Commit Graph

1114 Commits

Author SHA1 Message Date
Sage Weil
0eba993fad doc/rados/operations/health-checks: document AUTH_BAD_CAPS
Signed-off-by: Sage Weil <sage@redhat.com>
2019-08-14 20:40:08 -05:00
Sage Weil
7e9ba0a1c1 doc/reados/operations/health-checks: document PG_SLOW_SNAP_TRIMMING
The mitigation steps are weak, but it's not clear concrete guidance to
provide.

Signed-off-by: Sage Weil <sage@redhat.com>
2019-08-14 20:40:08 -05:00
Sage Weil
078ef210d5 doc/rados/operations/health-checks: document MGR_DOWN
Signed-off-by: Sage Weil <sage@redhat.com>
2019-08-14 20:40:08 -05:00
Sage Weil
1b6745efb4 doc/rados/operations/health-alerts: document BLUESTORE_NO_COMPRESSION
Signed-off-by: Sage Weil <sage@redhat.com>
2019-08-14 20:40:08 -05:00
Anthony D'Atri
51fb48b0f7
doc: operations: correct 'comma-delimited'
CIDR blocks are comma-separated, not comma-delimited.

Signed-off-by: Anthony D'Atri <anthony.datri@gmail.com>
2019-08-13 12:50:39 -07:00
Josh Durgin
3f18ed55aa
Merge pull request #28227 from sseshasa/monCachePriority
mon/OSDMonitor: Use generic priority cache tuner for mon caches

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2019-08-09 14:23:39 -07:00
Sage Weil
f011c13547 Merge PR #29292 into master
* refs/pull/29292/head:
	os/bluestore: warn on no per-pool omap
	os/bluestore: fsck: warning (not error) by default on no per-pool omap
	os/bluestore: fsck: int64_t for error count
	os/bluestore: default size of 1 TB for testing
	os/bluestore: behave if we *do* set PGMETA and PERPOOL flags
	os/bluestore: do not set both PGMETA_OMAP and PERPOOL_OMAP
	os/bluestore: fsck: only generate 1 error per omap_head
	os/bluestore: make fsck repair convert to per-pool omap
	os/bluestore: teach fsck to tolerate per-pool omap
	os/bluestore: ondisk format change to 3 for per-pool omap
	mon/PGMap: add data/omap breakouts for 'df detail' view
	osd/osd_types: separate get_{user,allocated}_bytes() into data and omap variants
	mon/PGMap: fix stored_raw calculation
	mon/PGMap: add in actual omap usage into per-pool stats
	osd: report per-pool omap support via store_statfs_t
	os/bluestore: set per_pool_omap key on mkfs
	osd/osd_types: count per-pool omap capable OSDs
	os/bluestore: report omap_allocated per-pool
	os/bluestore: add pool prefix to omap keys
	kv/KeyValueDB: take key_prefix for estimate_prefix_size()
	os/bluestore: fix manual omap key manipulation to use Onode::get_omap_key()
	os/bluestore: make omap key helpers Onode methods
	os/bluestore: add Onode::get_omap_prefix() helper
	os/bluestore: change _do_omap_clear() args

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2019-08-09 10:40:45 -05:00
Sage Weil
b8501164ef os/bluestore: warn on no per-pool omap
Signed-off-by: Sage Weil <sage@redhat.com>
2019-08-09 08:21:18 -05:00
Neha Ojha
c9d2833b25
Merge pull request #29425 from aclamk/wip-bluestore-monitor-allocations
[bluestore][tools] Inspect allocations in bluestore

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Igor Fedotov <ifedotov@suse.com>
Reviewed-by: Neha Ojha <nojha@redhat.com>
2019-08-07 11:37:34 -07:00
Adam Kupczyk
713f9b4d09 doc/rados/operations/health-checks: document BlueStore fragmentation and BlueFS space available features
Signed-off-by: Adam Kupczyk <akupczyk@redhat.com>
2019-08-07 19:18:21 +02:00
Sridhar Seshasayee
3b96417e18 mon/OSDMonitor: Use generic priority cache tuner for mon caches
Use priority cache manager to tune inc, full and rocksdb caches.

