]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
Alfredo Deza [Mon, 23 Oct 2017 13:44:27 +0000 (09:44 -0400)]
ceph-volume lvm.activate only prime-osd-dir when directory is empty
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Mon, 23 Oct 2017 13:20:26 +0000 (09:20 -0400)]
ceph-volume lvm.activate safeguard against auto detect objectstore flag not being set
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 19:18:20 +0000 (15:18 -0400)]
ceph-volume util.system use strings for comparison in py3
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 19:10:08 +0000 (15:10 -0400)]
f ceph-volume tests update changes from the help menu in lvm
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 18:12:02 +0000 (14:12 -0400)]
ceph-volume lvm.common --journal-size doesn't accept a volume group
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 18:04:31 +0000 (14:04 -0400)]
ceph-volume lvm.prepare filestore does not require a volume group
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 18:04:05 +0000 (14:04 -0400)]
ceph-volume lvm.common volume groups are no longer required
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 16:07:06 +0000 (12:07 -0400)]
doc/ceph-volume activate workflow mention tmpfs in osd dirs
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 16:02:10 +0000 (12:02 -0400)]
doc/ceph-volume update activation to include bluestore support
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 15:58:47 +0000 (11:58 -0400)]
doc/ceph-volume update create to indicate bluestore support
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 15:51:55 +0000 (11:51 -0400)]
doc/ceph-volume update prepare with bluestore workflow
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 14:15:09 +0000 (10:15 -0400)]
doc/ceph-volume update filestore to indicate it is not the only/default objectstore
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 14:00:17 +0000 (10:00 -0400)]
doc/ceph-volume elaborate on env vars for interval and tries in activation
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 13:33:55 +0000 (09:33 -0400)]
ceph-volume lvm.common update cli flags help for bluestore support
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 13:23:35 +0000 (09:23 -0400)]
ceph-volume util.disk st_mode is needed for stat()
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 13:23:02 +0000 (09:23 -0400)]
ceph-volume decorators always log to the file with exceptions
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 12:49:32 +0000 (08:49 -0400)]
ceph-volume tests verify behavior of get_lv_from_argument
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 12:48:01 +0000 (08:48 -0400)]
ceph-volume api.lvm return result of get_lv when using arguments
If the argument is an absolute path it is fine to just return whatever
get_lv finds since it is a "safe" call, it will return a None if nothing
is found
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 12:12:01 +0000 (08:12 -0400)]
ceph-volume lvm.listing support bluestore, not only filestore
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 12:10:51 +0000 (08:10 -0400)]
ceph-volume api.lvm allow full paths to detect lv from arguments
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 20 Oct 2017 12:10:26 +0000 (08:10 -0400)]
ceph-volume tests add support for bluestore list verification
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Thu, 19 Oct 2017 17:20:55 +0000 (13:20 -0400)]
ceph-volume tests activate with fsid works for bluestore and filestore
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Thu, 19 Oct 2017 17:14:05 +0000 (13:14 -0400)]
ceph-volume tests arg validator can accept absolute paths
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Thu, 19 Oct 2017 16:03:17 +0000 (12:03 -0400)]
ceph-volume tests update changes from the help menu in lvm
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Thu, 19 Oct 2017 15:46:57 +0000 (11:46 -0400)]
ceph-volume tests update to get_lv from get_journal_lv
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Thu, 19 Oct 2017 15:30:29 +0000 (11:30 -0400)]
ceph-volume tests.util new path/device mount interface
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Thu, 19 Oct 2017 13:49:25 +0000 (09:49 -0400)]
ceph-volume tests update api.lvm tests
The create_lv signature changed to require full size description and
tags need to be an actual dictionary (vs. keyword args)
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Wed, 18 Oct 2017 20:06:55 +0000 (16:06 -0400)]
ceph-volume lvm.activate ceph-bluestore-tool should populate the osd dir
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Wed, 18 Oct 2017 19:06:01 +0000 (15:06 -0400)]
ceph-volume lvm.activate auto detect objectstore type
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Wed, 18 Oct 2017 19:00:19 +0000 (15:00 -0400)]
ceph-volume lvm.trigger enable objectstore auto detection for activate
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Wed, 18 Oct 2017 16:00:34 +0000 (12:00 -0400)]
ceph-volume lvm.activate add bluestore support for activation
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Wed, 18 Oct 2017 15:40:38 +0000 (11:40 -0400)]
ceph-volume util.system create mappings of mounts
This makes it easier for consumers to detect a path, or a device that
might be mounted or might have more than one mount, including tmpfs and
devtmpfs support, which was just not possible before.
