KR20160118402A - Access Pattern based Cache Management Method for VDI Mass Data Processing - Google Patents

Access Pattern based Cache Management Method for VDI Mass Data Processing Download PDF

Info

Publication number
KR20160118402A
KR20160118402A KR1020150045931A KR20150045931A KR20160118402A KR 20160118402 A KR20160118402 A KR 20160118402A KR 1020150045931 A KR1020150045931 A KR 1020150045931A KR 20150045931 A KR20150045931 A KR 20150045931A KR 20160118402 A KR20160118402 A KR 20160118402A
Authority
KR
South Korea
Prior art keywords
access pattern
vdi
data
cache
management method
Prior art date
Application number
KR1020150045931A
Other languages
Korean (ko)
Inventor
전기만
안재훈
손재기
Original Assignee
전자부품연구원
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 전자부품연구원 filed Critical 전자부품연구원
Priority to KR1020150045931A priority Critical patent/KR20160118402A/en
Publication of KR20160118402A publication Critical patent/KR20160118402A/en

Links

Images

Classifications

    • 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
    • G06F3/0662—Virtualisation aspects
    • G06F3/0664—Virtualisation aspects at device level, e.g. emulation of a storage device or system
    • 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
    • G06F3/0646—Horizontal data movement in storage systems, i.e. moving data in between storage devices or systems
    • G06F3/0652—Erasing, e.g. deleting, data cleaning, moving of data to a wastebasket
    • 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
    • G06F3/0671—In-line storage system
    • G06F3/0673—Single storage device
    • G06F3/0674—Disk device
    • 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
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors

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)
  • Memory System Of A Hierarchy Structure (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

Provided is an access pattern based cache management method for processing VDI mass data. According to an embodiment of the present invention, the cache management method generates an data access pattern of a VDI user and loads a portion of data base on the access pattern among data stored on a storage disk on a cache disk. Thereby, the present invention can improve performance by more efficiently managing a cache space.

Description

{Access Pattern based Cache Management Method for VDI Mass Data Processing}

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a VDI (Virtual Desktop Infrastructure) technology, and more particularly, to a cache management method for large-capacity data processing in a VDI and a server using the same.

In the VDI environment, cache saturation often occurs due to an increase in the processing of guest OS and user data requests. The cache is designed to process data faster. In this case, the operation of the cache causes a delay in the I / O processing, resulting in a decrease in the service speed.

Currently, in a small VDI environment, cache operation enables efficient data processing only by hashing-based search and operation for I / O request processing. However, in a VDI environment where a large number of users access, data with a high hit ratio is lost from the cache due to low utilization frequency for each user.

Therefore, the adverse effect of the cache operation and the cache space management become unreasonable, and a method for solving the problem is required.

SUMMARY OF THE INVENTION The present invention has been made to solve the above problems, and it is an object of the present invention to provide a method and apparatus for efficiently managing a cache space by using a data access pattern of a user based on a data access request in a VDI environment. The present invention provides a method for enhancing the performance of a system.

According to an aspect of the present invention, there is provided a cache management method comprising: generating a data access pattern of a VDI user; And loading the selected data on the second disk based on the access pattern among the data stored in the first disk.

The access pattern may be a data set requested by the user.

The cache management method according to an embodiment of the present invention may further include deleting data loaded on the second disk based on the access pattern.

The loading step may be performed on an access pattern whose occurrence frequency is higher than a reference, and the deleting step may be performed on an access pattern whose occurrence frequency is lower than a reference.

The access pattern may be generated in units of programs.

According to another aspect of the present invention, there is provided a server comprising: a management module for generating a data access pattern of a VDI user; And a cache module for loading a part of data stored on the first disk based on the access pattern on the second disk.

As described above, according to the embodiments of the present invention, performance can be improved by more efficiently managing the cache space using the data access pattern of the user collected based on the data access request in the VDI environment.

1 is a diagram illustrating a VDI environment to which the present invention is applicable;
Fig. 2 is a detailed block diagram of the VDI system shown in Fig. 1,
3 is a flowchart provided in the description of a cache management method according to an embodiment of the present invention.

Hereinafter, the present invention will be described in detail with reference to the drawings.

