Commit Graph

40537 Commits

Author SHA1 Message Date
Gregory Farnum
ba12448c80 Merge pull request #4211 from ceph/wip-11120
osdc/Striper.cc fix stripe_count == 1 && stripe_unit != object_size

Reviewed-by: John Spray <jspray@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
2015-03-31 09:26:04 -07:00
Kefu Chai
508ee9bb95 Merge pull request #4225 from Fale/patch-1
doc: fix the architecture diagram in cephfs.rst

Reviewed-by: Kefu Chai <kchai@redhat.com>
2015-04-01 00:05:51 +08:00
Fabio Alessandro Locati
d5d6468e88 doc: fix the architecture diagram in cephfs.rst
Signed-off-by: Fabio Alessandro Locati <fabio@locati.cc>
2015-03-31 18:00:45 +02:00
John Spray
9b171d23eb Merge pull request #4215 from ceph/wip-11258
Wip 11258

Reviewed-by: John Spray <john.spray@redhat.com>
2015-03-31 14:23:19 +01:00
Sage Weil
497737aabf Merge remote-tracking branch 'gh/hammer'
Conflicts:
	src/gmock
	src/osd/ReplicatedPG.cc
2015-03-30 15:41:13 -07:00
Sage Weil
c7de236d2f os/KeyValueDB: skip experimental check for test_init
We don't want to spit out the warning twice, and we don't have cct
anyway.

Also test_init is annoying; we should try to kill it.

Signed-off-by: Sage Weil <sage@redhat.com>
2015-03-30 15:14:15 -07:00
Sage Weil
2e908f1e87 Merge pull request #3878 from ceph/wip-dirty-pg-keys
osd: coalesce into single omap_setkeys for normal writes

Tested-by: Andreas Bluemle <andreas.bluemle@itxperts.de>
Reviewed-by: David Zafman <dzafman@redhat.com>
2015-03-30 11:18:56 -07:00
Loic Dachary
b28a42ce32 Merge pull request #4212 from zhouyuan/isal_2.13
erasure-code: Update ISA-L to 2.13

Reviewed-by: Loic Dachary <ldachary@redhat.com>
2015-03-30 20:17:38 +02:00
Sage Weil
a05871a185 Merge pull request #4160 from ceph/wip-rocksdb
update rocksdb
2015-03-30 10:57:07 -07:00
Sage Weil
a4c01f38f1 mark kinetic experimental
Signed-off-by: Sage Weil <sage@redhat.com>
2015-03-30 10:00:01 -07:00
Sage Weil
002b7fdadf mark rocksdb experimental
Signed-off-by: Sage Weil <sage@redhat.com>
2015-03-30 10:00:01 -07:00
Loic Dachary
6f4936ee96 Merge pull request #4131 from t-miyamae/wip-mshec-documentation-h2
erasure code: add shec's documentation / change default layout

Reviewed-by: Loic Dachary <ldachary@redhat.com>
2015-03-30 14:37:08 +02:00
Yan, Zheng
ccdeaf87df mds: fix out-of-order messages
When MDS is no longer laggy, it should process deferred messages
first, then process newly received messages.

Fix: #11258
Signed-off-by: Yan, Zheng <zyan@redhat.com>
2015-03-30 17:49:06 +08:00
Kefu Chai
f47a572424 Merge pull request #4183 from stiopaa1/OSDMonTrailingSpaces
mon/OSDMonitor: remove trailing whitespaces

Reviewed-by: Kefu Chai <kchai@redhat.com>
2015-03-30 16:43:37 +08:00
Yuan Zhou
59aa6700fa erasure-code: Update ISA-L to 2.13
ISA-L 2.13 brings better performance on Avoton (20%). There's no impact on Xeon
platform. The details are in the release notes.

