Commit Graph

307 Commits

Author SHA1 Message Date
Jason Dillaman
878d0b0c3f doc: document pool tags in rados pool operations doc
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
2017-07-19 13:13:01 -04:00
Kefu Chai
a0d935966c doc: add instructions for replacing an OSD
* 8/ceph.rst: `rm` subcommand removes osd from osdmap, not the cluster.
  the latter is more ambiguous in different contexts.
* rados/operations/add-or-rm-osds.rst: add a subsection of "Replacing an
  OSD". update the subsection of "Removing the OSD" with "ceph osd
  purge" command
* release-notes.rst: link from it to the new subsection in add-or-rm-osds.rst

Signed-off-by: Kefu Chai <kchai@redhat.com>
2017-07-19 11:23:47 +08:00
Sage Weil
8b21c6b6fd Merge pull request #16027 from liewegas/wip-crush-rule-class
mon,crush: create crush rules using device classes for replicated and ec pools via cli

Reviewed-by: Loic Dachary <ldachary@redhat.com>
2017-07-08 21:34:13 -05:00
Kefu Chai
254e07441c doc: kill sphinx warnings
* doc/release-notes.rst: escape asterisks not used for inline emphasis
    fix bad hyper links
* doc/rados/troubleshooting/troubleshooting-osd.rst: escape asterisks
    not used for inline emphasis
* doc/radosgw/index.rst: add orphan docs to toc
* doc/dev/perf_histograms.rst: indent block quote
* doc/install/manual-freebsd-deployment.rst: fix block quotes
* doc/mgr/administrator.rst: escape asterisks not used for inline emphasis
* doc/start/quick-rbd.rst: add missing hyper link target

Signed-off-by: Kefu Chai <kchai@redhat.com>
2017-07-07 11:50:33 +08:00
Sage Weil
dc7a2aaf7a erasure-code: ruleset-* -> crush-*
1) ruleset is an obsolete term, and
2) crush-{rule,failure-domain,...} is more descriptive.

Note that we are changing the names of the erasure code profile keys
from ruleset-* to crush-*.  We will update this on upgrade when the
luminous flag is set, but that means that during mon upgrade you cannot
create EC pools that use these fields.

When the upgrade completes (users sets require_osd_release = luminous)
existing ec profiles are updated automatically.

Signed-off-by: Sage Weil <sage@redhat.com>
2017-07-06 15:01:03 -04:00
Greg Farnum
51838305a2 osdmap: do not automatically create an rbd pool on cluster creation; skip pool 0
We don't use pool ID 0 any more because CephFS can't handle it.
Update the user quick-start to include it, and add some links to support that process.
Fix the tests to handle the new state of life.

Signed-off-by: Greg Farnum <gfarnum@redhat.com>
2017-06-28 10:52:49 -04:00
Sage Weil
8f44e6f69a doc/start/os-recommendations: update
Signed-off-by: Sage Weil <sage@redhat.com>
2017-06-23 10:36:19 -04:00
Greg Farnum
6846f4830c mgr: print a more helpful error message for when users lack mgr cephx caps
Add some brief documentation on updating their caps and link to it.

Fixes: http://tracker.ceph.com/issues/20296

Signed-off-by: Greg Farnum <gfarnum@redhat.com>
2017-06-16 18:41:10 -07:00
liuchang0812
998ee1d190 doc: kill some broken links
Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
2017-06-07 16:13:45 +08:00
MinSheng Lin
e86cef3134 doc: fix broken link in erasure-code.rst
Fixes: http://tracker.ceph.com/issues/19972
Signed-off-by: MinSheng Lin <minsheng.l@inwinstack.com>
2017-05-18 09:48:07 +08:00
Sage Weil
1919297826 Merge pull request #14494 from drunkard/master
doc: two minor fixes
2017-04-25 12:11:03 -05:00
Josh Durgin
bad606605a doc: update ec docs for overwrite support
Signed-off-by: Josh Durgin <jdurgin@redhat.com>
2017-04-19 17:45:43 -07:00
Josh Durgin
930eae214c OSDMonitor: get stripe_width via stripe_unit in ec profile
With bluestore, making the smallest write match min_alloc_size avoids
write amplification. With EC pools this is the stripe unit, or
stripe_width / num_data_chunks. Rather than requiring people to divide
by k to get the smallest ec write, allow it to be specified directly
via stripe_unit. Store it in the ec profile so changing a monitor
config option isn't necessary to set it.

This is particularly important for ec overwrites since they allow random i/o
which should match bluestore's checksum granularity (aka min_alloc_size).

