are both in the SLA level.
  • the embodiment includes the following steps:
  • the S1, the user, or the administrator allocates a virtual machine through the management interface or the self-service platform, and applies resources such as CPU, memory, and volume device from the computing system and the storage system to create a virtual machine.
  • VM1 and VM2 are created, wherein the SLA levels of VM1 and VM2 are both "high", that is, "H” (High), and the SLA level can be specified at the same time as the VM is created. Or the default configuration is generated, and the present invention is not limited thereto.
  • the storage unit corresponding to VM1 is specifically Lun1
  • the storage unit corresponding to VM2 is specifically Lun2.
  • S2 and VM1 After S2 and VM1 are started, they are in the running state.
  • the computing system sends a sleep command to VM2, so that VM2 enters the Hibernate state.
  • the identification module on the computing system identifies and records the task types of VM1 and VM2, and carries the task type in the task type information, and delivers the information to the storage system according to a certain message protocol interface or a configuration file.
  • the task type information can be expressed, for example, in Table 1.
  • Table 1 is an attribute table of the task type information of the present invention.
  • the task parsing module on the storage system obtains the task type information, analyzes and identifies the task, and obtains the scheduling policy according to the task type of the operation service or the application service of the VM, and sends the scheduling policy to the service quality module on the storage system.
  • the operation tasks are Running and Hibernate as an example.
  • the storage system pre-stores a mapping table of the correspondence between the task type and the storage service level SLA, as shown in Table 2.
  • the table 2 can be set by the user self-service, or the system default configuration.
  • the task resolution module is the storage unit corresponding to VM1, that is, the scheduling policy acquired by Lun1 is “H”; for VM2, the task resolution module is the corresponding storage unit, that is, the scheduling policy acquired by Lun2 is “M”. "(Medium). In Table 2, the scheduling policy is "L” (Low), which is indicated as low.
  • the service quality module on the storage system manages and schedules the storage units corresponding to each VM according to the scheduling policy, and uses the Lun as the granularity to uniformly manage the resources of the storage system, allocate resources reasonably, and achieve QoS and SLA requirements to satisfy users.
  • the QoS module is guaranteed according to the policy of “H”
  • the QoS module performs scheduling guarantee according to the “M” policy, which is compared with the prior art.
  • the embodiment of the present invention may implement the purpose of scheduling the VM according to different task types of the VM.
  • the storage system may store corresponding VMs according to task types of different VMs.
  • the storage unit performs intelligent scheduling to realize intelligent scheduling management of storage units under different tasks, so as to ensure the protection of key services and the priority protection of key operational tasks, thereby rationally allocating resources. For example, when a VM is created in batches, a large amount of IO is generated, which affects the online experience of the user who is running the VM, but the business type of the task type itself that creates the VM may not be high. Therefore, with the present invention, the priority of the task type can be distinguished, and the problem can be effectively solved to avoid the impact of the batch operation on the online user.
  • the mapping relationship between the task type and the scheduling policy is static, as shown in Table 2, however, the present invention is not limited thereto.
  • the task type corresponds to The scheduling policy can be dynamically configured.
  • the storage system may determine the operation information corresponding to the task type according to the task type information, and According to the operation information, the service unit SLA of the calculation unit itself is processed to obtain a scheduling policy of the task type.
  • Table 3 which is a mapping table of the correspondence between the task type and the storage service level SLA in the third embodiment of the storage resource scheduling method of the present invention.
  • the storage system acquires a scheduling policy of the task type according to the SLA level of the VM itself and the task type, so that the service quality module performs scheduling management on the storage unit corresponding to the computing unit according to the scheduling policy.
  • the corresponding storage unit process is not managed according to the fixed mode, but the VM's own SLA level and task type are combined with the VM. The corresponding storage unit is scheduled.
  • the SLA level of VM1 is “H” and the SLA level of VM2 is “M”, according to Table 3, the task type of VM is also created, and the SLA level of VM1 is “downgraded”, so that VM1 corresponds to storage.
  • the scheduling policy of the unit is “M”, and the scheduling policy of the storage unit corresponding to VM2 is low, that is, “L” (Low).
  • the SLA level of the VM is operated, and if it exceeds the minimum, it is processed according to the minimum.
  • the VM2 Take VM2 as an example. If the task type is to delete the VM, the VM2's own SLA level is “M”, and after “down two levels”, it exceeds the minimum “L”. At this time, for the task type of deleting VM2, it corresponds to The scheduling policy of the storage unit is "L".
  • the scheduling policy may be a specific performance indicator or the like in addition to the foregoing SLA level, and the storage system generates a performance indicator for the task type according to the task type information.
  • performance indicators include but are not limited to the transmission rate (Million bits per second, MBPS), the number of read and write operations per second (Input / Output Operations Per Second, IOPS), business delay, input / output (Input / Output, IO The time delay, etc., the quality of service module of the storage system obtains a scheduling policy that conforms to the performance indicator according to the performance indicator.
  • Table 4 is a mapping table of the correspondence between the task type and the scheduling policy in Embodiment 4 of the storage resource scheduling method of the present invention.
  • Task number Task type Scheduling strategy Other 1 Create a VM MBPS ⁇ 30MB — 2 Delete VM IOPS ⁇ 50% — 3 Start VM constant —
  • the storage system schedules the storage unit corresponding to the computing unit according to the task type and the performance indicator.
  • the performance indicator may be fixed or relative. For example, VM1 and VM2 are deleted at the same time, the SLA level of VM1 is “H”, and the SLA level of VM2 is “L”. In this case, the level can be The performance index is set separately for the "H” and the VM of the rank "L”.
  • the manner of mapping between the task type and the scheduling policy in the above table 2 and the manner of dynamically mapping between the task type and the scheduling policy in the above Table 3, and the above table The manner in which the mapping between the task type and the scheduling policy is performed by the performance indicator is not independent. In the practical implementation mode, the combination may also be used.
  • the time can be combined with the time, and at a certain time period, for a certain time.
  • the storage unit corresponding to the VM sets the SLA level, the MBPS performance indicator, and the like for the time period.
  • FIG. 5 and Tables 1 to 4 are the detailed description of the storage computing system using the architecture shown in FIG. 1 as an example.
  • the computing system identifies the task type and sends the task. The type information is sent to the storage system, and the storage system acquires the scheduling policy according to the task type.
  • the present invention is not limited thereto. In other feasible implementation manners, for example, when the storage computing system adopts the architecture shown in FIG. 3, the computing system may also identify the task type and obtain a scheduling policy, and then directly The scheduling policy is sent to the storage system, see the detailed description of the previous embodiment.
  • FIG. 6 is a schematic structural diagram of Embodiment 1 of a storage computing system according to the present invention.
  • the storage computing system provided in this embodiment is an embodiment of the device corresponding to the embodiment of the present invention.
  • the specific implementation process is not described herein.
  • the storage computing system 1000 provided by this embodiment specifically includes: a computing system 100 and a storage system 200.
  • the computing system 100 has at least one computing unit, and the storage system 200 has at least one storage unit.
  • the computing system 100 further includes an identification module 11 and
  • the sending module 12 includes a task parsing module 21 and a QoS module 22.
  • the identifier module 11 is configured to identify, for any one of the at least one computing unit, a task type of the computing unit;
  • the sending module 12 is configured to send task type information to the task parsing module 21 of the storage system, where the task type information carries the task type;
  • the task parsing module 21 is configured to acquire a scheduling policy of the task type according to the task type information.
  • the QoS module 22 is configured to schedule, according to the scheduling policy parsed by the task parsing module 21, a storage unit corresponding to the computing unit.
  • the storage computing system provided by the embodiment of the present invention, for any computing unit, the computing system identifies the task type of the computing unit, the computing system sends the task type information to the storage system, and the task type information carries the task type; the storage system acquires the task according to the task type information.
  • the scheduling policy of the type and scheduling the storage unit corresponding to the computing unit according to the scheduling policy In the method, by sensing different tasks of the computing unit, resource scheduling is performed for the task type, and scheduling management under different tasks of the same storage unit is realized.
  • FIG. 7 is a schematic structural diagram of Embodiment 2 of a storage computing system according to the present invention.
  • the storage computing system 1000 of the present embodiment is based on the device structure of FIG. 6.
  • the scheduling policy is specifically a storage service level of the task type
  • the storage system 200 further includes a storage module 23, where The correspondence between the storage task type and the storage service level;
  • the task parsing module 21 is configured to search the corresponding relationship stored by the storage module 23 according to the task type information, and determine a storage service level of the task type.
  • the task parsing module 21 is specifically configured to determine, according to the task type information, operation information corresponding to the task type, according to the operation. Information, processing the service level of the computing unit to obtain a scheduling policy of the task type.
  • the task parsing module 21 is specifically configured to generate a performance indicator for the task type according to the task type information.
  • FIG. 8A is a schematic structural diagram of Embodiment 3 of a storage computing system according to the present invention.
  • the storage computing system 1000 of the present embodiment is based on the device structure of FIG. 6.
  • the computing system 100 further includes: a communication interface establishing module 13;
  • a communication interface establishing module 13 configured to establish a connection between the computing system and the storage system Letter interface
  • the sending module 12 is specifically configured to send task type information to the storage system by using the communication interface established by the communication interface establishing module.
  • FIG. 8B is a schematic structural diagram of Embodiment 4 of a storage computing system according to the present invention. As shown in FIG. 8B, the storage computing system 1000 of the present embodiment is based on the device structure of FIG. 6. Further, the computing system 100 further includes: a configuration module 14;
  • a configuration module 14 configured to configure a configuration file for communication between the computing system and the storage system
  • the sending module 12 is configured to carry the task type information in the configuration file configured by the configuration module, and send the information to the storage system.
  • the storage computing system shown in FIG. 8A and FIG. 8B when the scheduling policy is specifically the storage service level of the task type, optionally includes a storage module 23 for storing the correspondence between the task type and the storage service level. relationship.
  • FIG. 9 is a schematic structural diagram of Embodiment 5 of a storage computing system according to the present invention.
  • the storage computing system provided in this embodiment is an apparatus embodiment corresponding to the embodiment of FIG. 4 of the present invention, and the specific implementation process is not described herein again.
  • the storage computing system 2000 provided by this embodiment specifically includes: a computing system 300 and a storage system 400.
  • the computing system 300 has at least one computing unit, and the storage system 400 has at least one storage unit.
  • the computing system 300 further includes an identifier mapping module 31. With the sending module 32, the storage system 400 includes a quality of service module 41.
  • the identifier mapping module 31 is configured to identify, for any one of the at least one computing unit, a task type of the computing unit, and obtain a scheduling policy of the task type according to the task type;
  • the sending module 32 is configured to send a scheduling policy of the task type to the quality of service module 41 of the storage system;
  • the QoS module 41 is configured to schedule, according to the scheduling policy sent by the sending module 32, a storage unit corresponding to the computing unit.
  • the storage computing system provided by the embodiment of the present invention, for any computing unit, the computing system identifies the task type of the computing unit, and acquires the scheduling policy according to the task type. Then, the scheduling policy is sent to the storage system, so that the storage system schedules the storage unit corresponding to the computing unit.
  • the scheduling policy is sent to the storage system, so that the storage system schedules the storage unit corresponding to the computing unit.
  • resource scheduling is performed for the task type, and the same is achieved. Scheduling management of different storage units under different tasks.
  • FIG. 10 is a schematic structural diagram of Embodiment 6 of a storage computing system according to the present invention.
  • the storage computing system 2000 of the present embodiment is based on the device structure of FIG. 9.
  • the computing system 300 further includes a storage module 33, configured to store a correspondence between the task type and the storage service level;
  • the identifier mapping module 31 is configured to search the corresponding relationship stored by the storage module 33 according to the task type, and determine a storage service level of the task type.
  • the identifier mapping module 31 is specifically configured to determine operation information corresponding to the task type, and process the service level of the computing unit according to the operation information to obtain a scheduling policy of the task type.
  • the identifier mapping module 31 is specifically configured to generate the performance indicator for the task type according to the task type.
  • FIG. 11 is a schematic structural diagram of Embodiment 7 of a storage computing system according to the present invention.
  • the storage computing system 3000 provided by this embodiment includes: a processor 51 and a memory 52.
  • the storage computing system 3000 can also include a transmitter 53, a receiver 54. Transmitter 53 and receiver 54 can be coupled to processor 51.
  • the transmitter 53 is configured to transmit data or information
  • the receiver 54 is configured to receive data or information
  • the memory 52 stores execution instructions.
  • the processor 51 communicates with the memory 52, and the processor 51 calls
  • the execution instructions in the memory 52 are used to perform the method embodiments shown in FIG. 2 and FIG. 5, and the implementation principles and technical effects are similar, and details are not described herein again.
  • FIG. 12 is a schematic structural diagram of Embodiment 8 of a storage computing system according to the present invention.
  • the storage computing system 4000 provided by this embodiment includes a processor 61 and a memory 62.
  • the storage computing system 4000 can also include a transmitter 63, a receiver 64. Transmitter 63 and receiver 64 can be coupled to processor 61.
  • the transmitter 63 is configured to transmit data or information
  • the receiver 64 is configured to receive data or information
  • the memory 62 stores execution instructions.
  • the processor 61 communicates with the memory 62, and the processor 61 calls
  • the execution instructions in the memory 62 are used to perform the method embodiments shown in FIG. 4 and FIG. 5, and the implementation principles and technical effects are similar, and are not described herein again.
  • the aforementioned program can be stored in a computer Read in the storage medium.
  • the program when executed, performs the steps including the foregoing method embodiments; and the foregoing storage medium includes various media that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disk.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Software Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种存储资源调度方法及存储计算系统，该存储计算系统具有计算系统和存储系统，计算系统具有至少一个计算单元，存储系统具有至少一个存储单元，该方法包括：对于至少一个计算单元中的任一计算单元，计算系统识别计算单元的任务类型，计算系统向存储系统发送任务类型信息，任务类型信息携带任务类型；存储系统根据任务类型信息，获取任务类型的调度策略；存储系统根据调度策略，对计算单元对应的存储单元进行调度。该方法中，通过感知计算单元不同的任务，针对任务类型进行资源调度，实现对同一个存储单元不同任务下的调度管理。

