CN108595116B - Cluster data read-write performance optimization method based on Oracle RAC - Google Patents

Cluster data read-write performance optimization method based on Oracle RAC Download PDF

Info

Publication number
CN108595116B
CN108595116B CN201810271075.1A CN201810271075A CN108595116B CN 108595116 B CN108595116 B CN 108595116B CN 201810271075 A CN201810271075 A CN 201810271075A CN 108595116 B CN108595116 B CN 108595116B
Authority
CN
China
Prior art keywords
oracle rac
cluster
optimization method
data read
performance optimization
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CN201810271075.1A
Other languages
Chinese (zh)
Other versions
CN108595116A (en
Inventor
徐伽
杨建�
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Wisu Technology Co ltd
Original Assignee
Zhejiang Wisu Technology Co ltd
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 Zhejiang Wisu Technology Co ltd filed Critical Zhejiang Wisu Technology Co ltd
Priority to CN201810271075.1A priority Critical patent/CN108595116B/en
Publication of CN108595116A publication Critical patent/CN108595116A/en
Application granted granted Critical
Publication of CN108595116B publication Critical patent/CN108595116B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F3/0602—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
    • 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]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a cluster data read-write performance optimization method based on distributed storage Oracle RAC, which comprises the following steps: dividing a part of storage space in 2 or more server nodes of an Oracle Rac cluster; secondly, mounting the marked storage space to other servers with database instances in an Oracle Rac cluster through an iSCSI protocol operated by a common Ethernet or an infiniband high-bandwidth low-delay network; and thirdly, the server in the Oracle RAC creates and aggregates the identified iSCSI disks through the DM and realizes multi-path management. The invention provides the capability of performing local direct read-write access on the space which is divided by the local computer and bypasses the network, thereby reducing the influence of the network bottleneck to the maximum extent.

Description

Cluster data read-write performance optimization method based on Oracle RAC
Technical Field
The invention relates to the field of databases, in particular to a cluster data read-write performance optimization method based on distributed storage Oracle RAC.
Background
The local access bandwidth and IOPS of the current storage media (such as NVMe flash disk, PCI-E flash card, multi-block SSD disk and the like) greatly surpass the transmission bandwidth and IOPS of the common Ethernet and even exceed the Infiniband (Infiniband) network, and particularly in the case of multi-block storage media, the network bottleneck is more obvious.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention provides a cluster data read-write performance optimization method based on distributed storage Oracle RAC, which comprises the following steps:
dividing a part of storage space in 2 or more server nodes of an Oracle Rac cluster;
secondly, mounting the marked storage space to other servers with database instances in an Oracle Rac cluster through an iSCSI protocol operated by a common Ethernet or an infiniband high-bandwidth low-delay network;
and thirdly, the server in the Oracle RAC creates and aggregates the identified iSCSI disks through the DM and realizes multi-path management.
Further, the server of the planned storage space does not directly access the storage space through any network.
Further, all server nodes of the Oracle Rac cluster manage all mounted storage spaces through the ASM, and configure 2 or 3 copies of data redundancy.
Furthermore, the Oracle RAC server identifies and marks the local medium through a local priority reading algorithm, detects whether the data to be accessed exist on the local medium, and preferentially reads the data from the local medium if the data to be accessed exist on the local medium.
The invention provides the capability of performing local direct read-write access on the space which is divided by the local computer and bypasses the network, thereby reducing the influence of the network bottleneck to the maximum extent. In a 2-node RAC cluster with 2 copies configured by an Automatic Storage Manager (ASM) and a 3-node RAC cluster with 3 copies configured by an Automatic Storage Manager (ASM), 100% local read is achieved because each node has one complete copy of data. In a 3-node RAC cluster, under the environment of 10Gb/s Ethernet, the performance of Oracle IOPS which enables the local priority reading function is increased by more than 100 percent compared with the performance before the local priority reading function is enabled (the storage medium is an NVMe disk), and the IO performance is basically equivalent to that of a conventional Oracle RAC cluster which uses an Infiniband switching network with 56 Gb/s. And when the number of NVMe disks per node is increased, the IO performance of the Oracle RAC cluster using the method is further improved and exceeds the performance of the conventional Oracle RAC cluster using the 56Gb/s Infiniband switching network at present.
Drawings
FIG. 1 is a schematic of the method topology of the present invention.
Detailed Description
The invention will be further explained with reference to the drawings.
As shown in fig. 1, the method for optimizing data read-write performance based on distributed storage Oracle RAC cluster of the present invention comprises the following steps:
dividing a part of storage space in 2 or more server nodes of an Oracle Rac cluster;
secondly, mounting the marked storage space to other servers with database instances in an Oracle Rac cluster through an iSCSI protocol operated by a common Ethernet or an infiniband high-bandwidth low-delay network;
and thirdly, the server in the Oracle RAC creates and aggregates the identified iSCSI disks through the DM and realizes multi-path management.
The server where the partitioned storage space is located does not directly access the storage space through any network; all server nodes of the Oracle Rac cluster manage all mounted storage spaces through the ASM, and configure data redundancy of 2 or 3 copies.
The Oracle RAC server identifies and marks the local medium through a local priority reading algorithm, detects whether the data to be accessed exist on the local medium or not, and preferentially reads the data from the local medium if the data to be accessed exist on the local medium.

