librbd: reduce log level for image format 1 warning

Signed-off-by: Jason Dillaman <dillaman@redhat.com>

Merge pull request #8768 from cbodley/wip-rgw-admin-zonegroup

radosgw-admin: add missing --zonegroup-id to usage

Merge pull request #8300 from jcsp/wip-standby-replay-reorg

mds: Fix standby replay MDS in upgrades and simplify standby replay logic (#15591)

Reviewed-by: Greg Farnum <gfarnum@redhat.com>

Merge pull request #8550 from xiexingguo/xxg-wip-cls

objclass: honour do_osd_ops() results before going any further

Reviewed-by: Sage Weil <sage@redhat.com>

Merge pull request #8367 from Yan-waller/yj-wip-utthrottle

test/throttle: reassign the value of 'delay' in ThrottleTest.get

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>

Merge pull request #8392 from dachary/wip-virtualenv-jewel

Makefile-env.am: set a default for CEPH_BUILD_VIRTUALENV (part 3)

Reviewed-by: Alfredo Deza <adeza@redhat.com>

Merge pull request #8439 from ErwanAliasr1/evelu-file-leak

tests: Delete temporary files created by ceph_objectstore_tool.py

Reviewed-by: Sage Weil <sage@redhat.com>

Merge pull request #8632 from xiexingguo/xxg-wip-deepscrub

osd: fix be_deep_scrub() can't catch omap error

Reviewed-by: Kefu Chai <kchai@redhat.com>

Merge pull request #8742 from majianpeng/bluestore-wal-transaction

os/bluestore: record released extents into bluestore_wal_transaction_t.

Reviewed-by: Sage Weil <sage@redhat.com>

Merge pull request #8763 from wjwithagen/patch-10

os/filestore: Make sure str-pointer is not 0x0 when referenced

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>

Merge pull request #8808 from wjin/fast_heartbeat

osd: fast dispatch heartbeat message

Reviewed-by: Haomai Wang <haomai@xsky.com>
Reviewed-by: Sage Weil <sage@redhat.com>

Merge pull request #8811 from stiopaa1/log_includes

log: remove unnecessary includes from header file

Reviewed-by: Sage Weil <sage@redhat.com>

Merge pull request #8831 from wjin/clean

osd: clean heartbeat dispatch message

Reviewed-by: Sage Weil <sage@redhat.com>

Merge pull request #8821 from aderumier/deb-fix-default-ceph-location

debian: fix /etc/default/ceph location

Reviewed-by: Sage Weil <sage@redhat.com>

osd/PG: update info.stats.* mappings on splitReviewed-by: Samuel Just <sjust@redhat.com>

osd/PG: update info.stats.* mappings on split

Reviewed-by: Samuel Just <sjust@redhat.com>

Merge pull request #8733 from xiexingguo/xxg-wip-fix-reweightlessutil

mon/OSDMonitor: improve reweight_by_utilization() logic

Reviewed-by: Sage Weil <sage@redhat.com>

Merge pull request #8837 from liewegas/wip-reweight

mon/OSDMonitor: max_osds must be > 0 for reweight-by-*

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>

Merge pull request #8926 from ceph/wip-ec-test-check

test/ec: build the libs only when 'make check'

Reviewed-by: Loic Dachary <ldachary@redhat.com>

Merge pull request #8546 from jcsp/wip-15465

mds: fix auth caps with hyphen in path (#15465)

Reviewed-by: Yan, Zheng <zyan@redhat.com>

Merge pull request #8484 from jcsp/wip-15399

mds: use epoch as incarnation counter (#15399)

Reviewed-by: Sage Weil <sage@redhat.com>

test/ec: build the libs only when 'make check'

Currently, we are always building the erasure code libraries while we
need them only when 'make check' is run. Moving the test libraries to
check_LTLIBRARIES should fix this for us.

We no longer need to remove the libec libs manually, remove the lines
that do that.

Signed-off-by: Boris Ranto <branto@redhat.com>

Merge pull request #8876 from kmroz/wip-fix-rgw-lttng-segfault

global: don't link lttng into libglobal

Reviewed-by: Josh Durgin <jdurgin@redhat.com>

Merge pull request #8637 from roidayan/xio-remove_rdma_and_ibverbs_from_configure

confiugre.ac: remove rdma and ibverbs dependency from xio

Merge pull request #8704 from ceph/wip-cmake-xio-libs

cmake: removed rdmacm & ibverbs parallel to PR#8637

Merge pull request #8914 from adamemerson/wip-grr-warnings

I have a hatred for warnings

Reviewed-by: Greg Farnum <gfarnum@redhat.com>

Merge pull request #8917 from liewegas/wip-civetweb-fix

civetweb: combine various submodule changes

Reviewed-by: Adam Emerson <aemerson@redhat.com>

civetweb: combine various submodule changes

There were some accidental reverts, fixes, re-reverts,
and follow-on changes that are hard to follow and in the
end did not include what we want.  Merge it all together.

