Difference between revisions of "Luster Intel: Notes from training"

From Define Wiki
Jump to navigation Jump to search
(Created page with "== Luster Training, Swindon, January 2014 == === What is lustre === * multi vendor global parallel file system * Parallel, Shared, Multi-Vendor, Open source, Scalable, Provi...")
 
(No difference)

Latest revision as of 11:15, 29 January 2014

Luster Training, Swindon, January 2014

What is lustre

  • multi vendor global parallel file system
  • Parallel, Shared, Multi-Vendor, Open source, Scalable, Provided by intel
  • Not currently a windows client - working on a samba client that will produce good, but not great results
  • scale out = more servers = more bandwidth
  • scale up = more targets = more storage

Meta Data Servers

  • turn on HT to make use of as many threads as possible
  • 2.5 is going to focus on the meta date server - looking to turn it into a cluster
  • Can be set up with HA failover

Object servers

  • Suggest setting up with pairs to allow for failover

Main Componants

  • Management Target - Luster mount service, intal point on contact
  • Metadata Target
  • Object Storage Targets

General Recommendations

Managment - Barebones install on its on system (avoid sharing databases etc)

Retrieved from "http://wiki.define-technology.com/mediawiki-1.35.0/index.php?title=Luster_Intel:_Notes_from_training&oldid=3907"