Claims (4)

1. A cluster data read-write performance optimization method based on distributed storage Oracle RAC comprises the following steps:
dividing a part of storage space in 2 or more server nodes of an Oracle Rac cluster;
secondly, mounting the marked storage space to other servers with database instances in an Oracle Rac cluster through an iSCSI protocol operated by a common Ethernet or an infiniband high-bandwidth low-delay network;
and thirdly, the server in the Oracle RAC creates and aggregates the identified iSCSI disks through the DM and realizes multi-path management.
2. The distributed storage-based Oracle RAC cluster data read-write performance optimization method of claim 1, wherein: the server of the planned storage space does not directly access the storage space through any network.
3. The distributed storage-based Oracle RAC cluster data read-write performance optimization method of claim 1, wherein: all server nodes of the Oracle Rac cluster manage all mounted storage spaces through the ASM, and configure data redundancy of 2 or 3 copies.
4. The distributed storage-based Oracle RAC cluster data read-write performance optimization method of claim 1, wherein: the Oracle RAC server identifies and marks the local medium through a local priority reading algorithm, detects whether the data to be accessed exist on the local medium or not, and preferentially reads the data from the local medium if the data to be accessed exist on the local medium.
CN201810271075.1A 2018-03-29 2018-03-29 Cluster data read-write performance optimization method based on Oracle RAC Expired - Fee Related CN108595116B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810271075.1A CN108595116B (en) 2018-03-29 2018-03-29 Cluster data read-write performance optimization method based on Oracle RAC

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810271075.1A CN108595116B (en) 2018-03-29 2018-03-29 Cluster data read-write performance optimization method based on Oracle RAC

Publications (2)

Publication Number Publication Date
CN108595116A CN108595116A (en) 2018-09-28
CN108595116B true CN108595116B (en) 2021-04-20

Family

ID=63624884

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810271075.1A Expired - Fee Related CN108595116B (en) 2018-03-29 2018-03-29 Cluster data read-write performance optimization method based on Oracle RAC

Country Status (1)

Country Link
CN (1) CN108595116B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113111122A (en) * 2021-03-08 2021-07-13 北京世纪安图数码科技发展有限责任公司 Real estate registration data read-write separation method facing RAC cluster
CN114356239B (en) * 2021-12-30 2023-08-29 苏州浪潮智能科技有限公司 Distributed storage IO unloading method, system, equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7512707B1 (en) * 2005-11-03 2009-03-31 Adobe Systems Incorporated Load balancing of server clusters
CN102164161A (en) * 2011-01-10 2011-08-24 清华大学 Method and device for performing file layout extraction on parallel file system
CN102164177A (en) * 2011-03-11 2011-08-24 浪潮(北京)电子信息产业有限公司 Method, device and system for sharing storage pool by cluster
CN103595799A (en) * 2013-11-18 2014-02-19 北京中创信测科技股份有限公司 Method for achieving distributed shared data bank
CN103873559A (en) * 2014-02-13 2014-06-18 南京斯坦德通信股份有限公司 Database all-in-one machine capable of realizing high-speed storage
CN106686099A (en) * 2017-01-03 2017-05-17 杭州沃趣科技股份有限公司 Method of realizing active-active mode across machine rooms of OracleRAC database based on infiniband network

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7512707B1 (en) * 2005-11-03 2009-03-31 Adobe Systems Incorporated Load balancing of server clusters
CN102164161A (en) * 2011-01-10 2011-08-24 清华大学 Method and device for performing file layout extraction on parallel file system
CN102164177A (en) * 2011-03-11 2011-08-24 浪潮(北京)电子信息产业有限公司 Method, device and system for sharing storage pool by cluster
CN103595799A (en) * 2013-11-18 2014-02-19 北京中创信测科技股份有限公司 Method for achieving distributed shared data bank
CN103873559A (en) * 2014-02-13 2014-06-18 南京斯坦德通信股份有限公司 Database all-in-one machine capable of realizing high-speed storage
CN106686099A (en) * 2017-01-03 2017-05-17 杭州沃趣科技股份有限公司 Method of realizing active-active mode across machine rooms of OracleRAC database based on infiniband network

Also Published As

Publication number Publication date
CN108595116A (en) 2018-09-28

Similar Documents

Publication Publication Date Title
US11620064B2 (en) Asynchronous semi-inline deduplication
US20180024756A1 (en) Technologies for enhanced memory wear leveling
US7529830B2 (en) Storage system and communication control method
US20140136789A1 (en) Host side deduplication
US20140237202A1 (en) System for preventing duplication of autonomous distributed files, storage device unit, and data access method
EP1438671A2 (en) Protocol translation in a storage system
CN108595116B (en) Cluster data read-write performance optimization method based on Oracle RAC
CN109327332B (en) LIO-based iSCSI GateWay high-availability implementation method under Ceph cloud storage
CN107422989B (en) Server SAN system multi-copy reading method and storage system
US20160352831A1 (en) Methods for sharing nvm ssd across a cluster group and devices thereof
US20230409227A1 (en) Resilient implementation of client file operations and replication
CN106066890A (en) A kind of distributed high-performance data storehouse integrated machine system
US9513996B2 (en) Information processing apparatus, computer-readable recording medium having stored program for controlling information processing apparatus, and method for controlling information processing apparatus
CN105187502A (en) Method and system based on distributed elastic block storage
EP3180697A1 (en) Coalescing storage operations
US8117493B1 (en) Fast recovery in data mirroring techniques
US20150213047A1 (en) Coalescing sequences for host side deduplication
WO2002050681A1 (en) Method and apparatus for unified storage of data for storage area network systems and network attached storage systems
CN110663034B (en) Method for improved data replication in cloud environment and apparatus therefor
US11275698B2 (en) Termination of non-volatile memory networking messages at the drive level
US10498815B2 (en) Data recovery objective modeling
CN107291390B (en) Data hierarchical storage method and device
CN103037031A (en) Internet protocol (IP) address administration method of internet small computer system interface (ISCSI) target device
KR101943902B1 (en) Data movement service delivery method on the san network environment
US10860334B2 (en) System and method for centralized boot storage in an access switch shared by multiple servers

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20210420