Signed-off-by: Sage Weil <sage@redhat.com>

global: don't link lttng into libglobal

Rely on dynamic initialization instead. Linking lttng in this way had
the unfortunate side effect of causing radosgw to segfault (when
daemonized) during sigterm processing (ie. during lttng_ust_exit()).

This was originally removed in 638738f, but accidentally re-added via
5f61d36.

Signed-off-by: Karol Mroz <kmroz@suse.com>

Merge pull request #8809 from trociny/wip-rbd-mirror-asok-restart

rbd-mirror: admin socket commands to start/stop/restart mirroring

Reviewed-by: Jason Dillaman <dillaman@redhat.com>

Merge pull request #8775 from cy-lee/fix-15604-rbd-nbd-write-error

rbd-nbd: fix rbd-nbd aio callback error handling

Reviewed-by: Jason Dillaman <dillaman@redhat.com>

test: Fix warnings in chain_xattr tests

Signed-off-by: Adam C. Emerson <aemerson@redhat.com>

Merge pull request #8910 from dillaman/wip-15709

librbd: unlock image if journal error encountered during lock

Reviewed-by: Josh Durgin <jdurgin@redhat.com>

tests: Fix warnings in C write operations test

Signed-off-by: Adam C. Emerson <aemerson@redhat.com>

Merge pull request #8907 from dillaman/wip-15690

librbd: possible race condition leads to use-after-free

Reviewed-by: Josh Durgin <jdurgin@redhat.com>

Merge pull request #8793 from cbodley/wip-rgw-admin-modify

radosgw-admin: update usage for zone[group] modify

Reviewed-by: Abhishek Lekshmanan <abhishek@suse.com>

librbd: unlock image if journal error encountered during lock

Explicitly unlock to prevent a client from accidentally blacklisting
itself when retrying the lock.

Fixes: http://tracker.ceph.com/issues/15709
Signed-off-by: Jason Dillaman <dillaman@redhat.com>

Merge pull request #8893 from flyd1005/wip-fix-duplicated1

init-ceph.in: remove duplicated words

Merge pull request #8894 from flyd1005/wip-fix-duplicated2

os: remove duplicated words

Merge pull request #8895 from flyd1005/wip-fix-duplicated3

pybind/rados: remove duplicated words

Merge pull request #8896 from flyd1005/wip-fix-duplicated4

mon: remove duplicated words

Merge pull request #8898 from flyd1005/wip-fix-duplicated6

libcephfs.h: remove duplicated words

Merge pull request #8899 from flyd1005/wip-fix-duplicated7

erasure-code: remove duplicated words

Merge pull request #8900 from flyd1005/wip-fix-duplicated8

common: remove duplicated words

Merge pull request #8901 from flyd1005/wip-fix-duplicated9

cls_user: remove duplicated words

Reviewed-by: Sage Weil <sage@redhat.com>

mds: fix upgrades with replay daemons in map

In the new world, a standby replay daemon which
is actively replaying has its rank set.  In the old
world it did not: map this during the upgrade/downgrade
paths in decode/encode.

Fixes: http://tracker.ceph.com/issues/15591
Signed-off-by: John Spray <john.spray@redhat.com>

doc: add cephfs daemon management docs

Principally to tell people how to configure
standby, but more generally as a place to define
our terms for GIDs etc.

Signed-off-by: John Spray <john.spray@redhat.com>

mds: omit fscid in single-filesystem status output

Signed-off-by: John Spray <john.spray@redhat.com>

mds: simplify standby/standby-replay logic

This used to use an arcane set of constants
in standby_for_rank, combined with daemons sometimes
sending requests to enter state STANDBY_REPLAY.

Simplify this so that there is only one place we
put daemons into standby replay, and that is
in tick->maybe_promote_staandby.

There is a behavioural change in here, which is
that we used to sometimes promote standbys to
be standby-replay, even if they didn't have
"standby replay = true", when they did have
a standby_for_rank or standby_for_name set.
I'm calling that a bug, and making it so that
daemons will only go into standby-replay if
"standby replay = true" is set.

Signed-off-by: John Spray <john.spray@redhat.com>

messages: add MMDSBeacon::standby_replay

So that daemons can explicitly say that they
want to be standby replay, instead of using
magic standby_for_rank values.