Description

存储资源调度方法及存储计算系统 技术领域
本发明实施例涉及计算机技术，尤其涉及一种存储资源调度方法及存储计算系统。
背景技术
服务等级协议(Service-Level Agreement，SLA)是指提供者与用户之间就服务的品质、水准等所达成的双方共同认可的协议，从用户角度表达对服务质量(Quality of Service，QoS)的要求。云计算场景下，存储和计算作为云的两大核心资源，经过有机融合，联合对外提供各种应用。为保证重点应用的服务质量、各种应用的可预测性等，需要引入QoS机制对存储资源进行调度管理。
一般来说，现有技术中，一般采用如下方式对存储资源进行调度管理：存储系统和计算系统相对独立，分离管理，存储系统提供存储单元给计算系统使用，并以存储单元为粒度对存储资源进行管理。具体的，计算系统中的计算单元，如虚拟机(Virtual Machine，VM)等对应不同的存储单元，根据QoS预先为各VM配置SLA级别，存储系统根据SLA级别对各存储单元进行优化及性能管理。但是现有技术中，仅能够处理和调度不同存储单元间的资源。
发明内容
本发明实施例提供一种存储资源调度方法及存储计算系统。
第一个方面，本发明实施例提供一种存储资源调度方法，适用于具有计算系统和存储系统的存储计算系统，所述计算系统具有至少一个计算单元，所述存储系统具有至少一个存储单元，该方法包括：
对于所述至少一个计算单元中的任一计算单元，所述计算系统识别所述 计算单元的任务类型；
所述计算系统向所述存储系统发送任务类型信息，所述任务类型信息携带所述任务类型；
所述存储系统根据所述任务类型信息，获取所述任务类型的调度策略；
所述存储系统根据所述调度策略，对所述计算单元对应的存储单元进行调度。
在第一个方面的第一种可能的实现方式中，所述调度策略具体为所述任务类型的存储服务等级，所述存储系统存储有所述任务类型与所述存储服务等级的对应关系；
所述存储系统根据所述任务类型信息，获取所述任务类型的调度策略，包括：
所述存储系统根据所述任务类型信息查找所述对应关系，确定所述任务类型的存储服务等级。
在第一个方面的第二种可能的实现方式中，所述任务类型信息还携带所述计算单元的服务等级；
所述存储系统根据所述任务类型信息，获取所述任务类型的调度策略，包括：
所述存储系统根据所述任务类型信息，确定所述任务类型对应的操作信息；
根据所述操作信息，对所述计算单元的服务等级进行处理以得到所述任务类型的调度策略。
在第一个方面的第三种可能的实现方式中，所述调度策略具体为性能指标，所述存储系统根据所述任务类型信息，获取所述任务类型的调度策略，包括：
所述存储系统根据所述任务类型信息，为所述任务类型生成所述性能指标。
结合第一个方面、第一个方面的第一种、第二种或第三种可能的实现方式，在第一个方面的第四种可能的实现方式中，所述计算系统向所述存储系统发送所述任务类型信息之前，还包括：
所述计算系统在所述计算系统与所述存储系统之间建立通信接口；
所述计算系统向所述存储系统发送所述任务类型信息，包括：
所述计算系统通过所述通信接口向所述存储系统发送所述任务类型信息。
结合第一个方面、第一个方面的第一种、第二种或第三种可能的实现方式，在第一个方面的第五种可能的实现方式中，所述计算系统向所述存储系统发送所述任务类型信息之前，还包括：
所述计算系统配置所述计算系统与所述存储系统之间进行通信的配置文件；
所述计算系统向所述存储系统发送所述任务类型信息，包括：
所述计算系统将所述任务类型信息携带在所述配置文件中发送给所述存储系统。
第二个方面，本发明实施例提供一种存储资源调度方法，适用于具有计算系统和存储系统的存储计算系统，所述计算系统具有至少一个计算单元，所述存储系统具有至少一个存储单元，该方法包括：
对于所述至少一个计算单元中的任一计算单元，所述计算系统识别所述计算单元的任务类型；
所述计算系统根据所述任务类型，获取所述任务类型的调度策略；
所述计算系统向所述存储系统发送所述任务类型的调度策略；
所述存储系统根据所述调度策略，对所述计算单元对应的存储单元进行调度。
在第二个方面的第一种可能的实现方式中，所述调度策略具体为所述任务类型的存储服务等级，所述计算系统存储有所述任务类型与所述存储服务等级的对应关系；
所述计算系统根据所述任务类型，获取所述任务类型的调度策略，包括：所述计算系统根据所述任务类型查找所述对应关系，确定所述任务类型的存储服务等级。
在第二个方面的第二种可能的实现方式中，所述计算系统根据所述任务类型，获取所述任务类型的调度策略，包括：
所述计算系统确定所述任务类型对应的操作信息；根据所述操作信息，对所述计算单元的服务等级进行处理以得到所述任务类型的调度策略。
在第二个方面的第三种可能的实现方式中，所述调度策略具体为性能指标，所述计算系统根据所述任务类型，获取所述任务类型的调度策略，包括：
所述计算系统根据所述任务类型，为所述任务类型生成所述性能指标。
第三个方面，本发明实施例提供一种存储计算系统，包括计算系统和存储系统，所述计算系统具有至少一个计算单元，所述存储系统具有至少一个存储单元，所述计算系统还包括标识模块与发送模块，所述存储系统还包括任务解析模块与服务质量模块；其中，
所述标识模块，用于对于所述至少一个计算单元中的任一计算单元，识别所述计算单元的任务类型；
所述发送模块，用于向所述存储系统的任务解析模块发送任务类型信息，所述任务类型信息携带所述任务类型；
所述任务解析模块，用于根据所述任务类型信息，获取所述任务类型的调度策略；
所述服务质量模块，用于根据所述任务解析模块解析的所述调度策略，对所述计算单元对应的存储单元进行调度。
在第三个方面的第一种可能的实现方式中，当所述调度策略具体为所述任务类型的存储服务等级时，所述存储系统还包括存储模块，用于存储所述任务类型与所述存储服务等级的对应关系；
所述任务解析模块，具体用于根据所述任务类型信息查找所述存储模块存储的所述对应关系，确定所述任务类型的存储服务等级。
在第三个方面的第二种可能的实现方式中，当所述任务类型信息还携带所述计算单元的服务等级时，
所述任务解析模块，具体用于根据所述任务类型信息，确定所述任务类型对应的操作信息，根据所述操作信息，对所述计算单元的服务等级进行处理以得到所述任务类型的调度策略。
在第三个方面的第三种可能的实现方式中，当所述调度策略具体为性能指标时，
所述任务解析模块，具体用于根据所述任务类型信息，为所述任务类型生成所述性能指标。
结合第三个方面、第三个方面的第一种、第二种或第三种可能的实现方 式，在第三个方面的第四种可能的实现方式中，所述计算系统还包括：通信接口建立模块；
所述通信接口建立模块，用于在所述计算系统与所述存储系统之间建立通信接口；
所述发送模块，具体用于通过所述通信接口建立模块建立的所述通信接口向所述存储系统发送所述任务类型信息。
结合第三个方面、第三个方面的第一种、第二种或第三种可能的实现方式，在第三个方面的第五种可能的实现方式中，所述计算系统还包括：配置模块；
所述配置模块，用于配置所述计算系统与所述存储系统之间进行通信的配置文件；
所述发送模块，具体用于将所述任务类型信息携带在所述配置模块配置的所述配置文件中发送给所述存储系统。
第四个方面，本发明实施例提供一种存储计算系统，包括计算系统和存储系统，所述计算系统具有至少一个计算单元，所述存储系统具有至少一个存储单元，所述计算系统还包括识别映射模块与发送模块，所述存储系统还包括服务质量模块；其中，
所述识别映射模块，用于对于所述至少一个计算单元中的任一计算单元，识别所述计算单元的任务类型，并根据所述任务类型，获取所述任务类型的调度策略；
所述发送模块，用于向所述存储系统的服务质量模块发送所述任务类型的调度策略；