Signed-off-by: Josh Durgin <jdurgin@redhat.com>
2017-04-19 17:45:43 -07:00
David Zafman
a5731076ad osd: Handle backfillfull_ratio just like nearfull and full
Add BACKFILLFULL as a local OSD cur_state
Notify monitor of this new fullness state

Signed-off-by: David Zafman <dzafman@redhat.com>
2017-04-17 08:00:24 -07:00
David Zafman
79a4ac41c5 common: Remove unused config option osd_recovery_threads
Signed-off-by: David Zafman <dzafman@redhat.com>
2017-04-17 07:58:30 -07:00
Drunkard Zhang
3c70331d6b doc: indent style fixes
Signed-off-by: Drunkard Zhang <gongfan193@gmail.com>
2017-04-13 12:51:44 +08:00
Sage Weil
b841ab2592 Merge pull request #14419 from badone/wip-doc-pg-states-min_size
docs: Clarify the relationship of min_size to EC pool recovery

Reviewed-by: Sage Weil <sage@redhat.com>
2017-04-11 21:10:35 -05:00
Patrick Dinnen
c5931484c9 doc: correct arguments for ceph tell osd.N bench
Signed-off-by: Patrick Dinnen pdinnen@gmail.com
2017-04-11 15:57:11 -04:00
Brad Hubbard
ac6123d7a6 docs: Clarify the relationship of min_size to EC pool recovery
Signed-off-by: Brad Hubbard <bhubbard@redhat.com>
2017-04-10 15:14:20 +10:00
Sven Seeberg
804134a2bf renamed hit_set_grade_search_last_n to hit_set_search_last_n
Signed-off-by: Sven Seeberg <sseebergelverfeldt@suse.com>
2017-03-24 10:25:06 +01:00
Kefu Chai
3ffa869af2 Merge pull request #13942 from xiexingguo/wip-cleanup-proc-repinfo
osd/PG: conditionally retry on receiving pg-notify when Primary is Incomplete

Reviewed-by: Sage Weil <sage@redhat.com>
2017-03-22 23:57:13 +08:00
xie xingguo
18c83bb97e osd/PG: kill PG_STATE_REPLAY
This replay state of PG is not functionable and
hence should not be made visible to user.

Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
2017-03-20 10:24:25 +08:00
Drunkard Zhang
33290a4f48 doc: typo fix in rados/operations/crush-map
Signed-off-by: Drunkard Zhang <gongfan193@gmail.com>
2017-03-16 14:40:31 +08:00
Loic Dachary
154f3d3d27 crush: document the class qualifier
The class qualifier is documented for devices and step take
only. Although it shows in the buckets and could be set by the user, it
would be very error prone to do so.

Refs: http://tracker.ceph.com/issues/18943

Signed-off-by: Loic Dachary <ldachary@redhat.com>
2017-03-01 17:24:09 +01:00
Sage Weil
9c881e99f4 Merge pull request #12923 from liewegas/wip-df-avail
mon/PGMap: factor mon_osd_full_ratio into MAX AVAIL calc

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2017-02-08 20:51:46 -06:00
Sage Weil
f223ac9291 mon/PGMap: factor mon_osd_full_ratio into MAX AVAIL calc
If we only fill OSDs to 95%, we should factor that into
the MAX AVAIL calculation for the pool.

Fixes: http://tracker.ceph.com/issues/18522
Signed-off-by: Sage Weil <sage@redhat.com>
2017-02-03 10:08:33 -05:00
Brad Hubbard
9549943761 doc: min_size advice is not helpful
When we are in the incomplete state adjusting min_size will not help with recovery.

Signed-off-by: Brad Hubbard <bhubbard@redhat.com>
2017-01-16 12:36:33 +10:00
Sage Weil
63bb2b7d45 doc: remove crash_replay_interval mentions
Signed-off-by: Sage Weil <sage@redhat.com>
2016-12-29 10:30:08 -05:00
Kefu Chai
f3d453d872 Merge pull request #12662 from Liuchang0812/doc-fix
doc: fix document about rados mon

Reviewed-by: Kefu Chai <kchai@redhat.com>
2016-12-27 21:09:06 +08:00
liuchang0812
52db747f32 doc: fix document about rados mon
Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
2016-12-27 14:59:04 +08:00
Brad Hubbard
c51a3afe03 doc: Remove "splitting" state
There is no splitting state so remove it from pg-states.rst

Signed-off-by: Brad Hubbard <bhubbard@redhat.com>
2016-12-23 09:23:19 +10:00
Brad Hubbard
e793376da8 doc: Modify documentation for mon_osd_down_out_interval
Update docs to reflect the new default of 600 set by 817d65bd4

Signed-off-by: Brad Hubbard <bhubbard@redhat.com>
2016-12-09 18:02:41 +10:00
Wido den Hollander
95ed04a536
doc: Add documentation about mon_allow_pool_delete before pool remove
Tell users they need to set this to true before Monitors will allow
pools to be removed.

