RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2025-02-24 11:37:37 +00:00
Code Issues Packages Projects Releases Wiki Activity
76,339 Commits 216 Branches 395 Tags 1.4 GiB
139cc382ab
Commit Graph

76339 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Kefu Chai
9dea6dc763 Merge pull request #16589 from Yan-waller/wip-walle-0726testwatchnotify 
test/rados: fix wrong parameter order of RETURN1_IF_NOT_VAL

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-07-28 13:14:07 +08:00
Kefu Chai
b3b972c733 Merge pull request #16609 from wjwithagen/wip-wjw-FreeBSD-group-wheel 
ceph_disk/main.py: FreeBSD root has wheel for group

Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-07-28 13:13:28 +08:00
Kefu Chai
55a3e5790e Merge pull request #16593 from shangzhong/wip-20660 
os/bluestore/StupidAllocator: rounded down len to an align boundary

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-07-28 13:07:06 +08:00
Sage Weil
9bc2b74798 common/options: document bluestore options 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-07-27 22:31:51 -04:00
Sage Weil
5bc9f6dafe compressor: accept 'none' or '' for none 
This makes the parse and output methods match up.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-07-27 22:30:12 -04:00
Sage Weil
5fd23dcf26 os/bluestore: observe bluestore_compression_required_ratio 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-07-27 22:30:12 -04:00
Sage Weil
625859b42b doc/dev/config: some guidance around defining config options 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-07-27 22:30:12 -04:00
Patrick Donnelly
fb039383e9
Merge PR #16435 into master 
* refs/remotes/upstream/pull/16435/head:
	qa: whitelist trim error during powercycle tests

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-07-27 17:54:59 -07:00
Sage Weil
89cf82c599 mgr/PyState: shut up about get_config on nonexistent keys 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-07-27 18:06:22 -04:00
Patrick Donnelly
ced01a2335
qa: fix wait for wrong health message 
Fixes: http://tracker.ceph.com/issues/20805

Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
 2017-07-27 14:40:05 -07:00
Sage Weil
cb12a81905 Merge pull request #16450 from markhpc/wip-rocksdb-bloomsettings 
kv/RocksDBStore: Table options for indexing and filtering

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-07-27 16:26:09 -05:00
Sage Weil
41bcf2fee5 Merge pull request #16281 from badone/wip-PG-cluster-log-audit 
osd: Log audit

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-07-27 16:25:30 -05:00
Sage Weil
862392fbf9 Merge pull request #16514 from liewegas/wip-20744 
qa/tasks/ceph: wait for mgr to activate and pg stats to flush in health()

Reviewed-by: John Spray <john.spray@redhat.com>
 2017-07-27 16:24:59 -05:00
Sage Weil
4af49a8866 osd/PG: ignore CancelRecovery in NotRecovering 
It's possible to get >1 CancelRecovery events in the queue.
The first will transition us from Recovering to NotRecovering.
Currently the second will make us crash.

This is harmless; instead just swallow the event.

Fixes: http://tracker.ceph.com/issues/20804
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-07-27 16:59:44 -04:00
Patrick Donnelly
d7f5af40a2
qa: whitelist trim error during powercycle tests 
Fixes: http://tracker.ceph.com/issues/20566

Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
 2017-07-27 13:24:21 -07:00
Sage Weil
5e46c354cf Merge pull request #16635 from dzafman/wip-fix-test-pidfile 
test: test_pidfile running 2nd mon has unreliable log output

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-07-27 15:06:17 -05:00
Jason Dillaman
d61094f45e osd: silence coverity warning in async read operation contexts 
Coverity doesn't know that the context is deleted via the "complete"
method and the embedded context is therefore also destructed when
it's completed.

Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2017-07-27 15:18:24 -04:00
David Zafman
c76f306ff5 test: test_pidfile running 2nd mon has unreliable log output 
Signed-off-by: David Zafman <dzafman@redhat.com>
 2017-07-27 11:23:54 -07:00
Neha Ojha
f8ae463492 osd: add default_device_class to metadata 
Signed-off-by: Neha Ojha <nojha@redhat.com>
 2017-07-27 11:21:10 -07:00
Jason Dillaman
da62225448 osd: moved OpFinisher logic from OSDOp to OpContext 
This allows the memory lifetime of the OpFinisher to be tightly
controlled since the OpContext cannot be copied.