所述服务质量模块，用于根据所述发送模块发送的所述调度策略，对所述计算单元对应的存储单元进行调度。
在第四个方面的第一种可能的实现方式中，当所述调度策略具体为所述任务类型的存储服务等级时，所述计算系统还包括存储模块，用于存储所述任务类型与所述存储服务等级的对应关系；
所述识别映射模块，具体根据所述任务类型根据所述存储模块存储的所述对应关系，确定所述任务类型的存储服务等级。
在第四个方面的第二种可能的实现方式中，所述识别映射模块，具体用 于确定所述任务类型对应的操作信息；根据所述操作信息，对所述计算单元的服务等级进行处理以得到所述任务类型的调度策略。
在第四个方面的第三种可能的实现方式中，当所述调度策略具体为性能指标时，所述识别映射模块，具体用于根据所述任务类型，为所述任务类型生成所述性能指标。
本发明实施例提供的存储资源调度方法及存储计算系统，对于任意计算单元，计算系统识别计算单元的任务类型，计算系统向存储系统发送任务类型信息，任务类型信息携带任务类型；存储系统根据任务类型信息，为任务类型配置调度策略；存储系统根据调度策略，对计算单元对应的存储单元进行调度。或者，对于任意计算单元，计算系统识别计算单元的任务类型，并根据任务类型获取调度策略。然后，将调度策略发送给存储系统，使得存储系统对计算单元对应的存储单元进行调度。上述方法中，通过感知计算单元不同的任务，针对任务类型进行资源调度，实现对同一个存储单元不同任务下的调度管理。
附图说明
图1为本发明存储资源调度方法所适用的存储计算系统的一种架构示意图；
图2为本发明存储资源调度方法实施例一的流程图；
图3为本发明存储资源调度方法所适用的存储计算系统的另一种架构示意图；
图4为本发明存储资源调度方法实施例二的流程图；
图5为本发明存储资源调度方法实施例三的过程示意图；
图6为本发明存储计算系统实施例一的结构示意图；
图7为本发明存储计算系统实施例二的结构示意图；
图8A为本发明存储计算系统实施例三的结构示意图；
图8B为本发明存储计算系统实施例四的结构示意图；
图9为本发明存储计算系统实施例五的结构示意图；
图10为本发明存储计算系统实施例六的结构示意图；
图11为本发明存储计算系统实施例七的结构示意图；
图12为本发明存储计算系统实施例八的结构示意图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
图1为本发明存储资源调度方法所适用的存储计算系统的一种架构示意图。如图1所示，存储计算系统，例如云系统，通常由计算系统、存储系统以及网络(图中未示出)三大资源构成，计算系统具有至少一个计算单元，如虚拟机(Virtual Machine，VM)等，在计算单元上可以运行不同的应用，如数据库、虚拟设备接口(Virtual Device Interface，VDI)、邮箱服务等；存储系统的物理设备可以为服务器、网络连接存储(Network Attached Storage，NAS)、存储区域网络(Storage Area Networking，SAN)等，存储系统以存储单元为粒度对存储资源进行管理，存储单元例如为卷(volume，Lun)、文件或主机等。需要说明的是，本实施例中，是从逻辑的角度将计算存储系统划分为计算系统与存储系统的，然而，实际部署中，计算系统和存储系统可独立也可以合一部署，通过虚拟化技术，对外提供虚拟服务，如云主机等。
图2为本发明存储资源调度方法实施例一的流程图。同时结合图1与图2详细描述，本实施例包括如下步骤：
101、对于所述至少一个计算单元中的任一计算单元，所述计算系统识别所述计算单元的任务类型。
如图1所示，计算系统上部署有标识模块，用于识别计算系统的任意计算单元的任务类型。以计算单元为VM为例，计算系统的标识模块识别VM的任务类型，该任务包括VM的操作任务或应用业务，其中，操作任务包括但不限于：VM的启动、重启、创建、删除、迁移、或唤醒，应用业务包括但不限于：VM的杀毒、备份、或远程复制容灾。具体的，在计算系统进行VM管理时，标识模块识别该VM当前的任务类型。
102、所述计算系统向所述存储系统发送任务类型信息，所述任务类型信息携带所述任务类型。
在识别该VM当前的任务类型后，计算系统向存储系统发送携带任务类型的任务类型信息，该任务类型信息包括但不限于VM的身份标识(IDentity，ID)、VM的操作任务或应用业务的类型。可选地，该任务类型信息还可以包括VM的SLA等级等。
103、所述存储系统根据所述任务类型信息，获取所述任务类型的调度策略。
如图1所示，存储系统上部署有任务解析模块，用于解析计算系统发送的任务类型信息，并为该任务类型信息携带的任务类型获取调度策略。其中，调度策略例如是计算单元对应的存储单元的SLA等级、存储单元的性能需求等。具体的，用户可通过配置界面、配置命令、配置文件参数或系统默认等方式设定或修改不同计算单元的任务类型的调度策略。
104、所述存储系统根据所述调度策略，对所述计算单元对应的存储单元进行调度。
如图1所示，存储系统上部署有服务质量模块，用于按照调度策略，对计算单元对应的存储单元进行调度等。具体的，服务质量模块按照调度策略，对所管理的计算单元，如Lun、文件或主机等对象进行性能管理和资源调度以满足用户的服务质量和服务等级。其中，调度可以包含但不限于：业务迁移，业务限制，流量控制，资源调度等。
本发明实施例提供的存储资源调度方法，对于任意计算单元，计算系统识别计算单元的任务类型，计算系统向存储系统发送任务类型信息，任务类型信息携带任务类型；存储系统根据任务类型信息，获取任务类型的调度策略并根据调度策略，对计算单元对应的存储单元进行调度。该方法中，通过感知计算单元不同的任务，针对任务类型进行资源调度，实现同一个存储单元不同任务下的调度管理。
可选的，上述实施例中，计算系统在计算系统与存储系统之间建立通信接口，计算系统通过所述通信接口向存储系统发送任务类型信息。
具体的，计算系统和存储系统之间可通过具体的协议配置该通信接口，通过该通信接口传递任务类型信息等。
可选的，上述实施例中，计算系统配置计算系统与存储系统之间进行通信的配置文件，计算系统将任务类型信息携带在配置文件中发送给所述存储 系统。例如，通过XML等配置文件传递任务类型信息。
需要说明的是，上述图1所示的存储计算系统的架构示意图中，为实现本发明所新增的标识模块、任务解析模块、服务质量模块等可以灵活部署，本发明并不以此为限。例如，可以将标识模块和任务解析模块均部署于计算系统侧。具体的，请参见图3。
图3为本发明存储资源调度方法所适用的存储计算系统的另一种架构示意图。相较于图1实施例，本实施例中，对标识模块和任务解析模块进行功能合一，将该两个模块组合成一个“识别映射模块”并部署于计算系统侧。
请参照图3，识别映射模块用于完成对VM的操作任务及业务应用等业务类型的识别，并在计算系统侧直接完成计算单元对应的存储单元的调度策略的获取，然后通过消息接口或配置文件等形式，将调度策略发送给存储系统，由存储系统的服务质量模块进行相应的性能管理调度。由此可知，本实施例中，计算系统侧直接根据任务类型，为计算单元对应的存储单元获取调度策略，无需将任务类型信息发送至存储系统。
基于图3所示的存储计算系统，本发明实施例还提供一种存储资源调度方法。具体可参见图4。
图4为本发明存储资源调度方法实施例二的流程图。本实施例同样适用于具有计算系统和存储系统的存储计算系统，所述计算系统具有至少一个计算单元，所述存储系统具有至少一个存储单元，同时结合图3与图4的详细描述，本实施例包括如下步骤：
201、对于所述至少一个计算单元中的任一计算单元，所述计算系统识别所述计算单元的任务类型。
如图3所示，计算系统上部署有识别映射模块，用于识别计算系统的任意计算单元的任务类型。该步骤中，关于任务类型的相关描述可参见上述图2步骤101，此处不再赘述。
