ceph/doc/start/intro.rst

   1 ===============
   2  Intro to Ceph
   3 ===============
   4
   5 Whether you want to provide :term:`Ceph Object Storage` and/or :term:`Ceph Block
   6 Device` services to :term:`Cloud Platforms`, deploy a :term:`Ceph Filesystem` or
   7 use Ceph for another purpose, all :term:`Ceph Storage Cluster` deployments begin
   8 with setting up each :term:`Ceph Node`, your network and the Ceph Storage
   9 Cluster. A Ceph Storage Cluster requires at least one Ceph Monitor and at least
  10 two Ceph OSD Daemons. The Ceph Metadata Server is essential when running Ceph
  11 Filesystem clients.
  12
  13 .. ditaa::  +---------------+ +---------------+ +---------------+
  14             |      OSDs     | |    Monitor    | |      MDS      |
  15             +---------------+ +---------------+ +---------------+
  16
  17 - **Ceph OSDs**: A :term:`Ceph OSD Daemon` (Ceph OSD) stores data, handles data
  18   replication, recovery, backfilling, rebalancing, and provides some monitoring
  19   information to Ceph Monitors by checking other Ceph OSD Daemons for a
  20   heartbeat. A Ceph Storage Cluster requires at least two Ceph OSD Daemons to
  21   achieve an ``active + clean`` state when the cluster makes two copies of your
  22   data (Ceph makes 3 copies by default, but you can adjust it).
  23
  24 - **Monitors**: A :term:`Ceph Monitor` maintains maps of the cluster state,
  25   including the monitor map, the OSD map, the Placement Group (PG) map, and the
  26   CRUSH map. Ceph maintains a history (called an "epoch") of each state change
  27   in the Ceph Monitors, Ceph OSD Daemons, and PGs.
  28
  29 - **MDSs**: A :term:`Ceph Metadata Server` (MDS) stores metadata on behalf of
  30   the :term:`Ceph Filesystem` (i.e., Ceph Block Devices and Ceph Object Storage
  31   do not use MDS). Ceph Metadata Servers make it feasible for POSIX file system
  32   users to execute basic commands like ``ls``, ``find``, etc. without placing
  33   an enormous burden on the Ceph Storage Cluster.
  34
  35 Ceph stores a client's data as objects within storage pools. Using the CRUSH
  36 algorithm, Ceph calculates which placement group should contain the object,
  37 and further calculates which Ceph OSD Daemon should store the placement group.
  38 The CRUSH algorithm enables the Ceph Storage Cluster to scale, rebalance, and
  39 recover dynamically.
  40
  41
  42 .. raw:: html
  43
  44         <style type="text/css">div.body h3{margin:5px 0px 0px 0px;}</style>
  45         <table cellpadding="10"><colgroup><col width="50%"><col width="50%"></colgroup><tbody valign="top"><tr><td><h3>Recommendations</h3>
  46
  47 To begin using Ceph in production, you should review our hardware
  48 recommendations and operating system recommendations.
  49
  50 .. toctree::
  51    :maxdepth: 2
  52
  53    Hardware Recommendations <hardware-recommendations>
  54    OS Recommendations <os-recommendations>
  55
  56
  57 .. raw:: html
  58
  59         </td><td><h3>Get Involved</h3>
  60
  61    You can avail yourself of help or contribute documentation, source
  62    code or bugs by getting involved in the Ceph community.
  63
  64 .. toctree::
  65    :maxdepth: 2
  66
  67    get-involved
  68    documenting-ceph
  69
  70 .. raw:: html
  71
  72         </td></tr></tbody></table>