Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Draft slide of Demystifying DHT in GlusterFS

Demystifying DHT in GlusterFS

  • Be the first to comment

  • Be the first to like this

Draft slide of Demystifying DHT in GlusterFS

  1. 1. Demystifying DHT in GlusterFS Ankit Raj
  2. 2. ●Why we need distributed file system...? Storing and accessing files in a client/server architecture. ● Uses multiple servers to store data and use multiple clients (local or remote). ● Organizes and displays files and directories from multiple servers as if they were ● stored in your local system. ● It is easier to distribute documents to multiple clients, provide a centralized storage ● system ● Client machines are not using their resources to store the data.
  3. 3. Terminology ● Bricks ● Volume ● Node ● Translator ● Trusted pool storage ● volfile
  4. 4. Why DHT? ● Why we use distributed hash model for glusterfs
  5. 5. How DHT solve your problem? ● Will describe it’s internal working
  6. 6. DHT fops ● Mkdir ● Create ● Lookup ● Lookup-selfheal ● Rmdir ● Read ● Rename ● Unlink
  7. 7. Managing Scalability in GlusterFS ● Expand volumes ● Rebalance ● How rebalance works: ● Shrink volumes ● Replace brick
  8. 8. ● Q&A