202、所述计算系统根据所述任务类型，获取所述任务类型的调度策略。
相较于上述图2中计算系统发送任务类型信息给存储系统，使得存储系统获取任务类型的调度信息，本实施例中，任务类型的调度策略由部署在计算系统上的识别映射模块获取。
203、所述计算系统向所述存储系统发送所述任务类型的调度策略。
204、所述存储系统根据所述调度策略，对所述计算单元对应的存储单元进行调度。
上述步骤203与步骤204中，在获取到任务类型的调度策略后，计算系统直接将调度策略发送给存储系统；相应的，存储系统接收调度策略，并根据该调度策略对计算单元对应的存储单元进行调度。
本发明实施例提供的存储资源调度方法，对于任意计算单元，计算系统识别计算单元的任务类型，并根据任务类型获取调度策略。然后，将调度策略发送给存储系统，使得存储系统对计算单元对应的存储单元进行调度。该方法中，通过感知计算单元不同的任务，针对任务类型进行资源调度，实现同一个存储单元不同任务下的调度管理。
图5为本发明存储资源调度方法实施例三的过程示意图。本实施例中，计算单元具体为VM，以SLA等级均为“高”的VM1、VM2为例，本实施例具体包括如下步骤：
S1、用户或管理员通过管理界面或自助服务平台分配虚拟机，从计算系统和存储系统分别申请CPU、内存、卷设备等资源从而创建虚拟机。
本步骤中，假设创建了两个虚拟机，即VM1与VM2，其中，VM1与VM2的SLA等级均为“高”，即“H”(High)，该SLA等级可在创建VM的同时指定，或者按照默认配置生成，本发明并不以此为限制，VM1对应的存储单元具体为Lun1，VM2对应的存储单元具体为Lun2。
S2、VM1启动后处于正常运行(Running)状态，计算系统对VM2下发休眠指令，使得VM2进入休眠(Hibernate)状态。
S3、计算系统上的标识模块，识别并记录VM1与VM2的任务类型，并将该任务类型携带在任务类型信息中，按照某种消息协议接口或通过配置文件等形式，传递给存储系统。
本步骤中，任务类型信息例如可以用表1表示，表1为本发明任务类型信息的属性表。
表1
VM ID SLA State State ID Other
VM1 H Running 6 ……
VM2 H Hibernate 5 ……
S4、存储系统上的任务解析模块，在接收到任务类型信息，对其解析识别后，根据VM的操作业务或应用业务等任务类型，获取调度策略并下发给存储系统上的服务质量模块。表1中，以操作任务为Running和Hibernate为例。
具体的，存储系统预先存储有任务类型与存储服务等级SLA对应关系的映射表，如表2所示。该表2可以由用户自助设定，或者系统默认配置。
结合表2，针对VM1，任务解析模块为VM1对应的存储单元，即Lun1获取的调度策略为“H”；针对VM2，任务解析模块为其对应的存储单元，即Lun2获取的调度策略为“M”(Medium)。表2中，调度策略为“L”(Low)，表示为低。
表2
任务编号 任务类型 调度策略 Other
1 创建VM M ……
2 删除VM L ……
3 启动VM H ……
4 迁移VM H ……
5 休眠VM M ……
6 Running H ……
7 备份VM L ……
8 VM杀毒 L ……
…… …… …… ……
S5、存储系统上的服务质量模块根据调度策略，以Lun为粒度，对各VM对应的存储单元进行管理调度，从而统一管理存储系统的资源，合理配置资源，达成QoS和SLA的要求，满足用户体验。例如，对于VM1对应的存储单元Lun1，服务质量模块按照“H”的策略进行保障，而对于VM2对应的存储单元Lun2，服务质量模块按照“M”的策略进行调度保障，这相对于现有技术中的仅根据VM的SLA等级对该VM对应的存储单元进行调度的方法，本发明实施例可以实现对不同任务类型的VM的细分，根据VM的不同任务类型对VM进行调度的目的。
本实施例中，存储系统可根据不同VM的任务类型，对各VM对应的存 储单元进行智能调度，实现不同任务下的存储单元的智能调度管理，做到重点业务的保障、关键操作任务的性能优先保护，从而合理调配资源。例如，批量创建VM时会产生大量IO，此时会影响正在Running的VM的用户的在线体验，但创建VM的任务类型本身的业务实时性可能并不高。因此，利用本发明，即可区分任务类型的优先级，有效解决此问题，避免批量操作对在线用户的影响。
上述图5实施例中，任务类型与调度策略之间的映射关系是静态的，例如表2所示，然而，本发明并不以此为限，在其他可能的实施方式中，任务类型对应的调度策略可动态配置。例如，当任务类型信息携带计算单元自身的服务等级SLA、调度策略具体为对任务类型对应的存储服务等级SLA的操作信息时，存储系统可根据任务类型信息，确定任务类型对应的操作信息，并根据该操作信息，对计算单元自身的服务等级SLA进行处理以得到任务类型的调度策略。具体的，可见表3，表3为本发明存储资源调度方法实施例三中任务类型与存储服务等级SLA对应关系的映射表。
表3
Figure PCTCN2014089540-appb-000001
Figure PCTCN2014089540-appb-000002
结合表3，本实施例中，存储系统根据VM本身的SLA等级以及任务类型，获取任务类型的调度策略，使得服务质量模块根据调度策略，对计算单元对应的存储单元进行调度管理。该存储资源调度过程中，相较于上述实施例，对于任意等级的VM，并非按照固定模式对其对应的存储单元进程调度管理，而是结合该VM自身的SLA等级以及任务类型，对该VM对应的存储单元进行调度。例如，VM1的SLA等级为“H”，VM2的SLA等级为“M”，则根据表3，同样是创建VM的任务类型，对VM1的SLA等级“降一级”，从而使得VM1对应的存储单元的调度策略为“M”，VM2对应的存储单元的调度策略为低，即“L”(Low)。
需要说明的是，根据表3中的操作信息，对VM的SLA等级进行操作，若超过最低，则按照最低限度处理。以VM2为例，若任务类型为删除VM，则由于VM2自身的SLA等级为“M”，“降两级”后超过最低限度“L”，此时，对于删除VM2的任务类型，对其对应的存储单元的调度策略为“L”。
另外，调度策略除了可以是上述的SLA等级外，还可以是具体的性能指标等，存储系统根据任务类型信息，为任务类型生成性能指标。其中，性能指标包括但不限于传输速率(Million bits per second，MBPS)、每秒进行读写操作的次数(Input/Output Operations Per Second，IOPS)、业务时延、输入输出(Input/Output，IO)时延等，存储系统的服务质量模块根据性能指标，对任务类型获取符合该性能指标的调度策略。具体的，可参见表4，表4为本发明存储资源调度方法实施例四中任务类型与调度策略对应关系的映射表。
表4
任务编号 任务类型 调度策略 Other
1 创建VM MBPS≤30MB ……
2 删除VM IOPS≤50％ ……
3 启动VM 不变 ……
4 迁移VM 不变 ……
5 休眠VM MBPS≤20MB ……
6 Running 不变 ……
7 备份VM 2倍延时 ……
8 VM杀毒 IOPS≤50％ ……
…… …… …… ……
结合表4，本实施例中，存储系统根据任务类型以及性能指标，对计算单元对应的存储单元进行调度。其中，该性能指标可以是固定的，也可以是相对性的，例如，同时删除VM1与VM2，VM1的SLA等级为“H”，VM2的SLA等级为“L”，此时，可以对等级为“H”与等级为“L”的VM分别设置性能指标。