Because in some cases daemons would indicate this
with a beacon requesting STANDBY_REPLAY state, we
also munge these during decode to be normal STANDBY
requests with standby_replay=true.

Signed-off-by: John Spray <john.spray@redhat.com>

mds: remove ONESHOT_REPLAY mode

This predated cephfs-journal-tool.  Don't bother
with any backwards-compatibility mechanisms here, as
it was a seriously niche undocumented thing.

On the off chance that someone ran an old ceph-mds against
a newer ceph-mon with oneshot enabled, it shouldn't break
anything, it just won't do what they want.

Signed-off-by: John Spray <john.spray@redhat.com>

Merge pull request #8698 from HeyoQiang/hyq0422

rbd: help message distinction between commands and aliases

Reviewed-by: Jason Dillaman <dillaman@redhat.com>

librbd: possible race condition leads to use-after-free

The invoke async operation state machine can complete before the
owner lock is released.  Use a stack reference to prevent
use-after-free.

Fixes: http://tracker.ceph.com/issues/15690
Signed-off-by: Jason Dillaman <dillaman@redhat.com>

Merge pull request #8788 from jmunhoz/fix-15626

rgw: add AWS4 completion support for RGW_OP_SET_BUCKET_WEBSITE

Merge pull request #8897 from flyd1005/wip-fix-duplicated5

mds: remove duplicated words

Reviewed-by: John Spray <john.spray@redhat.com>

Merge pull request #8760 from theanalyst/f/rgw-orphans-list-jobs

rgw orphans list jobs

rbd:make a distinction of help message between ''rbd snap rollback" and "rbd snap revert"

Fixes: https://tracker.ceph.com/issues/15521
Signed-off-by: Yongqiang He <he.yongqiang@h3c.com>

Merge pull request #8469 from dachary/wip-15403-api-test-timeout

tests: be more generous with test timeout

Reviewed-by: Nathan Cutler <ncutler@suse.com>

Merge pull request #8655 from theanalyst/rgw/multisite-delete

rgw: forward delete bucket to master before deleting them in a zone
Reviewed-by: Orit Wasserman <owasserm@redhat.com>

Merge pull request #7193 from theanalyst/doc/rgw-13066-fix

doc:explain service tenant config for rgw keystone

Merge pull request #8782 from SUSE/wip-15627

install-deps.sh: systemd-rpm-macros must be installed on SUSE

Reviewed-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
Reviewed-by: Loic Dachary <ldachary@redhat.com>

Merge pull request #8875 from tchaikov/wip-double-colon

automake: use :: rule for adding target

Reviewed-by: Loic Dachary <ldachary@redhat.com>

rbd-nbd: Fix aio_callback error handling

Change aio_callback return code handling for NBD_CMD_READ command.

Tracker:
http://tracker.ceph.com/issues/15604

Signed-off-by: Chang-Yi Lee <cy.l@inwinstack.com>

Merge pull request #8852 from yuyuyu101/wip-async-clock

msg/async/Event: replace ceph_clock_now with coarse_real_clock

Reviewed-by: Kefu Chai <kchai@redhat.com>

cls_user: remove duplicated words

Signed-off-by: Li Peng <lip@dtdream.com>

common: remove duplicated words

Signed-off-by: Li Peng <lip@dtdream.com>

erasure-code: remove duplicated words

Signed-off-by: Li Peng <lip@dtdream.com>

libcephfs.h: remove duplicated words

Signed-off-by: Li Peng <lip@dtdream.com>

mds: remove duplicated 'this'

Signed-off-by: Li Peng <lip@dtdream.com>

mds: remove duplicated words

Signed-off-by: Li Peng <lip@dtdream.com>

mon: remove duplicated words

Signed-off-by: Li Peng <lip@dtdream.com>

pybind/rados: remove duplicated words

Signed-off-by: Li Peng <lip@dtdream.com>

os: remove duplicated words

Signed-off-by: Li Peng <lip@dtdream.com>

init-ceph.in: remove duplicated words

Signed-off-by: Li Peng <lip@dtdream.com>

Merge pull request #8891 from tchaikov/wip-fix-test-using-dash

test/encoding/readable.sh: use bash instead of sh

Reviewed-by: Brad Hubbard <bhubbard@redhat.com>

Merge pull request #8889 from linuxbox2/rbd-nbd-cmake

cmake: fix rbd-nbd linkage

Reviewed-by: Kefu Chai <kchai@redhat.com>

test/encoding/readable.sh: use bash instead of sh

aside from the `source` statement, the readable.sh is POSIX shell
script. we can just "." the referenced helper script. but to be
consistent with other encoding/*.sh scripts, let's just change the
shebang line to "#!/bin/bash".

