Cost-effective IAAS (infrastructure-as-a-service) cloud storage based on adaptive virtual disks (AVD)

• US 9,442,669 B2
• Filed: 08/06/2014
• Issued: 09/13/2016
• Est. Priority Date: 08/06/2014
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated (Kyndryl Holdings, Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Nicolae, Bogdan
• Primary Examiner(s): Shyu, Jing-Yih
• Application Number:
  US14/452,732
• Publication Number:
  US 20160041787A1
• Time in Patent Office: 769 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/0613 in relation to throughput
• CPC Class Codes: G06F 3/0631 by allocating resources to storage systems
• CPC Class Codes: G06F 3/0649 Lifecycle management
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

There are provided a system, a method and a computer program product for operating a cloud computing storage system. The cloud computing storage system allocates and manages virtual disks. A virtual disk provides a logical data storage. The cloud computing storage system divides data stored in the virtual disks into chunks and allocates the chunks to physical data storage devices. The cloud computing storage system monitors I/O access patterns and user requests to change data storage capacities and throughputs of the virtual disks in real time. The cloud computing storage system dynamically reconfigures an allocation of the chunks to the physical data storage devices.

Claims

1. A method for operating a cloud computing storage system, the method comprising:

allocating and managing at least one virtual disk for a user, the at least one virtual disk providing a logical data storage;

dividing data stored in the at least one virtual disk into chunks and allocating the chunks to physical data storage devices;

monitoring Input/Output (I/O) access patterns corresponding to the user and requests provided from the user, wherein the requests provided from the user includes change of data storage capacity and throughput of the at least one virtual disk in real time;

dynamically reconfiguring an allocation of the chunks to the physical data storage devices in response to the monitored I/O access patterns and the requests provided from the user, and

charging, by using a cost model, the user based on the data storage capacity and the throughput of the at least one virtual disk, the cost model determining a cost to use the cloud computing storage system for the user based on;

the data storage capacity of the at least one virtual disk that is provided to or to be provided to the user;

the throughput of the at least one virtual disk that is provided to or to be provided to the user; and

an adjustment factor that converts the data storage capacity and the throughput of the at least one virtual disk, which is provided to or to be provided to the user, to a monetary value.

2. The method according to claim 1, further comprising:

enabling the user to modify the data storage capacity and the throughput of the at least one virtual disk dynamically in real time.

3. The method according to claim 1, wherein the reconfiguring the allocation of the chunks comprises:

migrating the chunks between the physical data storage devices of various capacities and throughput capabilities in order to dynamically adapt to a modification of I/O performance and capacity requirements as specified by the user.

4. The method according to claim 3, wherein the reconfiguring the allocation of the chunks comprises:

consolidating the chunks in the physical data storage devices providing a least throughput and capacity in order to support as many users as possible and reduce operational costs without violating the I/O performance and the capacity requirements.

5. The method according to claim 4, wherein the migration and consolidation relies on:

monitoring I/O parameters that include one or more of;

number of I/O operations, size of data being transferred, data storage capacity needed for the I/O operations; and

predicting, based on the monitored I/O parameters and past I/O operations, I/O operations to be occurred in a future pre-determined time period.

6. The method according to claim 1, wherein the allocation and

management of the at least one virtual disk comprises:

virtualization techniques to leverage a physical infrastructure running the at least one virtual disk.

7. A system for operating a cloud computing storage system, the system comprising:

a middleware running on a cloud computing infrastructure, said middleware configured to perform;

allocating and managing at least one virtual disk for a user, the at least one virtual disk providing a logical data storage;

dividing data stored in the at least one virtual disk into chunks and allocating the chunks to physical data storage devices;

monitoring Input/Output (I/O) access patterns corresponding to the user and requests provided from the user, wherein the requests provided from the user includes change of data storage capacity and throughput of the at least one virtual disk in real time;

dynamically reconfiguring an allocation of the chunks to the physical data storage devices in response to the monitored I/O access patterns and the requests provided from the user, and

charging, by using a cost model, the user based on the data storage capacity and the throughput of the at least one virtual disk, the cost model determining a cost to use the cloud computing storage system for the user based on;

the data storage capacity of the at least one virtual disk that is provided to or to be provided to the user;

the throughput of the at least one virtual disk that is provided to or to be provided to the user; and

an adjustment factor that converts the data storage capacity and the throughput of the at least one virtual disk, which is provided to or to be provided to the user, to a monetary value.