1 is a diagram illustrating a Virtual Desktop Infrastructure (VDI) environment to which the present invention is applicable. 1, a VDI environment to which the present invention is applicable includes a plurality of VDI clients 10-1, 10-2, 10-3, ... 10-n and a VDI system 100, So that they can communicate with each other.

The VDI clients 10-1, 10-2, 10-3, ... 10-n provide a virtual desktop service to the users utilizing the resources of the VDI system 100. [ To this end, the VDI system 100 includes a VDI server 110, a hard disk drive (HDD) 120, and a solid state disk (SSD)

The HDD 120 is a large-capacity disk in which an OS and various programs are stored. The SSD 130 functions as a cache in the VDI system 100 with a disk having a high access speed.

2 is a detailed block diagram of the VDI system 100 shown in FIG. 2, the VDI server 110 of the VDI system 100 includes the guest OSes 111, the hypervisor 113, the access pattern management module 115, and the block level virtual cache module 117 .

The guest OSes 111 are virtual machines assigned to the VDI clients 10-1, 10-2, 10-3, ... 10-n. The hypervisor 113 is a means for managing / controlling access of the guest OSes 111 to the resources of the VDI server 110. [

The block level virtual cache module 117 processes the data requests of the guest OSes 111 delivered via the hypervisor 113. To this end, the block level virtual cache module 117 accesses the HDD 120 and the SSD 130.

In this process, the block level virtual cache module 117 loads data stored in the HDD 120 into the SSD 130 and deletes data stored in the SSD 130.

 The access pattern management module 115 controls the management operation of the SSD 130 by the block level virtual cache module 117. The management of the SSD 130 is based on the data access pattern of the user (hereinafter abbreviated as 'access pattern').

The access pattern means a data set that the VDI clients 10-1, 10-2, 10-3, ... 10-n have requested to access. This can be the data set (exe file, dll, lib) needed to run the program.

 The access pattern management module 115 collects data access requests transmitted from the VDI clients 10-1, 10-2, 10-3, ... 10-n via the guest OSes 111, . The access pattern management module 115 can update the generated access pattern in real time / periodically.

Then, the access pattern management module 115 controls the management operation of the SSD 130 by the block-level virtual cache module 117 based on the generated / updated access pattern. Specifically, data included in the access pattern having a high frequency is loaded on the SSD 130, and data included in the access pattern having a low frequency is deleted from the SSD 130, respectively.

Hereinafter, a cache management method by the access pattern management module 115 will be described in detail with reference to FIG. 3 is a flowchart provided in the description of a cache management method according to an embodiment of the present invention.

As shown in FIG. 3, first, the access pattern management module 115 generates / updates an access pattern (S210). The access pattern generation / update in step S210 may be performed in real time / periodically.

The access pattern management module 115 monitors the data access requests of the guest OSes 111 transferred to the block level virtual cache module 117 via the hypervisor 113. [

If it is determined that the occurrence frequency of the access pattern is higher than the reference (S220-Y), the access pattern management module 115 controls the block level virtual cache module 117 based on the access pattern to perform cache preloading (S230 ). When the frequency of the access pattern is more than the reference, it refers to a case where an access pattern is displayed by many users.

Step S230 is an operation of loading data into the cache before a user's request is made. Specifically, the access pattern management module 115 controls the block level virtual cache module 117 to copy the data included in the access pattern stored in the HDD 120 to the SSD 130.

If the data included in the access pattern is already loaded in the SSD 130, step S230 is not performed.

Thereby, the warm data having a high hit rate is prevented from being lost in the SSD 130, and can be restored even if it is lost during the cache utilization process.

On the other hand, when it is determined that the occurrence frequency of the access pattern is less than the reference (S240-Y), the access pattern management module 115 controls the block level virtual cache module 117 based on the access pattern to perform cache deletion S250). When the frequency of the access pattern is less than the reference, it refers to a case where the access pattern is not displayed by many users.

In step S250, the access pattern management module 115 controls the block level virtual cache module 117 to delete the data included in the access pattern stored in the SSD 130.

If the data included in the access pattern is not loaded in the SSD 130, step S250 is not performed.

Up to now, a preferred embodiment of the access pattern-based cache management method for VDI large data processing has been described in detail.

The access pattern mentioned in the above embodiment is preferably generated / updated in units of programs and managed. The program for managing the access pattern is preferably limited to those having a high access frequency by the user.