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Mon, 16 Oct 2017 10:51:05 +0000 (06:51 -0400)]
ceph-volume util.prepare separate filestore vs. bluestore prepare utils
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Mon, 16 Oct 2017 10:50:27 +0000 (06:50 -0400)]
ceph-volume process allow obfuscating a key or index when logging commands
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Fri, 13 Oct 2017 13:22:53 +0000 (09:22 -0400)]
ceph-volume util.prepare add other ln helpers for bluestore
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Thu, 12 Oct 2017 20:08:52 +0000 (16:08 -0400)]
ceph-volume util.arg_validators allow to pass a group as --data for lvm
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Thu, 12 Oct 2017 20:08:16 +0000 (16:08 -0400)]
ceph-volume util.disk add utilities for is_device and is_partition
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Thu, 12 Oct 2017 20:05:22 +0000 (16:05 -0400)]
ceph-volume api.lvm udpate create_lv for bluestore
Require full size notation for LVM (e.g. 50G or 100M) and do not
"translate" tags by pre-fixing them with 'ceph'. That is already how the
rest of the API works, no need to make that translation in one place
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Thu, 12 Oct 2017 19:42:22 +0000 (15:42 -0400)]
ceph-volume lvm.prepare update filestore workflow to use new helpers
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Thu, 12 Oct 2017 18:19:07 +0000 (14:19 -0400)]
ceph-volume lvm.prepare initial take on bluestore support
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Thu, 12 Oct 2017 18:16:25 +0000 (14:16 -0400)]
ceph-volume lvm.common update help flags for bluestore usage
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Wed, 11 Oct 2017 18:30:41 +0000 (14:30 -0400)]
ceph-volume api.lvm allow to create a vg
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Tue, 10 Oct 2017 16:30:06 +0000 (12:30 -0400)]
ceph-volume lvm add block CLI flags for bluestore
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Alfredo Deza [Tue, 10 Oct 2017 16:15:14 +0000 (12:15 -0400)]
ceph-volume lvm make bluestore the default option
Signed-off-by: Alfredo Deza <adeza@redhat.com>
Sage Weil [Wed, 18 Oct 2017 13:51:39 +0000 (08:51 -0500)]
Merge pull request #18376 from tchaikov/wip-authors
doc: update Component Technical Leads and maintainers to canonical location
Reviewed-by: Sage Weil <sage@redhat.com>
Casey Bodley [Wed, 18 Oct 2017 12:18:12 +0000 (08:18 -0400)]
Merge pull request #18355 from gaosibei/wip-rgw-refrence
RGW: change function parameters from value to refrence
Reviewed-by: Radoslaw Zarzynski <rzarzyns@redhat.com>
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Matt Benjamin [Wed, 18 Oct 2017 11:57:20 +0000 (07:57 -0400)]
Merge pull request #17432 from joscollin/wip-cleanup-fix-rgwconf
rgw: Access RGWConf through RGWEnv
Matt Benjamin [Wed, 18 Oct 2017 11:52:57 +0000 (07:52 -0400)]
Merge pull request #17440 from mikulely/cleanup-iterate
rgw: update outdated debug func name
Matt Benjamin [Wed, 18 Oct 2017 11:52:39 +0000 (07:52 -0400)]
Merge pull request #17956 from zhangsw/fix-rgw-encry-torrent-bug
rgw: Torrents are not supported for objects encrypted using SSE-C
Matt Benjamin [Wed, 18 Oct 2017 11:52:19 +0000 (07:52 -0400)]
Merge pull request #18057 from baixueyu/branch1
rgw: fix radosgw-admin quota enable return value bug
Alfredo Deza [Wed, 18 Oct 2017 10:51:27 +0000 (06:51 -0400)]
Merge pull request #18375 from tchaikov/wip-ceph-disk-check-log
ceph-disk: write log to /var/log/ceph not to /var/run/ceph
Reviewed-by: Alfredo Deza <adeza@redhat.com>
scuttlemonkey [Fri, 10 Mar 2017 19:41:20 +0000 (14:41 -0500)]
AUTHORS: Update Component Technical Leads and maintainers to canonical location of ceph.com.
