User Tools

Site Tools


institute_lorentz:institutelorentz_maris_gluster

GlusterFS on maris

:!: AS of 1/5/2017 THIS PROJECT HAS BEEN DISCONTINUED BECAUSE NOT POPULAR

We have configured a GlusterFS to provide all maris users with extra 3TB of scrap storage.

GlusterFS is a scalable network filesystem that can use common off-the-shelf hardware to create large, distributed storage solutions for media streaming, data analysis, and other data- and bandwidth-intensive tasks.

Currently, access to this file system is enabled only on novamaris and the following maris nodes: maris049,maris050,maris051,maris052,maris053,maris054,maris055,maris056.

Access GlusterFS

The maris GlusterFS is mounted under the /maris-replicated-4×2 mount point on the nodes mentioned above.

The mount-point name `maris-replicated-4×2' was not chosen by chance. In fact the maris GlusterFS is a Distributed Replicated Glusterfs Volume in a four-by-two (4×2) configuration as explained in the section below.

Distributed Replicated GlusterFS Volume

A `Volume' is a collection of bricks and most of the gluster file system operations happen on the volume. GlusterFS supports different types of volumes based on the requirements. Some volumes are good for scaling storage size, some for improving performance and some for both.

The simplest GlusterFS configuration is the distributed volume configuration. Here, because files are distributed across various bricks in the volume, there is no data redundancy.

To add a degree of redundancy in case of disk(s) failure we opted to configure maris GlusterFS as a `distributed replicated volume'. In this volume files are distributed across replicated sets of bricks. The number of bricks is a multiple of the replica count. Adjacent bricks become replicas of each other. This type of volume is used when high availability of data due to redundancy and scaling storage is required. In maris' case there are eight bricks and a replica count 2, so the first two bricks become replicas of each other then the next two and so on. This volume is denoted as 4×2. Hence the name give to the mountpoint.

A simplified schematic representation of the maris glusterFS volume configuration is given below (only two bricks..)

:!: Although, there is a redundancy for the files in /maris-replicated-4×2, you are the ONLY person responsible to maintain a backup of your own data.

maris GlusterFS volume info

Volume Name: maris-replicated-4x2
Type: Distributed-Replicate
Volume ID: 4844f04c-2e4e-41ae-9e05-8b62ecf81fcf
Status: Started
Number of Bricks: 4 x 2 = 8
Transport-type: tcp
Bricks:
Brick1: gluster049:/export/gluster/brick
Brick2: gluster050:/export/gluster/brick
Brick3: gluster051:/export/gluster/brick
Brick4: gluster052:/export/gluster/brick
Brick5: gluster053:/export/gluster/brick
Brick6: gluster054:/export/gluster/brick
Brick7: gluster055:/export/gluster/brick
Brick8: gluster056:/export/gluster/brick
Options Reconfigured:
performance.readdir-ahead: on

GlusterFS network

maris GlusterFS uses dedicated network interfaces for efficiency.

institute_lorentz/institutelorentz_maris_gluster.txt · Last modified: 2017/05/03 09:20 by lenocil