另外，需要说明的是，上述表2中静态的对任务类型与调度策略之间进行映射的方式、以及上述表3中以动态的对任务类型与调度策略之间进行映射的方式、以及上述表4中通过性能指标对任务类型与调度策略之间进行映射的方式并不是独立的，在实际可行的实施方式中，也可以结合使用，例如，可配合时间生效，在某时间段，对某个VM对应的存储单元设置该时间段的SLA等级、MBPS性能指标等。
需要说明的是，上述图5以及表1-表4是以存储计算系统采用图1所示架构为例对本发明进行详细说明，其中S3、S4中是由计算系统对任务类型进行识别并发送任务类型信息给存储系统，由存储系统根据任务类型获取调度策略。然而，本发明并不以此为限制，在其他可行的实施方式中，例如，当存储计算系统采用图3所示架构时，也可由计算系统对任务类型进行识别并获取调度策略，然后，直接将调度策略发送至存储系统，参见前面实施例的具体描述。
图6为本发明存储计算系统实施例一的结构示意图。本实施例提供的存储计算系统是与本发明图2实施例对应的装置实施例，具体实现过程在此不再赘述。具体的，本实施例提供的存储计算系统1000具体包括：计算系统100和存储系统200，计算系统100具有至少一个计算单元，存储系统200具有至少一个存储单元；计算系统100还包括标识模块11与发送模块12，存储系统200包括任务解析模块21与服务质量模块22。
标识模块11，用于对于所述至少一个计算单元中的任一计算单元，识别所述计算单元的任务类型；
发送模块12，用于向所述存储系统的任务解析模块21发送任务类型信息，所述任务类型信息携带所述任务类型；
任务解析模块21，用于根据所述任务类型信息，获取所述任务类型的调度策略；
服务质量模块22，用于根据所述任务解析模块21解析的所述调度策略，对所述计算单元对应的存储单元进行调度。
本发明实施例提供的存储计算系统，对于任意计算单元，计算系统识别计算单元的任务类型，计算系统向存储系统发送任务类型信息，任务类型信息携带任务类型；存储系统根据任务类型信息，获取任务类型的调度策略并根据调度策略，对计算单元对应的存储单元进行调度。该方法中，通过感知计算单元不同的任务，针对任务类型进行资源调度，实现同一个存储单元不同任务下的调度管理。
图7为本发明存储计算系统实施例二的结构示意图。如图7所示，本实施例的存储计算系统1000在图6装置结构的基础上，进一步的，当调度策略具体为任务类型的存储服务等级时，存储系统200还包括存储模块23，用于存储任务类型与存储服务等级的对应关系；
任务解析模块21，具体用于根据所述任务类型信息查找所述存储模块23存储的所述对应关系，确定所述任务类型的存储服务等级。
可选的，当所述任务类型信息还携带所述计算单元的服务等级时，任务解析模块21，具体用于根据所述任务类型信息，确定所述任务类型对应的操作信息，根据所述操作信息，对所述计算单元的服务等级进行处理以得到所述任务类型的调度策略。
可选的，当所述调度策略具体为性能指标时，任务解析模块21，具体用于根据所述任务类型信息，为所述任务类型生成性能指标。
图8A为本发明存储计算系统实施例三的结构示意图。如图8A所示，本实施例的存储计算系统1000在图6装置结构的基础上，进一步的，计算系统100还包括：通信接口建立模块13；
通信接口建立模块13，用于在所述计算系统与所述存储系统之间建立通 信接口；
发送模块12，具体用于通过所述通信接口建立模块建立的所述通信接口向所述存储系统发送任务类型信息。
图8B为本发明存储计算系统实施例四的结构示意图。如图8B所示，本实施例的存储计算系统1000在图6装置结构的基础上，进一步的，计算系统100还包括：配置模块14；
配置模块14，用于配置所述计算系统与所述存储系统之间进行通信的配置文件；
发送模块12，具体用于将所述任务类型信息携带在所述配置模块配置的所述配置文件中发送给所述存储系统。
需要说明的是上述图8A与图8B所示的存储计算系统，当调度策略具体为任务类型的存储服务等级时，可选的还包括存储模块23，用于存储任务类型与存储服务等级的对应关系。
图9为本发明存储计算系统实施例五的结构示意图。本实施例提供的存储计算系统是与本发明图4实施例对应的装置实施例，具体实现过程在此不再赘述。具体的，本实施例提供的存储计算系统2000具体包括：计算系统300和存储系统400，计算系统300具有至少一个计算单元，存储系统400具有至少一个存储单元；计算系统300还包括标识映射模块31与发送模块32，存储系统400包括服务质量模块41。
所述标识映射模块31，用于对于所述至少一个计算单元中的任一计算单元，识别所述计算单元的任务类型，并根据所述任务类型，获取所述任务类型的调度策略；
所述发送模块32，用于向所述存储系统的服务质量模块41发送所述任务类型的调度策略；
所述服务质量模块41，用于根据所述发送模块32发送的所述调度策略，对所述计算单元对应的存储单元进行调度。
本发明实施例提供的存储计算系统，对于任意计算单元，计算系统识别计算单元的任务类型，并根据任务类型获取调度策略。然后，将调度策略发送给存储系统，使得存储系统对计算单元对应的存储单元进行调度。该方法中，通过感知计算单元不同的任务，针对任务类型进行资源调度，实现同一 个存储单元不同任务下的调度管理。
图10为本发明存储计算系统实施例六的结构示意图。如图10所示，本实施例的存储计算系统2000在图9装置结构的基础上，进一步的，当所述调度策略具体为所述任务类型的存储服务等级时，所述计算系统300还包括存储模块33，用于存储所述任务类型与所述存储服务等级的对应关系；
所述标识映射模块31，具体用于根据所述任务类型查找所述存储模块33存储的所述对应关系，确定所述任务类型的存储服务等级。
可选的，所述标识映射模块31，具体用于确定所述任务类型对应的操作信息；根据所述操作信息，对所述计算单元的服务等级进行处理以得到所述任务类型的调度策略。
可选的，当所述调度策略具体为性能指标时，所述标识映射模块31，具体用于根据所述任务类型，为所述任务类型生成所述性能指标。
图11为本发明存储计算系统实施例七的结构示意图。如图11所示，本实施例提供的存储计算系统3000，包括：处理器51和存储器52。存储计算系统3000还可以包括发射器53、接收器54。发射器53和接收器54可以和处理器51相连。其中，发射器53用于发送数据或信息，接收器54用于接收数据或信息，存储器52存储执行指令，当存储计算系统3000运行时，处理器51与存储器52之间通信，处理器51调用存储器52中的执行指令，用于执行图2和图5所示方法实施例，其实现原理和技术效果类似，此处不再赘述。
图12为本发明存储计算系统实施例八的结构示意图。如图12所示，本实施例提供的存储计算系统4000，包括：处理器61和存储器62。存储计算系统4000还可以包括发射器63、接收器64。发射器63和接收器64可以和处理器61相连。其中，发射器63用于发送数据或信息，接收器64用于接收数据或信息，存储器62存储执行指令，当存储计算系统4000运行时，处理器61与存储器62之间通信，处理器61调用存储器62中的执行指令，用于执行图4和图5所示方法实施例，其实现原理和技术效果类似，此处不再赘述。
本领域普通技术人员可以理解：实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储于一计算机可 读取存储介质中。该程序在执行时，执行包括上述各方法实施例的步骤；而前述的存储介质包括：ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是：以上各实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述各实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。