Also update the Pending Release Notes so that users can find this change
there.

This was changed with commit 5d7f4ea

Signed-off-by: Wido den Hollander <wido@42on.com>
2016-11-23 12:18:21 +01:00
whu_liuchang
6735a681c5 Update crush-map.rst
fix typo
2016-11-04 22:14:39 +08:00
Patrick Donnelly
4323d47122
mds: remove deprecated commands from docs
This mostly is just removing the commands from the man page ceph(1). I
left the legacy section in doc/cephfs/administration.rst as-is.

Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
2016-10-12 10:58:38 -04:00
Sage Weil
784fe23812 doc: remove old .libs reference
Signed-off-by: Sage Weil <sage@redhat.com>
2016-09-26 15:50:30 -04:00
Alfredo Deza
c8dc8d3998 doc/rados: remove references to premium support from inktank.com
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2016-09-22 07:43:43 -04:00
Barbora Ančincová
a9c0e7b789 Removed reference about pool ownership based on BZ#1368528
Signed-off-by: Bara Ancincova <bara@redhat.com>

https://bugzilla.redhat.com/show_bug.cgi?id=1368528

From email conversation with Sage and Sam:

I don't think it is used at all, and at a minimum it is
untested and undocumented and the implementation is alomst
certainly incomplete.

I definitely support removing any trace of it from the docs.

sage
2016-09-13 17:38:25 +05:30
Kefu Chai
f468c73b6b Merge pull request #10619 from chengweiv5/fix-doc
doc: fix rados/configuration/osd-config-ref.rst

Reviewed-by: Kefu Chai <kchai@redhat.com>
2016-08-15 23:00:02 +08:00
Chengwei Yang
fed35dd37f doc: fix command format
Signed-off-by: Chengwei Yang <yangchengwei@qiyi.com>
2016-08-12 13:23:15 +08:00
John Wilkins
5621a9ca4c Lowered third example to keep PG count lower.
Signed-off-by: John Wilkins <jowilkin@redhat.com>
2016-08-11 14:41:54 -07:00
Albert Tu
7fca0e5036 doc: fix broken link in SHEC erasure code plugin
Fixes: http://tracker.ceph.com/issues/16996

Signed-off-by: Albert Tu <albert.t@inwinstack.com>
2016-08-11 16:15:51 +08:00
Kefu Chai
89ba840a6c Merge pull request #10190 from ktdreyer/doc-delete-pool
doc: more details for pool deletion

Reviewed-by: Brad Hubbard <bhubbard@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
2016-07-10 19:57:07 +08:00
Ken Dreyer
3c43185002 doc: more details for pool deletion
Prior to this change, the documention instructed administrators to
delete rulesets and users, but did not go into details regarding how to
do that.

Add example commands that admins may use to search for rulesets and
users that might reference the to-be-deleted pool.

Signed-off-by: Ken Dreyer <kdreyer@redhat.com>
2016-07-08 07:42:29 -06:00
Ken Dreyer
99e0ee1223 doc: rm SysV instructions, add systemd
Signed-off-by: Ken Dreyer <kdreyer@redhat.com>
2016-07-07 11:59:18 -06:00
Sage Weil
ef3a678911 Merge pull request #9135 from flaf/master
doc: improvement of the "tunables" part

Reviewed-by: Sage Weil <sage@redhat.com>
2016-05-16 03:48:48 -04:00
lafont
4cc820812c doc: improvement of the "tunables" part
* Some CRUSH_TUNABLES$N references were false.
* The explanations concerning the warning when tunables are
  non-optimal were false or confusing.
* Make the definition of the "default" profile clearer.

Signed-off-by: François Lafont <francois.lafont@ac-versailles.fr>
2016-05-16 05:15:06 +02:00
Sage Weil
7488c917af doc/rados: adjust example cache tiering settings
These are saner values.

Signed-off-by: Sage Weil <sage@redhat.com>
2016-05-13 10:58:50 -04:00
Sage Weil
fcd1d097b1 doc/rados: words of caution about cache tiering
Signed-off-by: Sage Weil <sage@redhat.com>
2016-05-13 10:58:50 -04:00
Sage Weil
6b6b38163b doc/rados: drop description of cache modes we don't recommend
Signed-off-by: Sage Weil <sage@redhat.com>
2016-05-11 08:15:53 -04:00