Signed-off-by: Patrick McGarry <pmcgarry@redhat.com>
Mykola Golub [Wed, 18 Oct 2017 10:36:47 +0000 (13:36 +0300)]
Merge pull request #18315 from dillaman/wip-21797
librbd: object map batch update might cause OSD suicide timeout
Reviewed-by: Mykola Golub <to.my.trociny@gmail.com>
Kefu Chai [Wed, 18 Oct 2017 10:34:57 +0000 (18:34 +0800)]
Merge pull request #18345 from wido/doc-osd-replace
doc: Remove additional arguments when replacing OSD
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Wed, 18 Oct 2017 10:03:31 +0000 (18:03 +0800)]
ceph-disk: write log to /var/log/ceph not to /var/run/ceph
Signed-off-by: Kefu Chai <kchai@redhat.com>
Xie Xingguo [Wed, 18 Oct 2017 08:15:35 +0000 (16:15 +0800)]
Merge pull request #18373 from tchaikov/wip-opt-desc
doc: fix the desc of "osd max pg per osd hard ratio"
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
Kefu Chai [Wed, 18 Oct 2017 08:07:50 +0000 (16:07 +0800)]
doc: fix the desc of "osd max pg per osd hard ratio"
Signed-off-by: Kefu Chai <kchai@redhat.com>
Jos Collin [Wed, 18 Oct 2017 05:34:45 +0000 (05:34 +0000)]
Merge pull request #18370 from mikulely/cleanup-rgw-write-meta
rgw: drop outdated function doc
Reviewed-by: Jos Collin <jcollin@redhat.com>
Jiaying Ren [Wed, 18 Oct 2017 04:32:24 +0000 (12:32 +0800)]
rgw: drop misplaced&outdated func doc
Signed-off-by: Jiaying Ren <jiaying.ren@umcloud.com>
Kefu Chai [Wed, 18 Oct 2017 02:52:13 +0000 (10:52 +0800)]
Merge pull request #18352 from rzarzynski/wip-testfio-fix-pgps
Revert "bluestore/fio: Fixed problem with all objects having the same hash
Reviewed-by: Adam Kupczyk <akupczyk@redhat.com>
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com>
Kefu Chai [Wed, 18 Oct 2017 02:48:32 +0000 (10:48 +0800)]
Merge pull request #18338 from xiexingguo/wip-pg
osd/PrimaryLogPG: do not use approx_size() for log trimming
Reviewed-by: Sage Weil <sage@redhat.com>
Kefu Chai [Wed, 18 Oct 2017 02:47:37 +0000 (10:47 +0800)]
Merge pull request #18340 from Yan-waller/wip-walle-1014osdprimarypg
osd/PG: misc cleanups
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Wed, 18 Oct 2017 02:46:50 +0000 (10:46 +0800)]
Merge pull request #18351 from tchaikov/wip-osx
common/event_socket.h: include <errno.h> to use errno
Reviewed-by: Haomai Wang <haomai@xsky.com>
Kefu Chai [Wed, 18 Oct 2017 02:46:18 +0000 (10:46 +0800)]
Merge pull request #18353 from xiexingguo/wip-do-read
osd/PrimaryLogPG: trigger auto-repair on full-object-size CRC error
Reviewed-by: Sage Weil <sage@redhat.com>
Kefu Chai [Wed, 18 Oct 2017 02:45:48 +0000 (10:45 +0800)]
Merge pull request #18321 from majianpeng/msg-async-cleanup
msg/async: batch handle numevents.
Reviewed-by: Haomai Wang <haomai@xsky.com>
Kefu Chai [Wed, 18 Oct 2017 02:44:16 +0000 (10:44 +0800)]
Merge pull request #18358 from tchaikov/wip-max-pg-per-osd
osd,mon: add max-pg-per-osd limit
Reviewed-by: Sage Weil <sage@redhat.com>
Kefu Chai [Wed, 18 Oct 2017 02:43:22 +0000 (10:43 +0800)]
Merge pull request #18289 from smithfarm/wip-21762
build/ops: rpm: move ceph-*-tool binaries out of ceph-test subpackage
Reviewed-By: Kefu Chai <kchai@redhat.com>
Reviewed-by: Ken Dreyer <kdreyer@redhat.com>
gaosibei [Tue, 17 Oct 2017 13:22:40 +0000 (21:22 +0800)]
RGW: change function parameters from value to refrence
Signed-off-by: Sibei Gao <gaosb@inspur.com>
Matt Benjamin [Tue, 17 Oct 2017 16:42:10 +0000 (12:42 -0400)]
Merge pull request #18184 from oritwas/wip-rgw-21725
rgw: disable dynamic resharding in multisite environment
Kefu Chai [Tue, 17 Oct 2017 16:24:39 +0000 (00:24 +0800)]
Merge pull request #16745 from Liuchang0812/object-store-repair
common, tool: update kvstore-tool to repair key/value database
Reviewed-by: Kefu Chai <kchai@redhat.com>
Patrick Donnelly [Tue, 17 Oct 2017 15:12:46 +0000 (08:12 -0700)]
Merge PR #18281 into master
* refs/pull/18281/head:
Fixed the readme examples
ptl-tool: Drop Default Labelling of PRs
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
Kefu Chai [Tue, 17 Oct 2017 04:17:09 +0000 (12:17 +0800)]
mon: change "mon_pg_warn_min_per_osd" to uint64_t
* this silences a warning from -Wsign-compare.