Claims (20)

  1. 一种存储资源调度方法，其特征在于，适用于具有计算系统和存储系统的存储计算系统，所述计算系统具有至少一个计算单元，所述存储系统具有至少一个存储单元，该方法包括：
    对于所述至少一个计算单元中的任一计算单元，所述计算系统识别所述计算单元的任务类型；
    所述计算系统向所述存储系统发送任务类型信息，所述任务类型信息携带所述任务类型；
    所述存储系统根据所述任务类型信息，获取所述任务类型的调度策略；
    所述存储系统根据所述调度策略，对所述计算单元对应的存储单元进行调度。
  2. 根据权利要求1所述的方法，其特征在于，所述调度策略具体为所述任务类型的存储服务等级，所述存储系统存储有所述任务类型与所述存储服务等级的对应关系；
    所述存储系统根据所述任务类型信息，获取所述任务类型的调度策略，包括：
    所述存储系统根据所述任务类型信息查找所述对应关系，确定所述任务类型的存储服务等级。
  3. 根据权利要求1所述的方法，其特征在于，所述任务类型信息还携带所述计算单元的服务等级；
    所述存储系统根据所述任务类型信息，获取所述任务类型的调度策略，包括：
    所述存储系统根据所述任务类型信息，确定所述任务类型对应的操作信息；
    根据所述操作信息，对所述计算单元的服务等级进行处理以得到所述任务类型的调度策略。
  4. 根据权利要求1所述的方法，其特征在于，所述调度策略具体为性能指标，所述存储系统根据所述任务类型信息，获取所述任务类型的调度策略，包括：
    所述存储系统根据所述任务类型信息，为所述任务类型生成所述性能指 标。
  5. 根据权利要求1～4任一项所述的方法，其特征在于，所述计算系统向所述存储系统发送所述任务类型信息之前，还包括：
    所述计算系统在所述计算系统与所述存储系统之间建立通信接口；
    所述计算系统向所述存储系统发送所述任务类型信息，包括：
    所述计算系统通过所述通信接口向所述存储系统发送所述任务类型信息。
  6. 根据权利要求1～4任一项所述的方法，其特征在于，所述计算系统向所述存储系统发送所述任务类型信息之前，还包括：
    所述计算系统配置所述计算系统与所述存储系统之间进行通信的配置文件；
    所述计算系统向所述存储系统发送所述任务类型信息，包括：
    所述计算系统将所述任务类型信息携带在所述配置文件中发送给所述存储系统。
  7. 一种存储资源调度方法，其特征在于，适用于具有计算系统和存储系统的存储计算系统，所述计算系统具有至少一个计算单元，所述存储系统具有至少一个存储单元，该方法包括：
    对于所述至少一个计算单元中的任一计算单元，所述计算系统识别所述计算单元的任务类型；
    所述计算系统根据所述任务类型，获取所述任务类型的调度策略；
    所述计算系统向所述存储系统发送所述任务类型的调度策略；
    所述存储系统根据所述调度策略，对所述计算单元对应的存储单元进行调度。
  8. 根据权利要求7所述的方法，其特征在于，所述调度策略具体为所述任务类型的存储服务等级，所述计算系统存储有所述任务类型与所述存储服务等级的对应关系；
    所述计算系统根据所述任务类型，获取所述任务类型的调度策略，包括：所述计算系统根据所述任务类型查找所述对应关系，确定所述任务类型的存储服务等级。
  9. 根据权利要求7所述的方法，其特征在于，所述计算系统根据所述任 务类型，获取所述任务类型的调度策略，包括：
    所述计算系统确定所述任务类型对应的操作信息；根据所述操作信息，对所述计算单元的服务等级进行处理以得到所述任务类型的调度策略。
  10. 根据权利要求7所述的方法，其特征在于，所述调度策略具体为性能指标，所述计算系统根据所述任务类型，获取所述任务类型的调度策略，包括：
    所述计算系统根据所述任务类型，为所述任务类型生成所述性能指标。
  11. 一种存储计算系统，包括计算系统和存储系统，所述计算系统具有至少一个计算单元，所述存储系统具有至少一个存储单元，其特征在于：
    所述计算系统包括标识模块与发送模块，所述存储系统包括任务解析模块与服务质量模块；其中，
    所述标识模块，用于对于所述至少一个计算单元中的任一计算单元，识别所述计算单元的任务类型；
    所述发送模块，用于向所述存储系统的任务解析模块发送任务类型信息，所述任务类型信息携带所述任务类型；
    所述任务解析模块，用于根据所述任务类型信息，获取所述任务类型的调度策略；
    所述服务质量模块，用于根据所述任务解析模块解析的所述调度策略，对所述计算单元对应的存储单元进行调度。
  12. 根据权利要求11所述的存储计算系统，其特征在于，当所述调度策略具体为所述任务类型的存储服务等级时，所述存储系统还包括存储模块，用于存储所述任务类型与所述存储服务等级的对应关系；
    所述任务解析模块，具体用于根据所述任务类型信息查找所述存储模块存储的所述对应关系，确定所述任务类型的存储服务等级。
  13. 根据权利要求11所述的存储计算系统，其特征在于，当所述任务类型信息还携带所述计算单元的服务等级时，
    所述任务解析模块，具体用于根据所述任务类型信息，确定所述任务类型对应的操作信息，根据所述操作信息，对所述计算单元的服务等级进行处理以得到所述任务类型的调度策略。
  14. 根据权利要求11所述的存储计算系统，其特征在于，当所述调度策 略具体为性能指标时，
    所述任务解析模块，具体用于根据所述任务类型信息，为所述任务类型生成所述性能指标。
  15. 根据权利要求11～14任一项所述的存储计算系统，其特征在于，所述计算系统还包括：通信接口建立模块；
    所述通信接口建立模块，用于在所述计算系统与所述存储系统之间建立通信接口；
    所述发送模块，具体用于通过所述通信接口建立模块建立的所述通信接口向所述存储系统发送所述任务类型信息。
  16. 根据权利要求11～14任一项所述的存储计算系统，其特征在于，所述计算系统还包括：配置模块；
    所述配置模块，用于配置所述计算系统与所述存储系统之间进行通信的配置文件；
    所述发送模块，具体用于将所述任务类型信息携带在所述配置模块配置的所述配置文件中发送给所述存储系统。
  17. 一种存储计算系统，包括计算系统和存储系统，所述计算系统具有至少一个计算单元，所述存储系统具有至少一个存储单元，其特征在于：
    所述计算系统包括识别映射模块与发送模块，所述存储系统包括服务质量模块；其中，
    所述识别映射模块，用于对于所述至少一个计算单元中的任一计算单元，识别所述计算单元的任务类型，并根据所述任务类型，获取所述任务类型的调度策略；
    所述发送模块，用于向所述存储系统的服务质量模块发送所述任务类型的调度策略；
    所述服务质量模块，用于根据所述发送模块发送的所述调度策略，对所述计算单元对应的存储单元进行调度。
  18. 根据权利要求17所述的存储计算系统，其特征在于，当所述调度策略具体为所述任务类型的存储服务等级时，所述计算系统还包括存储模块，用于存储所述任务类型与所述存储服务等级的对应关系；
    所述识别映射模块，具体用于根据所述任务类型查找所述存储模块存储的所述对应关系，确定所述任务类型的存储服务等级。
  19. 根据权利要求17所述的存储计算系统，其特征在于，
    所述识别映射模块，具体用于确定所述任务类型对应的操作信息；根据所述操作信息，对所述计算单元的服务等级进行处理以得到所述任务类型的调度策略。
  20. 根据权利要求17所述的存储计算系统，其特征在于，当所述调度策略具体为性能指标时，
    所述识别映射模块，具体用于根据所述任务类型，为所述任务类型生成所述性能指标。
PCT/CN2014/089540 2014-02-24 2014-10-27 存储资源调度方法及存储计算系统 WO2015123999A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP14883281.9A EP3101870A4 (en) 2014-02-24 2014-10-27 METHOD FOR SCHEDULING STORAGE RESOURCES AND STORAGE CALCULATION SYSTEM
US15/245,807 US10241835B2 (en) 2014-02-24 2016-08-24 Scheduling storage and computing resources based on task types and service levels

