1

Currently i am testing a openstack-swift cluster made of 1 proxy node and 6 storage nodes. Each host has ubuntu 12.04. I put 5000 containers each having a text 4.6 KB. Each storage node has a 100 GB disk mounted and formatted as a xfs partition. After the test when i check disk usage on the storage nodes i came acroos a strange behaviour.

Mount point: /srv/node/sdb1

  • 2.0M accounts
  • 2.5G containers
  • 40M objects
  • 0 tmp

As you can containers directory having only db files for indexing takes too much space. Anyone come across this kind of behaviour before? What can be the reason for containers using this much space?

  • What is your df -h output? – ewwhite Dec 13 '12 at 12:22
  • /dev/sdb1 100G 2.5G 98G 3% /srv/node/sdb1 – fgakk Dec 13 '12 at 12:27
0

@fga

Were you able to find reason for this? You can also try out ssbench to find out what is happening with your cluster. I would hope it will be helpful to your analysis.

  • Thank you for the answer.For tests sofar i have been using tsung. But i have heard of ssbench and been planning to run another test with version grizzly soon. – fgakk Nov 14 '13 at 11:33

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.