* also switch all its user to the new-style option
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Tue, 17 Oct 2017 04:10:55 +0000 (12:10 +0800)]
osd,mon: change "mon_max_pg_per_osd" to uint64_t
as it should never be a negative number. if this option is disabled,
it's 0.
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Tue, 26 Sep 2017 07:54:14 +0000 (15:54 +0800)]
osd: add max-pg-per-osd limit
osd will refused to create new pgs, until its pg number is lower
than the max-pg-per-osd upper bound setting.
Signed-off-by: Kefu Chai <kchai@redhat.com>
Casey Bodley [Tue, 17 Oct 2017 15:06:53 +0000 (11:06 -0400)]
Merge pull request #18331 from Yan-waller/wip-walle-1008vstartrgw
vstart.sh: move rgw configuration to client.rgw section
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Jos Collin [Tue, 17 Oct 2017 06:08:49 +0000 (11:38 +0530)]
Fixed the readme examples
Fixed the readme examples, according to the new --label definition.
Signed-off-by: Jos Collin <jcollin@redhat.com>
Jos Collin [Fri, 13 Oct 2017 02:46:08 +0000 (08:16 +0530)]
ptl-tool: Drop Default Labelling of PRs
Dropped default labelling of PRs. Allowed --label '', which won't label the PR. The user can omit --label too, if the PR should not be labelled.
Signed-off-by: Jos Collin <jcollin@redhat.com>
Jos Collin [Tue, 17 Oct 2017 14:09:14 +0000 (14:09 +0000)]
Merge pull request #18231 from batrick/ptl-tool-labeled-prs
ptl-tool: load labeled PRs
Reviewed-by: Jos Collin <jcollin@redhat.com>
xie xingguo [Tue, 17 Oct 2017 12:23:05 +0000 (20:23 +0800)]
osd/PrimaryLogPG: trigger auto-repair on full-object-size CRC error
There are still FileStore users and the full-object CRC might be able
to catch silently returned data errors. Since we support auto-repair now,
let's trigger an auto-repair process instead.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
Kefu Chai [Tue, 17 Oct 2017 12:11:38 +0000 (20:11 +0800)]
common/lockdep: do not set std::string using braces
this silences follow warning from clang:
ceph/src/common/lockdep.cc:219:12: warning: braces around scalar initializer [-Wbraced-scalar-init]
name = { "unknown" };
^~~~~~~~~~~~~
1 warning generated.
Signed-off-by: Kefu Chai <kchai@redhat.com>
Radoslaw Zarzynski [Tue, 17 Oct 2017 11:09:02 +0000 (13:09 +0200)]
Revert "bluestore/fio: Fixed problem with all objects having the same hash"
This reverts commit
0eb5359273df2c92fa525683f88586878f57bb4b .
Signed-off-by: Radoslaw Zarzynski <rzarzyns@redhat.com>
Kefu Chai [Tue, 17 Oct 2017 11:57:36 +0000 (19:57 +0800)]
common/event_socket.h: include <errno.h> to use errno
OSX needs this also.
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Tue, 17 Oct 2017 11:51:51 +0000 (19:51 +0800)]
Merge pull request #18348 from Yan-waller/wip-walle-1017readmecmake
README.md: bump up cmake to 2.8.12
Reviewed-by: Kefu Chai <kchai@redhat.com>
Yan Jun [Tue, 17 Oct 2017 08:35:44 +0000 (16:35 +0800)]
README.md: bump up cmake to 2.8.12
Signed-off-by: Yan Jun <yan.jun8@zte.com.cn>
Jos Collin [Sat, 2 Sep 2017 05:59:01 +0000 (11:29 +0530)]
rgw: Access RGWConf through RGWEnv
Created functions rgw_conf_get_enable_ops_log(), rgw_conf_get_enable_usage_log() and
rgw_conf_get_defer_to_bucket_acls() and the necessary changes to provide the access of RGWConf through RGWEnv.