Signed-off-by: Kefu Chai <tchaikov@gmail.com>

Merge pull request #8885 from stiopaa1/osd_removeSendMessageConn

osd/OSD.h: remove C_OSD_SendMessageOnConn class

Reviewed-by: Kefu Chai <kchai@redhat.com>

automake: use :: rule for adding target

Signed-off-by: Kefu Chai <kchai@redhat.com>

Merge pull request #8072 from yuyuyu101/wip-async-skip-steps

async: skip unnecessary steps when parsing simple messages

cmake: fix rbd-nbd linkage

Use correct name for librbd, add parse_secret_objs and its
keyutils libdep.

Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>

Merge pull request #8883 from dillaman/wip-15685

librbd: clone fails if config overridden to use image format 1 by default

Reviewed-by: Josh Durgin <jdurgin@redhat.com>

Merge pull request #8882 from liewegas/wip-check-port

test/mon/mon-created-time: put on unique port

Reviewed-by: Loic Dachary <ldachary@redhat.com>

Merge pull request #8884 from ktdreyer/docs-packaging

doc: remove references to old EOL releases

Reviewed-by: Sage Weil <sage@redhat.com>

Merge pull request #8864 from trociny/fixup-rbd-mirror-test-log

qa/workunits/rbd: fix rbd-mirror log file name

Reviewed-by: Josh Durgin <jdurgin@redhat.com>

librbd: default clone operation to image format 2

Image format 1 doesn't support clones, so unless the user
overrode the setting, default to format 2.

Fixes: http://tracker.ceph.com/issues/15685
Signed-off-by: Jason Dillaman <dillaman@redhat.com>

librbd: add rbd_image_options_is_set helper method to API

Signed-off-by: Jason Dillaman <dillaman@redhat.com>

Merge pull request #8877 from dillaman/wip-15664

rbd-mirror: lockdep error during bootstrap

Reviewed-by: Josh Durgin <jdurgin@redhat.com>

doc: remove references to old EOL releases

There were several references to old releases like "dumpling",
"emperor", and "firefly", throughout the docs. Remove these and update
the examples to use jewel instead.

Remove references to CentOS 6 and RHEL 6, since we only support CentOS 7
now.

Signed-off-by: Ken Dreyer <kdreyer@redhat.com>

rbd-mirror: admin socket commands to start/stop/restart mirroring

Signed-off-by: Mykola Golub <mgolub@mirantis.com>

osd/OSD.h: remove C_OSD_SendMessageOnConn class

Signed-off-by: Michal Jarzabek <stiopa@gmail.com>

test/mon/mon-created-time: put on unique port

7122 is also used by test/osd/osd-reactivate.sh

Signed-off-by: Sage Weil <sage@redhat.com>

Merge pull request #8770 from ceph/wip-cmake

cmake: build fixes

Merge pull request #8844 from stiopaa1/log_removelexical

common/Graylog.h: remove lexical cast

Reviewed-by: Kefu Chai <kchai@redhat.com>

Merge pull request #8879 from ktdreyer/doc-rm-up2date

doc: drop references to "up2date"

doc: drop references to "up2date"

"up2date" has not been used since very old versions of RHEL (rhel4 or
5?). We only support el7 now, which is a yum-based platform.

Signed-off-by: Ken Dreyer <kdreyer@redhat.com>

Merge pull request #8878 from ktdreyer/wip-doc-rbd-dillaman

doc: Jason Dillaman is now RBD lead

Reviewed-by: Josh Durgin <jdurgin@redhat.com>

doc: Jason Dillaman is now RBD lead

Signed-off-by: Ken Dreyer <kdreyer@redhat.com>

cmake: Added rbd-nbd target

Signed-off-by: Ali Maredia <amaredia@redhat.com>

librbd: disable automatic refresh of image upon lock message

There is no need to refresh the image upon request/release/acquire
of the exclusive lock.  The next IO or maintenance op will kick off
the refresh.  This is interfering with the refresh state machine
unit test case (since two concurrent refreshes shouldn't be possible).

Signed-off-by: Jason Dillaman <dillaman@redhat.com>

librbd: update_features should release lock if acquired

There is a small window where requests are unblocked and before
the image is shut down where new requests can be accepted.  These
are correctly canceled during the shut down, but it can lead to
warning messages.

Signed-off-by: Jason Dillaman <dillaman@redhat.com>