Signed-off-by: Sridhar Seshasayee <sseshasa@redhat.com>
2019-08-06 20:22:16 +05:30
Jan Fajerski
f0746bbbec
Merge pull request #27859 from jan--f/update-bluestore-cache-doc
doc: update bluestore cache settings and clarify data fraction
2019-08-06 13:32:58 +02:00
Sage Weil
c6eafb7343 Merge PR #29337 into master
* refs/pull/29337/head:
	mon: enable telemetry module by default
	mgr/telemetry: force re-opt-in if the report contents change
	mgr/telemetry: less noise in the log
	mgr/telemetry: wake up serve on config change
	mgr/telemetry: track telemetry report revisions

Reviewed-by: Neha Ojha <nojha@redhat.com>
2019-08-05 13:08:53 -05:00
Abhishek L
067db76a4c
Merge pull request #29364 from capri1989/doc-pg-num
doc: pg_num should always be a power of two

Reviewed-By: Jan Fajerski <jfajerski@suse.com>
Reviewed-By: Sage Weil <sage@redhat.com>
Reviewed-By: Abhishek Lekshmanan <abhishek@suse.com>
2019-08-01 14:18:53 +02:00
Sage Weil
143e1f0469 mgr/telemetry: force re-opt-in if the report contents change
Signed-off-by: Sage Weil <sage@redhat.com>
2019-07-31 20:33:19 -05:00
Lars Marowsky-Bree
3a7e171df6 doc: Address further comments on choosing pg_num
Signed-off-by: Lars Marowsky-Bree <lmb@suse.com>
2019-07-31 15:14:04 +02:00
Lars Marowsky-Bree
bd20d692bb doc: adjust examples to use 2^n pg_num
The examples used pg_num set to 300 or 1000. This misled some users.

Signed-off-by: Lars Marowsky-Bree <lmb@suse.com>
2019-07-31 15:03:48 +02:00
Kai Wagner
3660e17e4b doc: pg_num should always be a power of two
Signed-off-by: Kai Wagner <kwagner@suse.com>
2019-07-30 08:35:16 +02:00
Jan Fajerski
9d8336a7f4 doc: update bluestore cache settings and clarify data fraction
Fixes: http://tracker.ceph.com/issues/39522

Signed-off-by: Jan Fajerski <jfajerski@suse.com>
2019-07-29 13:58:32 +02:00
Kefu Chai
3ed3de6c96 doc/rados/operations: crush_rule is a name
like
```
ceph osd pool set <pool-name> crush_rule <rule-name>
```
where `<rule-name>` is a string instead of a number.

Signed-off-by: Kefu Chai <kchai@redhat.com>
2019-07-27 21:35:39 +08:00
Sage Weil
0c0093e450 Merge PR #29034 into master
* refs/pull/29034/head:
	doc/mgr/crash: document missing commands, options
	qa/suites/rados/singleton/all/test-crash: whitelist RECENT_CRASH
	qa/suites/rados/mgr/tasks/insights: whitelist RECENT_CRASH
	qa/tasks/mgr/test_insights: crash module now rejects bad crash reports
	mgr/telemetry: fix remote into crash do_ls()
	mgr/crash: don't make these methods static
	mgr/BaseMgrModule: handle unicode health detail strings
	mgr/crash: verify timestamp is valid
	qa/suites/mgr: whitelist RECENT_CRASH
	mgr/crash: remove unused var
	mgr/crash: remove unused import 'six'
	qa/workunits/rados/test_crash: health check
	mgr/crash: improve validation on post
	mgr/crash: automatically prune old crashes after a year
	mgr/crash: raise RECENT_CRASH warning for recent (new) crashes
	mgr/crash: add 'crash ls-new'
	mgr/crash: add option and serve infra
	mgr/crash: keep copy of crashes in memory
	mgr/pg_autoscaler: adjust style to match built-in tables
	mgr/crash: make 'crash ls' a nice table with a NEW column
	mgr/crash: nicely format 'crash info' output
	mgr/crash: add 'crash archive <id>', 'crash archive-all' commands

Reviewed-by: Neha Ojha <nojha@redhat.com>
2019-07-24 17:20:21 -05:00
Kefu Chai
e6aee61076
Merge pull request #28772 from neha-ojha/wip-40528-2
osd: add hdd, ssd and hybrid variants for osd_snap_trim_sleep

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: David Zafman <dzafman@redhat.com>
2019-07-24 09:24:14 +08:00
Sage Weil
c885ee7f0c mgr/crash: raise RECENT_CRASH warning for recent (new) crashes
Signed-off-by: Sage Weil <sage@redhat.com>
2019-07-19 09:43:04 -05:00
Patrick Donnelly
a256c42d47
doc/cephfs: improve add/remove MDS section
Include hardware details and update language for modern tools.