Fixes: http://tracker.ceph.com/issues/20783
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2017-07-27 14:12:17 -04:00
Gregory Farnum
ba03ab92a8 Merge pull request #16629 from johnwilkins/wip-doc-remove-contractions 
Remove contractions from the documentation.

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
 2017-07-27 10:49:38 -07:00
Sage Weil
541de391e1 Merge pull request #16572 from liewegas/wip-pidfile 
test: add separate ceph-helpers-based smoke test

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-07-27 12:32:36 -05:00
John Wilkins
3b9f70d4fd doc/cephfs: Removed contractions for ESL speakers. 
Signed-off-by: John Wilkins <jowilkin@redhat.com>
 2017-07-27 10:01:29 -07:00
John Wilkins
c978a76b4d doc/start: Removed contractions for ESL speakers. 
Signed-off-by: John Wilkins <jowilkin@redhat.com>
 2017-07-27 09:59:00 -07:00
Ilya Dryomov
bd6e3e5f1f qa/tasks/rbd_fio: bump default fio version to 2.21 
I'm seeing sporadic single thread deadlocks on fio stat_mutex during krbd
thrash runs:

  (gdb) info threads
    Id   Target Id         Frame
  * 1    Thread 0x7f89ee730740 (LWP 15604) 0x00007f89ed9f41bd in __lll_lock_wait () from /lib64/libpthread.so.0
  (gdb) bt
  #0  0x00007f89ed9f41bd in __lll_lock_wait () from /lib64/libpthread.so.0
  #1  0x00007f89ed9f17b2 in pthread_cond_wait@@GLIBC_2.3.2 () from /lib64/libpthread.so.0
  #2  0x00000000004429b9 in fio_mutex_down (mutex=0x7f89ee72d000) at mutex.c:170
  #3  0x0000000000459704 in thread_main (data=<optimized out>) at backend.c:1639
  #4  0x000000000045b013 in fork_main (offset=0, shmid=<optimized out>, sk_out=0x0) at backend.c:1778
  #5  run_threads (sk_out=sk_out@entry=0x0) at backend.c:2195
  #6  0x000000000045b47f in fio_backend (sk_out=sk_out@entry=0x0) at backend.c:2400
  #7  0x000000000040cb0c in main (argc=2, argv=0x7fffad3e3888, envp=<optimized out>) at fio.c:63
  (gdb) up 2
  170                     pthread_cond_wait(&mutex->cond, &mutex->lock);
  (gdb) p mutex.lock.__data.__owner
  $1 = 15604

Upgrading to 2.21 seems to make these go away.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
 2017-07-27 18:57:43 +02:00
John Wilkins
ff2eebf88a doc/man: Removed contractions for ESL speakers. 
Signed-off-by: John Wilkins <jowilkin@redhat.com>
 2017-07-27 09:57:23 -07:00
John Wilkins
096af64ae6 doc/install: Removed contractions for ESL speakers. 
Signed-off-by: John Wilkins <jowilkin@redhat.com>
 2017-07-27 09:55:58 -07:00
John Wilkins
60e6cf509c doc/rgw: Removed contractions for ESL speakers. 
Signed-off-by: John Wilkins <jowilkin@redhat.com>
 2017-07-27 09:54:37 -07:00
John Wilkins
112e9936b1 doc/rbd: Removed contractions for ESL speakers. 
Signed-off-by: John Wilkins <jowilkin@redhat.com>
 2017-07-27 09:52:56 -07:00
John Wilkins
6640837da3 doc/rados: Removed contractions to improve readabilty for ESL speakers. 
Signed-off-by: John Wilkins <jowilkin@redhat.com>
 2017-07-27 09:46:53 -07:00
Sage Weil
c1aef68f02 Merge pull request #16569 from liewegas/wip-set-not-put 
mon: 'config-key put' -> 'config-key set'

Reviewed-by: Joao Eduardo Luis <joao@suse.de>
 2017-07-27 11:34:37 -05:00
Sage Weil
e469a8044c qa/standalone/crush/crush-classes: fix test 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-07-27 12:25:25 -04:00
Sage Weil
380de3395f qa/standalone/README 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-07-27 12:24:52 -04:00
Sage Weil
52d1814caf test/smoke.sh: add simple ceph-helpers-based smoke test 
This is just enough during make check to know things aren't totally
broken.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-07-27 12:24:52 -04:00
Sage Weil
a98a2619b3 osdc/Objecter: unify disparate EAGAIN handling paths into one 
We had two different code paths for EAGAIN that both
seemed to resend the same request again (with a new
tid), but implemneted it in two different ways. Further,
the first one was conditioned on the BALANCE_READS
flag but not LOCALIZED_READS, which should (I think) be
equivalent in this context.

