Ceph erasure code : ready for alpha testing

The addition of erasure code in Ceph started in april 2013 and was discussed during the first Ceph Developer Summit. The implementation reached an important milestone a few days ago and it is now ready for alpha testing.
For the record, here is the simplest way to store and retrieve an object in an erasure coded pool as of today:

parameters="erasure-code-k=2 erasure-code-m=1"
./ceph osd crush rule create-erasure ecruleset \
  $parameters \
./ceph osd pool create ecpool 12 12 erasure \
  crush_ruleset=ecruleset \
./rados --pool ecpool put SOMETHING /etc/group
./rados --pool ecpool get SOMETHING /tmp/group
$ tail -3 /tmp/group

The chunks are stored in three objects and it can be reconstructed if any of them are lost.

find dev | grep SOMETHING
This entry was posted in ceph. Bookmark the permalink.

6 Responses to Ceph erasure code : ready for alpha testing

  1. demon says:

    Will the erasure code decrease the performance of Ceph compared to the current multi-copy method ?Thank you

    • Loic Dachary says:

      Yes, the erasure code pools are going to be significantly slower than the replicated pools. It is one of the tradeoff : slower storage using less space versus faster storage using more space.

  2. Per Simonsen says:

    Why are the erasure code pools slower than replicated pools?

  3. huangjun says:

    We use rados to bench the erasure-code pool and replicated pool, there are no big difference of performance in seq read and write tests. But when we test erasure-code + cache tier in Cephfs way, it apparently slow than repliacted pools.

Leave a Reply

Your email address will not be published. Required fields are marked *


You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>