Fixes: http://tracker.ceph.com/issues/39620
Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
2019-07-12 17:11:12 -07:00
Nathan Cutler
31f29d796a doc: cover more cache modes in rados/operations/cache-tiering.rst
Fixes: http://tracker.ceph.com/issues/14153
Signed-off-by: Nathan Cutler <ncutler@suse.com>
2019-07-09 17:06:05 +02:00
Kefu Chai
00a67b07b1
Merge pull request #28753 from tchaikov/wip-doc-conf
doc/rados/configuration: update to be in sync with ConfUtils changes

Reviewed-by: Neha Ojha <nojha@redhat.com>
Reviewed-by: Brad Hubbard <bhubbard@redhat.com>
2019-07-04 13:23:24 +08:00
Xie Xingguo
873db7c2ef
Merge pull request #28805 from Rjerk/fix-doc
doc/rados/configuration: fix typos in osd-config-ref.rst

Reviewed-by: Kefu Chai <kchai@redhat.com>
2019-07-02 11:55:55 +08:00
Lan Liu
2d71227e43 doc/rados/configuration: fix typos in osd-config-ref.rst
Signed-off-by: Lan Liu <liulan@umcloud.com>
2019-07-02 10:22:03 +08:00
Kefu Chai
eceed56b95 doc/rados/configuration: update to be in sync with ConfUtils changes
Signed-off-by: Kefu Chai <kchai@redhat.com>
2019-07-02 10:13:02 +08:00
Kefu Chai
60403c0a21
Merge pull request #28750 from neha-ojha/wip-40488
doc/rados/operations/erasure-code.rst: allow recovery below min_size

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
Reviewed-by: Kefu Chai <kchai@redhat.com>
2019-07-02 10:00:03 +08:00
Gregory Farnum
0d9ea078f1 doc: update erasure-code.rst with review comments.
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
2019-06-28 14:52:47 -07:00
Gregory Farnum
4f246cf74d doc: update erasure code recovery description
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
2019-06-28 14:52:30 -07:00
Sage Weil
b4757f32a7 Merge PR #28491 into master
* refs/pull/28491/head:
	doc/rados/operations: add safe-to-destroy check to OSD replacement workflow

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2019-06-28 13:44:18 -05:00
Neha Ojha
733df09fe5 common/options.cc, doc: osd_snap_trim_sleep overrides other variants
A value > 0 for osd_snap_trim_sleep, will override the backend specific
variants of osd_snap_trim_sleep.

Signed-off-by: Neha Ojha <nojha@redhat.com>
2019-06-28 09:53:01 -07:00
Neha Ojha
bad43f856d
Merge pull request #28775 from neha-ojha/wip-doc-delete-sleep
doc/rados/configuration/osd-config-ref.rst: document osd_delete_sleep

Reviewed-by: Sage Weil <sage@redhat.com>
2019-06-28 09:11:00 -07:00
Neha Ojha
981babc8fa doc/rados/configuration/osd-config-ref.rst: document osd_delete_sleep
Signed-off-by: Neha Ojha <nojha@redhat.com>
2019-06-27 17:21:58 -07:00
Neha Ojha
accf95e9de doc/rados/configuration/osd-config-ref.rst: document snap trim sleep
Signed-off-by: Neha Ojha <nojha@redhat.com>
2019-06-27 12:46:41 -07:00
Sage Weil
0a28dd0348 doc/rados/operations: add safe-to-destroy check to OSD replacement workflow
Signed-off-by: Sage Weil <sage@redhat.com>
2019-06-27 10:42:17 -05:00
Neha Ojha
bfccdecb94 doc/rados/operations/erasure-code.rst: allow recovery below min_size
https://github.com/ceph/ceph/pull/17619 allows recovery below min_size
for EC pools starting in Octopus. Also mention that this wasn't allowed
earlier.