Furthermore, in performing cache management, temporal data that is not included in the access pattern may be periodically deleted by the access pattern management module 115.

Also, in the embodiment of the present invention, the HDD 120 and the SSD 130 are referred to as a kind of disk, and it is needless to say that the HDD 120 and the SSD 130 may be replaced with other types of disks.

The VDI environment assumed in the embodiment of the present invention is also only an example. It goes without saying that the technical idea of the present invention can be applied to a server / infrastructure environment other than the VDI environment as well as a PC environment.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, It will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the present invention.

10-1, 10-2, 10-3, ... 10-n: VDI client
100: VDI system 110: VDI server
111: guest OS 113: hypervisor
115: access pattern management module
117: Block level virtual cache module
120: HDD 130: SSD

Claims (6)

Generating a data access pattern of a Virtual Desktop Infrastructure (VDI) user; And
And loading the selected data on the second disk based on the access pattern among the data stored in the first disk.
The method according to claim 1,
The access pattern includes:
Wherein the data set is a data set requested by the user.
The method of claim 2,
And deleting data loaded on the second disk based on the access pattern.
The method of claim 3,
Wherein the loading step is performed for an access pattern whose occurrence frequency is higher than a reference,
Wherein said deleting step is performed for an access pattern whose occurrence frequency is less than a criterion.
The method according to claim 1,
The access pattern includes:
Wherein the program is generated in units of programs.
A management module for generating a data access pattern of a VDI (Virtual Desktop Infrastructure) user; And
And a cache module for loading a part of the data stored in the first disk based on the access pattern on the second disk.
KR1020150045931A 2015-04-01 2015-04-01 Access Pattern based Cache Management Method for VDI Mass Data Processing KR20160118402A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020150045931A KR20160118402A (en) 2015-04-01 2015-04-01 Access Pattern based Cache Management Method for VDI Mass Data Processing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020150045931A KR20160118402A (en) 2015-04-01 2015-04-01 Access Pattern based Cache Management Method for VDI Mass Data Processing

Publications (1)

Publication Number Publication Date
KR20160118402A true KR20160118402A (en) 2016-10-12

Family

ID=57173303

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020150045931A KR20160118402A (en) 2015-04-01 2015-04-01 Access Pattern based Cache Management Method for VDI Mass Data Processing

Country Status (1)

Country Link
KR (1) KR20160118402A (en)

Similar Documents

Publication Publication Date Title
US11061584B2 (en) Profile-guided data preloading for virtualized resources
AU2017258659B2 (en) Multi-Cluster Warehouse
US20170336998A1 (en) Method and system for sharing storage resource
US9489389B2 (en) System and method for maintaining cache coherency
US20160210067A1 (en) File system snapshot data management in a multi-tier storage environment
US10715622B2 (en) Systems and methods for accelerating object stores with distributed caching
US20170255527A1 (en) Live rollback for a computing environment
WO2017190084A1 (en) Offloading storage encryption operations
JP2014175009A (en) System, method and computer-readable medium for dynamic cache sharing in flash-based caching solution supporting virtual machines
US20140281301A1 (en) Elastic hierarchical data storage backend
US10635604B2 (en) Extending a cache of a storage system
US11204702B2 (en) Storage domain growth management
JP6774971B2 (en) Data access accelerator
US10298709B1 (en) Performance of Hadoop distributed file system operations in a non-native operating system
US11442927B1 (en) Storage performance-based distribution of deduplicated data to nodes within a clustered storage environment
US20140082275A1 (en) Server, host and method for reading base image through storage area network
CN110806911A (en) Cloud desktop management and control method, device and system
KR101918806B1 (en) Cache Management Method for Optimizing the Read Performance of Distributed File System
Lai et al. Io performance interference among consolidated n-tier applications: Sharing is better than isolation for disks
CN112579550B (en) Metadata information synchronization method and system of distributed file system
US20150212847A1 (en) Apparatus and method for managing cache of virtual machine image file
US11272006B2 (en) Intelligently distributing retrieval of recovery data amongst peer-based and cloud-based storage sources
US11055262B1 (en) Extensible streams on data sources
JP2013214201A (en) Garbage collection execution device, garbage collection execution method and garbage collection execution program
US9852139B1 (en) Directory partitioning with concurrent directory access