Glusterfs Distributed Storage (i)

Environment Preparation

1, centos6.8 System of virtual machines (four units)

2. Close Iptables and SELinux

3. Pre-installed Glusterfs package

Yum install-y centos-release-gluster37.noarchyum--enablerepo=centos-gluster*-test Install Glusterfs-server GLUSTERFS-CLI glusterfs-geo-replication

generation of Distributed File system

Computer through the file system management, storage data, and now the data explosion of information in the era of data can be obtained exponentially several times the growth, simply by increasing the number of hard disks to expand the computer file system storage capacity, has not been able to meet the current needs.

Distributed file system can effectively solve the data storage and management challenges, the fixed to a location of a file system, to any number of locations/multiple file systems, a large number of nodes to form a file system network. Each node can be distributed in different locations, communicating and transmitting data between nodes through the network. When people use distributed file systems, they do not need to worry about which node the data is stored on, or from which node, it is only necessary to manage and store the data in the file system as if it were a local file system.

• Typical NFS Representation

The network file system, which allows the sharing of resources across TCP/IP networks between computers in the network. In an NFS application, a local NFS client application can transparently read and write to files located on the remote NFS server, just as you would access a local file.

The benefits of NFS are as follows:

1. Conserve The disk space you use

The data that the client often uses can be centrally stored on a single machine and used for NFS publishing, so all computers inside the network can be accessed over the network without having to store them separately.

2. Save Hardware Resources

NFS can also share storage devices such as floppy drives, CDROM and zip, reducing the number of removable devices across the network.

3. Set up with the home owner directory

For special users, such as administrators, in order to manage the need, may often log on to all computers on the network, if each client, it is cumbersome to save the user's home directory, and does not guarantee the consistency of the data. In fact, the NFS service is set, then the client specifies the user's home directory location, and automatically mounts, you can use the user home directory file on any computer.

• The problems facing

There is not enough storage space to store more capacity.

Mount storage directly with NFS, there is a certain risk, there is a single point of failure.

Some scenarios do not meet the requirements, and a large amount of access to disk IO is a bottleneck.

GlusterFS Introduction

Glusterfs is the core of the Scale-out storage solution Gluster, an open source Distributed file system with strong scale-out capability to support petabytes of storage capacity and handle thousands of of clients through scaling. The Glusterfs aggregates the physically distributed storage resources with TCP/IP or InfiniBand RDMA networks, using a single global namespace to manage the data. The Glusterfs is based on a stackable user space design that provides superior performance for a variety of data loads.

Glusterfs supports standard clients running standard applications on any standard IP network, and users can access application data using standard protocols such as NFS/CIFS in a globally unified namespace. The glusterfs allows users to get rid of their original, high-cost, closed storage systems and to deploy a centrally managed, scale-out, virtualized storage pool that can be scaled to the TB/PB level using inexpensive storage devices.

Currently Glusterfs has been acquired by Redhat, its official website: http://www.gluster.org/

GlusterFS application Scenarios in the Enterprise

Theoretical and practical analysis, Glusterfs is mainly applicable to large file storage scenarios, for small files, especially massive small files, storage efficiency and access performance are poor performance. Massive small file LOSF problem is recognized by industry and academia, Glusterfs as a general-purpose distributed File system, there is no additional optimization measures for small files, performance is not good also understandable.

Media? documents, pictures, audio, video

Shared storage? Cloud storage, virtualized storage, HPC (High performance computing)

Big data? Log file, RFID (radio frequency identification) data

Glusterfs Distributed Storage (i)