Fixes: https://tracker.ceph.com/issues/40488
Signed-off-by: Neha Ojha <nojha@redhat.com>
2019-06-25 15:48:48 -07:00
Kefu Chai
1b0eb21220
Merge pull request #28677 from liewegas/wip-recovery-nvme
osd: add hdd and ssd variants for osd_recovery_max_active

Reviewed-by: Neha Ojha <nojha@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Mark Nelson <mnelson@redhat.com>
2019-06-23 01:56:42 +08:00
Sage Weil
35c0d75888 osd: add hdd and ssd variants for osd_recovery_max_active
Semi-arbitrarily set the SSD max to 10 (instead of 3).  This should be
tuned based on some real data.

Signed-off-by: Sage Weil <sage@redhat.com>
2019-06-20 16:24:51 -05:00
David Zafman
fa698e18e1 mon: Improve health status for backfill_toofull and recovery_toofull
Treat backfull_toofull as a warning condition because it can resolve itself.
Includes test case for PG_BACKFILL_FULL
Includes test case for recovery_toofull / PG_RECOVERY_FULL

Fixes: https://tracker.ceph.com/issues/39555

Signed-off-by: David Zafman <dzafman@redhat.com>
2019-06-20 02:22:01 +00:00
Kefu Chai
ce26c99bed
Merge pull request #28418 from xiexingguo/wip-kick-recovery-priority
osd: give recovery ops initialized by client op a higher priority

Reviewed-by: Neha Ojha <nojha@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
2019-06-18 23:29:42 +08:00
Hannes von Haugwitz
65c6425489 doc: update mondb recovery script
- be specific about stopped OSDs
- add missing '--no-mon-config' option
- fix indent of here script delimiting identifier
- use $host variable in for loop

Signed-off-by: Hannes von Haugwitz <hannes@vonhaugwitz.com>
2019-06-12 17:16:25 +02:00
xie xingguo
c0f87e0f91 osd: give recovery ops initialized by client op a higher priority
to use strict priority ordering.

The new "mclock_opclass/mclock_client" queue basically prioritizes
operations based on the class they belong to. The priority property
of an operation, if lower than a specific value (64, by default),
will get ignored and hence all operations from the same class will
be treated fairly in a FIFO fashion (but still limited by the total
IOPS or bandwidth available for the corresponding class).

To reduce the impact of performance, a more general strategy would be
enforcing some limitations on the IOPS or bandwidth for the background
recovery (or backfill) operation class. However, this way we'll end up
blocking client operations too if they are currently blocked by some
degraded objects which need to be recovered first.

We hereby grant recovery operations of this kind a higher priority
to force them to use strict priority ordering, which should still
be of significance once we switch to the new "mclock_opclass/mclock_client"
queue.

Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
2019-06-11 15:46:57 +08:00
Xie Xingguo
302d7bcdd8
Merge pull request #27735 from xiexingguo/wip-device-class-noout
osd: revamp {noup,nodown,noin,noout} related commands

Reviewed-by: Sage Weil <sage@redhat.com>
2019-06-05 14:17:06 +08:00
Jason Dillaman
d23bdb7931
Merge pull request #28296 from mcv21/doc-profile-rbd
doc: note explicitly that "profile rbd" allows blacklisting

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
2019-05-31 08:29:21 -04:00
Kefu Chai
f6b022bdbe
Merge pull request #27806 from ashitakasam/add-osd-alarm
osd: Better error message when OSD count is less than osd_pool_default_size

Reviewed-by: Neha Ojha <nojha@redhat.com>
2019-05-30 21:28:54 +08:00
xie xingguo
a3b0dc29b9 doc: refresh {noup,nodown,noin,noout} changes
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
2019-05-30 10:52:38 +08:00
Matthew Vernon
6812582222 doc: note explicitly that "profile rbd" allows blacklisting
The Luminous release notes tell users to ensure that rbd clients have
the ability to blacklist other client users; this is provided by
"profile rbd", which this change now documents explicitly in the user
management documentation.

Signed-off-by: Matthew Vernon <mv3@sanger.ac.uk>
2019-05-29 14:36:48 +01:00