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410062471.5 2014-02-24
CN201410062471.5A CN103795804A (zh) 2014-02-24 2014-02-24 存储资源调度方法及存储计算系统

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/245,807 Continuation US10241835B2 (en) 2014-02-24 2016-08-24 Scheduling storage and computing resources based on task types and service levels

Publications (1)

Publication Number Publication Date
WO2015123999A1 true WO2015123999A1 (zh) 2015-08-27

Family

ID=50671072

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/089540 WO2015123999A1 (zh) 2014-02-24 2014-10-27 存储资源调度方法及存储计算系统

Country Status (4)

Country Link
US (1) US10241835B2 (zh)
EP (1) EP3101870A4 (zh)
CN (1) CN103795804A (zh)
WO (1) WO2015123999A1 (zh)

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103795804A (zh) 2014-02-24 2014-05-14 华为技术有限公司 存储资源调度方法及存储计算系统
CN104142853B (zh) * 2014-08-12 2018-02-09 华为技术有限公司 虚拟机存储资源部署方法和装置
CN104657205B (zh) * 2014-12-26 2018-12-14 中通服公众信息产业股份有限公司 一种基于虚拟化的视频内容分析方法及系统
CN105446812A (zh) * 2016-01-04 2016-03-30 中国南方电网有限责任公司 一种多任务调度配置方法
CN105653365A (zh) * 2016-02-22 2016-06-08 青岛海尔智能家电科技有限公司 任务处理方法及装置
US10572650B2 (en) * 2016-02-29 2020-02-25 Intel Corporation Technologies for independent service level agreement monitoring
CN105808333B (zh) * 2016-03-04 2019-07-26 上海携程商务有限公司 任务分配方法及系统
CN106095534B (zh) * 2016-06-07 2019-07-23 百度在线网络技术（北京）有限公司 一种计算任务处理方法和系统
CN107273202A (zh) * 2017-07-14 2017-10-20 郑州云海信息技术有限公司 一种控制任务调度的方法和装置
CN108228354B (zh) * 2017-12-29 2022-03-18 杭州朗和科技有限公司 调度方法、系统、计算机设备和介质
US10725819B2 (en) 2018-05-18 2020-07-28 Acronis International Gmbh System and method for scheduling and allocating data storage
CN110750582B (zh) * 2018-07-23 2023-05-02 阿里巴巴集团控股有限公司 数据处理方法、装置和系统
CN113407317A (zh) * 2018-09-11 2021-09-17 华为技术有限公司 一种资源调度方法及装置
WO2021022486A1 (zh) * 2019-08-06 2021-02-11 西门子股份公司 配置优先级的方法、云平台、系统、计算设备和介质
CN111027689B (zh) * 2019-11-20 2024-03-22 中国航空工业集团公司西安航空计算技术研究所 配置方法、装置及计算系统
US11321257B2 (en) * 2019-12-31 2022-05-03 Micron Technology, Inc. Quality of service control of logical devices for a memory sub-system
US11829625B2 (en) * 2020-04-27 2023-11-28 EMC IP Holding Company LLC Slice memory control
CN113835616A (zh) * 2020-06-23 2021-12-24 华为技术有限公司 应用的数据管理方法、系统和计算机设备
US11726827B2 (en) * 2021-02-19 2023-08-15 Vast Data Ltd. Hierarchical workload allocation in a storage system
CN113742045A (zh) * 2021-09-15 2021-12-03 上海淇玥信息技术有限公司 一种分布式任务处理方法、装置和电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103023963A (zh) * 2012-10-31 2013-04-03 浪潮集团有限公司 一种用于云存储资源优化分配的方法
US20130179371A1 (en) * 2012-01-05 2013-07-11 Microsoft Corporation Scheduling computing jobs based on value
CN103561098A (zh) * 2013-11-05 2014-02-05 华为技术有限公司 一种选择存储资源方法、装置及系统
CN103581339A (zh) * 2013-11-25 2014-02-12 广东电网公司汕头供电局 基于云计算的存储资源分配监控处理方法
CN103795804A (zh) * 2014-02-24 2014-05-14 华为技术有限公司 存储资源调度方法及存储计算系统