There's a new API ec_encode_data_update() for incremental encoding
and decoding. The other highlevel API keeps the same as in 2.10

Signed-off-by: Yuan Zhou <yuan.zhou@intel.com>
2015-03-30 13:39:31 +08:00
Yan, Zheng
ad15f7d795 osdc/Striper.cc fix stripe_count == 1 && stripe_unit != object_size
Fixes:11120
Signed-off-by: Yan, Zheng <zyan@redhat.com>
2015-03-30 11:30:35 +08:00
Gregory Farnum
493eff569e Merge pull request #4209 from ceph/wip-java
fix rhel linking error

Backport: giant, firefly, dumpling

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
2015-03-28 11:02:52 -07:00
Noah Watkins
aed3434dc7 java: libcephfs_jni.so is in /usr/lib64 on rhel
Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
2015-03-27 19:34:12 -07:00
Noah Watkins
f5a95dc700 java: dump extra info for ftruncate assertion
Nightly ran and encountered a situation in which fstat following
ftruncate reported a size not equal to the truncated size.

Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
2015-03-27 19:09:15 -07:00
Gregory Farnum
71a0c793ab Merge pull request #4203 from Vicente-Cheng/fixed-get-mdsmap-assertion
mds: fixed the ceph get mdsmap assertion.

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
2015-03-27 11:35:30 -07:00
Gregory Farnum
c50f5b1e26 Merge pull request #4173 from ceph/wip-mds-kill-session
Wip mds kill session

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: John Spray <jspray@redhat.com>
2015-03-27 11:29:19 -07:00
Gregory Farnum
7721b224c4 Merge pull request #4168 from ceph/wip-11226-dir-fx
RFC client: Hold on to exclusive caps on directories we "own"

Reviewed-by: Sage Weil <sage@redhat.com>
2015-03-27 11:28:31 -07:00
Gregory Farnum
0e4a75b2e3 Merge pull request #4177 from ceph/wip-11226-extra
Wip 11226 extra

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
2015-03-27 11:27:58 -07:00
Gregory Farnum
413da564d4 Merge pull request #4189 from ceph/wip-11236
test_libcephfs: do cleanup in ReleaseMounted test

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
2015-03-27 11:26:21 -07:00
Gregory Farnum
bd1d11f6eb Merge pull request #4192 from ceph/wip-11218
#11218: Multi-MDS fixes for 'damaged' ranks

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
2015-03-27 11:24:50 -07:00
Josh Durgin
015c643735 Merge pull request #4199 from ceph/wip-11250
cls_rbd: fix read past end of bufferlist c_str() in debug log msg

Reviewed-by: Haomai Wang <haomaiwang@gmail.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2015-03-27 08:51:19 -07:00
Sage Weil
59143d141c Merge pull request #4194 from athanatos/wip-11199
ReplicatedPG: trim backfill intervals based on peer's last_backfill_star...

Reviewed-by: Sage Weil <sage@redhat.com>
2015-03-27 08:15:29 -07:00
Sage Weil
efb66b9120 Merge pull request #4195 from athanatos/wip-11197
PG: set/clear CREATING in Primary state entry/exit

Reviewed-by: Sage Weil <sage@redhat.com>
2015-03-27 08:10:20 -07:00
John Spray
f3f37a3293 Merge pull request #4200 from ceph/wip-mds-remove-inode
mds: properly remove inode after purging stray

Reviewed-by: John Spray <john.spray@redhat.com>
2015-03-27 11:33:07 +00:00
Vicente Cheng
f4398d2e6c Fixed the ceph get mdsmap assertion.
When we want to get mdsmap, we try to get_version()
    and the return value err = 0 means success.

    The assert verified r == 0. r would not change in this flow.
    It always meet assert and lead mon failure.

    I think this verify should be:
        assert(err == 0)
    It will help to check return value of get_version().

If you have any questions, feel free to let me know.
Thanks!

Signed-off-by: Vicente Cheng <freeze.bilsted@gmail.com>
2015-03-27 18:49:28 +08:00
Kefu Chai
d3029fe72a Merge pull request #4193 from larkly/patch-docerror-erasure
doc: Incomplete example in erasure-coded-pool.rst

Reviewed-by: Kefu Chai <kchai@redhat.com>
2015-03-27 18:31:16 +08:00
Yan, Zheng
d789f44074 mds: properly remove inode after purging stray
Signed-off-by: Yan, Zheng <zyan@redhat.com>
2015-03-27 15:10:53 +08:00
Sage Weil
ea32960f58 cls_rbd: fix read past end of bufferlist c_str() in debug log msg
Fixes: #11250
Signed-off-by: Sage Weil <sage@redhat.com>
2015-03-26 21:00:00 -07:00
Kefu Chai
3489fbdc92 Merge pull request #4196 from athanatos/wip-move-code
osd: Wip move code

Reviewed-by: Kefu Chai <kchai@redhat.com>
2015-03-27 10:24:22 +08:00
Sage Weil
877d5d8820 Merge pull request #4171 from majianpeng/cleanup
common: print hexadecimal for ghobject_t.generation.