Signed-off-by: Jos Collin <jcollin@redhat.com>
Wido den Hollander [Tue, 17 Oct 2017 09:01:27 +0000 (11:01 +0200)]
doc: Remove additional arguments when replacing OSD
It's not required to provide the --bluestore nor --osd-uuid option
to ceph-disk.
Using BlueStore is the default on master (e.g. Luminous) and thus
this option is not required.
When no OSD UUID is supplied ceph-disk will generate one, so we do
not need to supply one generated by uuidgen.
Signed-off-by: Wido den Hollander <wido@42on.com>
xie xingguo [Tue, 17 Oct 2017 01:55:57 +0000 (09:55 +0800)]
osd/PrimaryLogPG: do not use approx_size() for log trimming
There might be holes on log versions, thus the approx_size()
should (almost) always overestimate the actual number of log entries.
As a result, we might be at the risk of accessing violation
while searching for the oldest log entry to keep in the log list later.
Fix the above problem by counting the precise number of current
log entries instead.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
Yan Jun [Tue, 17 Oct 2017 06:47:47 +0000 (14:47 +0800)]
common/config: drop unused configuration item 'osd_backoff_on_down'
drop it for no more use.
Signed-off-by: Yan Jun <yan.jun8@zte.com.cn>
Jiaying Ren [Mon, 4 Sep 2017 07:17:42 +0000 (15:17 +0800)]
rgw: update outdated debug func name
Signed-off-by: Jiaying Ren <jiaying.ren@umcloud.com>
Kefu Chai [Tue, 17 Oct 2017 05:07:19 +0000 (13:07 +0800)]
Merge pull request #18081 from zhsj/revert-15089-add-mirror
doc: change cn mirror to ustc domain
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Tue, 17 Oct 2017 05:03:20 +0000 (13:03 +0800)]
Merge pull request #18312 from shinobu-x/sk-buffer_20171015
common/buffer: cleanups
Reviewed-by: Sage Weil <sage@redhat.com>
Kefu Chai [Tue, 17 Oct 2017 05:02:35 +0000 (13:02 +0800)]
Merge pull request #18318 from Linbing/wip-bluestore-compression
bluestore: comp_min_blob_size init error
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
Kefu Chai [Tue, 17 Oct 2017 05:01:30 +0000 (13:01 +0800)]
Merge pull request #18279 from lixiaoy1/rmrange
os/bluestore: use db->rm_range_keys to delete range of keys
Reviewed-by: Varada Kari <varada.kari@sandisk.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
lisali [Fri, 13 Oct 2017 09:51:39 +0000 (05:51 -0400)]
os/bluestore: use db->rm_range_keys to delete range of keys
As Key Value DB provides the rm_range_keys interface to remove
some range of keys, BlueStore should use the interface. DB can
provide more efficient ways.
Signed-off-by: Xiaoyan Li <xiaoyan.li@intel.com>
Kefu Chai [Tue, 17 Oct 2017 04:59:35 +0000 (12:59 +0800)]
Merge pull request #18320 from shinobu-x/sk-include_unordered_x
include: Remove unused header, ciso646
Reviewed-by: Jos Collin <jcollin@redhat.com>
Reviewed-by: Willem Jan Withagen <wjw@digiware.nl>
Kefu Chai [Tue, 17 Oct 2017 04:59:05 +0000 (12:59 +0800)]
Merge pull request #18319 from shinobu-x/sk-osd_20171016
osd: Don't include same header twice
Reviewed-by: Jos Collin <jcollin@redhat.com>
Patrick Donnelly [Tue, 10 Oct 2017 23:18:10 +0000 (16:18 -0700)]
ptl-tool: load labeled PRs
This lets you label in GitHub the PRs you want to test/merge.
Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
Kefu Chai [Sun, 15 Oct 2017 12:46:28 +0000 (20:46 +0800)]
qa/tasks/ceph: add "create_rbd_pool" option
True by default, but we can opt not to create the "rbd" pool.
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Tue, 26 Sep 2017 07:50:08 +0000 (15:50 +0800)]
mon/OSDMonitor: bypass checks if pg_temp.forced
originally, monitor ignores the pg_temp messages sent from replica osds,
but to re-trigger peering if replica osd's pg number drops down below
the setting, we need to bypass the checks.
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Tue, 26 Sep 2017 07:49:11 +0000 (15:49 +0800)]
messages/MOSDPGTemp: add `forced` field
the monitor is supposed to bypass some checks if `forced` is true.
Signed-off-by: Kefu Chai <kchai@redhat.com>