Family Cites Families (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH07302236A (ja) * 1994-05-06 1995-11-14 Hitachi Ltd 情報処理システムおよびその方法並びに情報処理システムにおけるサービス提供方法
US6904470B1 (en) * 2003-03-26 2005-06-07 Emc Corporation Device selection by a disk adapter scheduler
US7480912B2 (en) * 2003-05-29 2009-01-20 International Business Machines Corporation Method for policy-based, autonomically allocated storage
GB0513045D0 (en) * 2005-06-27 2005-08-03 Vidus Ltd Resource scheduling method and system
US7747662B2 (en) * 2005-12-30 2010-06-29 Netapp, Inc. Service aware network caching
US7895520B1 (en) * 2006-01-03 2011-02-22 Emc Corp Methods and apparatus for managing scheduled activities in a storage area network
CN100512307C (zh) * 2006-03-06 2009-07-08 华为技术有限公司 通讯网络中网络资源的分配方法及系统
US8473566B1 (en) * 2006-06-30 2013-06-25 Emc Corporation Methods systems, and computer program products for managing quality-of-service associated with storage shared by computing grids and clusters with a plurality of nodes
US7937373B2 (en) * 2007-09-07 2011-05-03 Csi Technology, Inc. Method and apparatus for automated storage of event-substantiating data
US7822731B1 (en) * 2008-03-28 2010-10-26 Emc Corporation Techniques for management of information regarding a sequential stream
US8943203B1 (en) * 2009-07-10 2015-01-27 Netapp, Inc. System and method for storage and deployment of virtual machines in a virtual server environment
JP5244831B2 (ja) * 2010-01-25 2013-07-24 株式会社日立製作所 計算機システム及びストレージ統合管理方法
US9213574B2 (en) * 2010-01-30 2015-12-15 International Business Machines Corporation Resources management in distributed computing environment
CN101908972A (zh) * 2010-05-25 2010-12-08 北京邮电大学 一种otn传输设备中mpls-tp业务通道资源分配方法及其装置
US9003157B1 (en) * 2010-06-30 2015-04-07 Emc Corporation Techniques for dynamic data storage configuration in accordance with an allocation policy
CN102567072B (zh) * 2010-12-20 2015-04-22 中国移动通信集团公司 一种资源分配方法、装置及系统
US8407501B2 (en) * 2011-03-28 2013-03-26 International Business Machines Corporation Allocation of storage resources in a networked computing environment based on energy utilization
US20120290789A1 (en) * 2011-05-12 2012-11-15 Lsi Corporation Preferentially accelerating applications in a multi-tenant storage system via utility driven data caching
US9152549B1 (en) * 2012-03-30 2015-10-06 Google Inc. Dynamically allocating memory for processes
US10102097B2 (en) * 2012-07-12 2018-10-16 International Business Machines Corporation Transaction server performance monitoring using component performance data
US9442954B2 (en) * 2012-11-12 2016-09-13 Datawise Systems Method and apparatus for achieving optimal resource allocation dynamically in a distributed computing environment
US9201777B2 (en) * 2012-12-23 2015-12-01 Advanced Micro Devices, Inc. Quality of service support using stacked memory device with logic die
US10552774B2 (en) * 2013-02-11 2020-02-04 Amazon Technologies, Inc. Cost-minimizing task scheduler
US9298385B2 (en) * 2013-04-12 2016-03-29 International Business Machines Corporation System, method and computer program product for deduplication aware quality of service over data tiering
CN103414657A (zh) * 2013-08-22 2013-11-27 浪潮(北京)电子信息产业有限公司 一种跨数据中心的资源调度方法、超级调度中心和系统
CN103501347B (zh) * 2013-10-14 2016-08-10 中国联合网络通信集团有限公司 资源分配方法及装置
JP6273866B2 (ja) * 2014-01-29 2018-02-07 富士通株式会社 制御プログラム、制御装置および制御方法
CN106155764A (zh) * 2015-04-23 2016-11-23 阿里巴巴集团控股有限公司 调度虚拟机输入输出资源的方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130179371A1 (en) * 2012-01-05 2013-07-11 Microsoft Corporation Scheduling computing jobs based on value
CN103023963A (zh) * 2012-10-31 2013-04-03 浪潮集团有限公司 一种用于云存储资源优化分配的方法
CN103561098A (zh) * 2013-11-05 2014-02-05 华为技术有限公司 一种选择存储资源方法、装置及系统
CN103581339A (zh) * 2013-11-25 2014-02-12 广东电网公司汕头供电局 基于云计算的存储资源分配监控处理方法
CN103795804A (zh) * 2014-02-24 2014-05-14 华为技术有限公司 存储资源调度方法及存储计算系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3101870A4 *

Also Published As

Publication number Publication date
US10241835B2 (en) 2019-03-26
EP3101870A1 (en) 2016-12-07
US20160364269A1 (en) 2016-12-15
CN103795804A (zh) 2014-05-14
EP3101870A4 (en) 2016-12-07

Similar Documents

Publication Publication Date Title
WO2015123999A1 (zh) 存储资源调度方法及存储计算系统
US10853142B2 (en) Stateless instance backed mobile devices
US9813423B2 (en) Trust-based computing resource authorization in a networked computing environment
US9983897B2 (en) Maintaining virtual machines for cloud-based operators in a streaming application in a ready state
US8769269B2 (en) Cloud data management
US9086897B2 (en) Method and architecture for virtual desktop service
US10489207B2 (en) System for resource management using performance specification and description information of the process
US20150128131A1 (en) Managing virtual machine patterns
US9537780B2 (en) Quality of service agreement and service level agreement enforcement in a cloud computing environment
US9710292B2 (en) Allowing management of a virtual machine by multiple cloud providers
US11057464B1 (en) Synchronization of data between local and remote computing environment buffers
US9735984B2 (en) Bursting cloud resources to affect state change performance
US9378039B2 (en) Virtual machine storage replication schemes
US20140297695A1 (en) Intelligent data routing and storage provisioning
US10489177B2 (en) Resource reconciliation in a virtualized computer system
US10678684B1 (en) Dynamic virtual storage creation and provisioning of virtual machine resources
WO2022103575A1 (en) Techniques for modifying cluster computing environments
WO2017113895A1 (zh) 一种创建虚拟机的方法及装置
JP6205013B1 (ja) アプリケーション利用システム
US10277521B2 (en) Authorizing an action request in a networked computing environment
US11928494B2 (en) Configuration techniques for managed virtual machines
US8972490B1 (en) User discovery in socially-aware data storage systems

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 14883281

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

REEP Request for entry into the european phase

Ref document number: 2014883281

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2014883281

Country of ref document: EP