Reviewed-by: Sage Weil <sage@redhat.com>
2015-03-26 17:45:20 -07:00
Bosse Klykken
d6acc6a581 Doc: Incomplete example in erasure-coded-pool.rst
Signed-off-by: Bosse Klykken <larkly@gmail.com>
2015-03-26 21:31:16 +01:00
Sage Weil
90c38b5b97 rocksdb: fix 32-bit build
Signed-off-by: Sage Weil <sage@redhat.com>
2015-03-26 11:04:18 -07:00
Sage Weil
ddad2d4465 Makefile-rocksdb.am: update for latest rocks
Lots of files changed here; rebuilt the list from scratch.

Signed-off-by: Sage Weil <sage@redhat.com>
2015-03-26 11:01:35 -07:00
Samuel Just
c176ebf791 osd/: Move ReplicatedBackend methods into ReplicatedBackend.cc
Signed-off-by: Samuel Just <sjust@redhat.com>
2015-03-26 10:50:19 -07:00
Samuel Just
e9d6096f25 ReplicatedPG: remove unused C_OnPushCommit
Signed-off-by: Samuel Just <sjust@redhat.com>
2015-03-26 10:44:00 -07:00
Josh Durgin
887354099e Merge pull request #4113 from wonzhq/rbd-fix
rbd: misc fixes

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2015-03-26 10:06:37 -07:00
John Spray
6413209ef3 mds: include damaged in MDSMap::dump
Signed-off-by: John Spray <john.spray@redhat.com>
2015-03-26 15:48:55 +00:00
John Spray
3b2a0917e8 mds: update peer failure response to account for damaged
...by calling get_down_mds_set instead of get_failed_mds_set.

Also remove a redundant if(true) around this region.

Signed-off-by: John Spray <john.spray@redhat.com>
2015-03-26 13:11:44 +00:00
John Spray
f311bb77e3 mds: add get_down_mds_set method
For places where we would like to treat failed
and damaged MDS ranks the same, like detecting
when someone has dropped offline.

Signed-off-by: John Spray <john.spray@redhat.com>
2015-03-26 13:11:44 +00:00
John Spray
7eccf920ba mds: account for 'damaged' in MDSMap::is_degraded
Fixes: #11218
Signed-off-by: John Spray <john.spray@redhat.com>
2015-03-26 13:11:44 +00:00
John Spray
aae265bfe1 mds: clarify MDBalancer::send_heartbeat
The initial is_degraded() check guarantees that
the 'in' set is equal to the 'up' set.  Later,
this calls get_mds_set and assigns it to a variable
called 'up'.

It's clearer to use get_up_mds_set into the variable
called up (this was confusing when debugging #11218
which was itself a result of is_degraded() ignoring
damaged ranks).

Signed-off-by: John Spray <john.spray@redhat.com>
2015-03-26 12:54:53 +00:00
Yan, Zheng
c7d5c02680 test_libcephfs: do cleanup in ReleaseMounted test
Fixes: #11236
Signed-off-by: Yan, Zheng <zyan@redhat.com>
2015-03-26 15:21:52 +08:00
Loic Dachary
9008a3391d Merge pull request #4188 from XinzeChi/wip-test-1
test: add compile-command for test_ceph_daemon.py

Reviewed-by: Loic Dachary <ldachary@redhat.com>
2015-03-26 07:45:05 +01:00
Xinze Chi
9418e432ad test: add compile-command for test_ceph_daemon.py
Signed-off-by: Xinze Chi <xmdxcxz@gmail.com>
2015-03-26 13:58:33 +08:00
Jianpeng Ma
aa6a46cfd9 common: print hexadecimal for ghobject_t.generation & shard_id
In filestore, it use hexadecimal for ghobject_t.generation &
shard_id. Make the same.

Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
2015-03-26 13:51:02 +08:00