Unify them into a single path.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-07-27 12:13:39 -04:00
Sage Weil
0b5036f072 qa/suites/rados/upgrade: fix upgrade wait for healthy 
There is no mgr, so we can't call ceph.healthy.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-07-27 12:10:34 -04:00
Sage Weil
a40d94b163 qa/tasks/ceph: wait for pg stats to flush in healthy check 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-07-27 12:10:27 -04:00
Sage Weil
80978dea8a qa/tasks/ceph_manager: wait_for_all_up -> wait_for_all_osds_up 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-07-27 12:10:26 -04:00
Sage Weil
7648894e55 qa/tasks/ceph_manager: expose flush_all_pg_stats 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-07-27 12:10:26 -04:00
Sage Weil
c7430c56cd Merge pull request #16388 from xiexingguo/wip-class-misc-fixes 
crush, mon: simplify device class manipulation commands

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-07-27 11:04:33 -05:00
Josh Durgin
c1a4877da1 Merge pull request #16172 from ivancich/wip-dup-ops 
PGLog: store extra duplicate ops beyond the normal log entries

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-07-27 08:57:39 -07:00
Yuri Weinstein
6942e3932b Merge pull request #16558 from hjwsm1989/fix-recovering-hang-with-unfound-objects 
osd/PrimaryLogPG: fix recovering hang when have unfound objects

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-07-27 08:37:15 -07:00
Yuri Weinstein
2eaa086c19 Merge pull request #16561 from Yan-waller/wip-walle-0725osddumpclinfo 
osd: add dump filter for tracked ops

Reviewed-by: Gregory Farnum <gfarnum@redhat.com>
 2017-07-27 08:36:23 -07:00
J. Eric Ivancich
a3d2c6b6a0 PGLog: continuation, store extra duplicate ops beyond the normal log entries 
This helps us avoid replaying non-idempotent client operations when
the pg log is very short, e.g. in an effort to force OSDs to use
backfill rather than regular recovery. This can be advantageous to
avoid blocking i/o to objects, at the cost of longer total time to
become clean (since backfill requires scanning the objects to see what
is missing).

Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
 2017-07-27 11:09:04 -04:00
Yuri Weinstein
105435a38e Merge pull request #16384 from mikulely/2-checkout-placmenet-target-existness 
rgw: check placement target existence during bucket creation

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2017-07-27 07:29:13 -07:00
Yuri Weinstein
2357dcd23c Merge pull request #16389 from prallabh/wip-20661 
rgw: Do not decrement stats cache when the cache values are zero

Reviewed-by: Orit Wasserman <owasserm@redhat.com>
 2017-07-27 07:27:37 -07:00
Yuri Weinstein
63a5f60b07 Merge pull request #16463 from cbodley/wip-20708 
rgw: fix parse/eval of policy conditions with IfExists

Reviewed-by: Adam C. Emerson <aemerson@redhat.com>
 2017-07-27 07:25:50 -07:00
Yuri Weinstein
8ff76b7033 Merge pull request #16495 from weiqiaomiao/wip_weiqm_rgw_crash 
rgw: fix radosgw will crash when service is restarted during lifecycl…

Reviewed-by: Casey Bodley <cbodley@redhat.com>
Reviewed-by: Daniel Gryniewicz <dang@redhat.com>
 2017-07-27 07:22:59 -07:00
Yuri Weinstein
5fc9dfa36f Merge pull request #16531 from rzarzynski/wip-rgw-20757 
rgw: fix memory leaks during Swift Static Website's error handling.

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2017-07-27 07:19:22 -07:00
Yuri Weinstein
b59e577334 Merge pull request #16601 from rzarzynski/wip-rgw-20774 
rgw: never let http_redirect_code of RGWRedirectInfo to stay uninitialized

Reviewed-by: Matt Benjamin <mbenjami@redhat.com>
 2017-07-27 07:18:42 -07:00