8. The system according to claim 7, wherein the middleware is further configured to perform:

enabling the user to modify the data storage capacity and the throughput of the at least one virtual disk dynamically in real time.

9. The system according to claim 7, wherein reconfiguring the allocation of the chunks comprises migrating the chunks between the physical data storage devices of various capacity and throughput capabilities in order to dynamically adapt to the modification of I/O performance and capacity requirements as specified by the user.

10. The system according to claim 9, wherein the reconfiguring the allocation of the chunks comprises consolidating the chunks in the physical data storage devices providing a least throughput and capacity in order to support as many users as possible and reduce operational costs without violating the I/O performance and the capacity requirements.

11. The system according to claim 10, wherein the migration and

consolidation relies on:

monitoring I/O parameters that include one or more of;

number of I/O operations, size of data being transferred, data storage capacity needed for the I/O operations; and

predicting, based on the monitored I/O parameters and past I/O operations, I/O operations to be occurred in a future pre-determined time period.

12. The system according to claim 7, wherein the allocation and

management of the at least one virtual disk comprises:

utilizing virtualization techniques to leverage a physical infrastructure running the at least one virtual disk.

13. A middleware program product comprising a computer readable storage medium, the computer readable storage medium excluding a propagating signal, the computer readable storage medium readable by a processing circuit and storing instructions run by the processing circuit for performing a method, said method comprising:

allocating and managing at least one virtual disk for a user, the at least one virtual disk providing a logical data storage;

dividing data stored in the at least one virtual disk into chunks and allocating the chunks to physical data storage devices;

monitoring Input/Output (I/O) access patterns corresponding to the user and requests provided from the user, wherein the requests provided from the user includes change of data storage capacity and throughput of the at least one virtual disk in real time;

dynamically reconfiguring an allocation of the chunks to the physical data storage devices in response to the monitored I/O access patterns and the requests provided from the user, and

charging, by using a cost model, the user based on the data storage capacity and the throughput of the at least one virtual disk, the cost model determining a cost to use the cloud computing storage system for the user based on;

the data storage capacity of the at least one virtual disk that is provided to or to be provided to the user;

the throughput of the at least one virtual disk that is provided to or to be provided to the user; and

an adjustment factor that converts the data storage capacity and the throughput of the at least one virtual disk, which is provided to or to be provided to the user, to a monetary value.

14. The middleware program product according to claim 13, wherein the method further comprises:

enabling the user to modify the data storage capacity and the throughput of the at least one virtual disk dynamically in real time.

15. The middleware program product according to claim 14, wherein the reconfiguring the allocation of the chunks comprises:

migrating the chunks between the physical data storage devices of various capacity and throughput capabilities in order to dynamically adapt to the modification of I/O performance and capacity requirements as specified by the user.

16. The middleware program product according to claim 15, wherein the reconfiguring the allocation of the chunks comprises:

consolidating the chunks in the physical data storage devices providing a least throughput and capacity in order to support as many users as possible and reduce operational costs without violating the I/O performance and the capacity requirements.

17. The middleware program product according to claim 16, wherein the migration and consolidation relies on:

monitoring I/O parameters that include one or more of;

number of I/O operations, size of data being transferred, data storage capacity needed for the I/O operations; and

predicting, based on the monitored I/O parameters and past I/O operations, I/O operations to be occurred in a future pre-determined time period.