Changed Availability section of ceph-mds.rst to reference ceph-mds, not ceph-mon.
Signed-off-by: James Ryan Cresawn <jrcresawn@gmail.com>

Client: fix build issue (lost semicolon)

Signed-off-by: Greg Farnum <greg@inktank.com>

Merge pull request #1320 from ceph/wip-libcephfs-fixes

Wip libcephfs fixes

Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>

Merge pull request #1338 from dachary/wip-mailmap

mailmap updates

Reviewed-by: Christophe Courtaut <christophe.courtaut@gmail.com>

mailmap: Danny Al-Gaaf affiliation

Signed-off-by: Loic Dachary <loic@dachary.org>

mailmap: Bjørnar Ness affiliation

Signed-off-by: Loic Dachary <loic@dachary.org>

mailmap: Ron Allred affiliation

Signed-off-by: Loic Dachary <loic@dachary.org>

mailmap: Steve Stock affiliation

Signed-off-by: Loic Dachary <loic@dachary.org>

mailmap: Christopher O'Connell affiliation

Reviewed-by: Christopher O'Connell <jwriteclub@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org>

Merge pull request #1370 from ceph/wip-7293

Make symlink  of librbd to qemu's folder so it can detect it.

Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

Make symlink  of librbd to qemu's folder so it can detect it.

Per issue #7293.

Signed-off-by: Sandon Van Ness <sandon@inktank.com>

doc: Improve CloudStack RBD documentation

mailmap: Mike Lundy affiliation

Signed-off-by: Loic Dachary <loic@dachary.org>

Merge pull request #1353 from ceph/wip-messenger-shutdown

msg: Make SimpleMessenger shutdown safer

Reviewed-by: Greg Farnum <greg@inktank.com>

msg: Make SimpleMessenger shutdown safer

...in the case where no dispatchers were ever added, previously
we would throw an assertion in wait().

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

Merge pull request #1329 from ceph/wip-doc-cache-pool

fix up docs for cache pools

These are definitely not complete, but they bring a few of the commands more up to date with current syntax.

Reviewed-by: Greg Farnum <greg@inktank.com>

mailmap: Mouad Benchchaoui affiliation

Signed-off-by: Loic Dachary <loic@dachary.org>

mailmap: Andrey Kuznetsov affiliation

Reviewed-by: Andrey Kuznetsov <Andrey_Kuznetsov@epam.com>
Signed-off-by: Loic Dachary <loic@dachary.org>

mailmap: Wang, Yaguang affiliation

and name normalization

Reviewed-by: Wang, Yaguang <yaguang.wang@intel.com>
Signed-off-by: Loic Dachary <loic@dachary.org>

Merge pull request #1345 from leseb/wip-ceph-disk-typo

Fix typo ceph-disk

Reviewed-by: Loic Dachary <loic@dachary.org>

Fix typo ceph-disk

Fix typo

Signed-off-by: Sébastien Han <sebastien.han@enovance.com>

mailmap: The Linux Box affiliations

Matt Benjamin, Adam C. Emerson and Casey Bodley are with The Linux Box

Signed-off-by: Loic Dachary <loic@dachary.org>

Merge pull request #1334 from kazhang/wip-get-hit_set-parameter

OSDMonitor: enable getting hit set parameters

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

OSDMonitor: enable getting hit set parameters
We would like to get the hit set parameters: hit_set_type |
hit_set_period | hit_set_count | hit_set_fpp via OSDMonitor

Signed-off-by: Kai Zhang <zakir.exe@gmail.com>

Merge pull request #1333 from ceph/wip-s3radoscheck-wusui

Use pgrep radosgw to determine if rados gateway is running.

Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>

Use pgrep radosgw to determine if rados gateway is running.
Fixes: 7528
Signed-off-by: Warren Usui <warren.usui@inktank.com>

client: fix Client::trim_caps()

allow trimming non-auth caps if the issued auth caps include all
caps client wants/uses.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

client: update dirfragtree/fragmap according to mds request reply

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

client: choose hash function according to dir layout

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

client: check inode's cap when looking up dentry

Some inodes in readdir reply may have no caps. Getattr mds request
for these inodes can return -ESTALE. The fix is consider dentry that
links to inode with no caps as invalid. Invalid dentry causes a
lookup request to send to the mds, the MDS will send caps back.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

client: add flushing inode to proper list when auth mds changes

add flushing inode to the new auth MDS' flushing caps list

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

client: add imported caps when handling cap export message

Version 3 cap export message includes information about the imported
caps. It allows us to add the imported caps if the corresponding cap
import message still hasn't been received.

This allow us to handle situation that the importer MDS crashes and
the cap import message is missing.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

client: remove exported caps when handling cap import message

Version 3 cap import message includes the ID of the exported
caps. It allow us to remove the exported caps if we still haven't
received the corresponding cap export message.

We remove the exported caps because they are stale, keeping them
can compromise consistence.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

client: use ceph_seq_cmp() to compare cap seq/mseq

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

client: don't send cap release when removing exported cap

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

Merge pull request #1323 from ceph/wip-requests-dependencies

Fix python-requests package dependencies.

Backport: firefly
Reviewed-by: Sage Weil <sage@inktank.com>

doc/dev/cache-pool: fix notes

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

client: clear migrate seq when MDS restarts

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

client: fix race between cap issue and revoke

If we receive new caps from the auth MDS and the non-auth MDS is
revoking the newly issued caps, we should release the caps from
the non-auth MDS. The scenario is filelock's state changes from
SYNC to LOCK. Non-auth MDS revokes Fc cap, the client gets Fc cap
from the auth MDS at the same time.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

client: check mds_wanted for imported cap

The MDS may have incorrect wanted caps after importing caps. So the
client should check the value mds has and send cap update if necessary.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

client: allow revoking duplicated caps issued by non-auth MDS

Allow revoking duplicated caps issued by non-auth MDS if these caps
are also issued by auth MDS.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

client: call handle_cap_grant() for cap import message

If client sends cap message that requests new max size during
exporting caps, the exporting MDS will drop the message quietly.
So the client may wait for the reply that updates the max size
forever. call handle_cap_grant() for cap import message can
avoid this issue.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

client: don't update i_max_size when handle reply from non-auth MDS

caps from non-auth mds don't have meaningful max_size

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

Fix python-requests package dependencies.

python-ceph does not require requests, but ceph-common does (for ceph-brag).

Signed-off-by: Dan Mick <dan.mick@inktank.com>

Merge pull request #1263 from ceph/wip-mds-dumper

mds: Dumper improvements

Reviewed-by: Greg Farnum <greg@inktank.com>

mds: Add dump-journal-entries

This adds a somewhat-human-readable peer to
the 'dump-journal' command.

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

mds: Create MDSUtility as base for Dumper/Resetter

These classes has lots of similar functionality and we may
want to add more similar things in the future.

Also, get a copy of the MDS map at startup
to learn the ID of the metadata pool instead of
assuming it's the default.

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

mds: Fix Dumper shutdown

It was shutting down messenger before monclient.  This
caused a sometimes-assertion when monclient tried to
reconnect in response to ms_handle_reset.

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

Merge pull request #1283 from ceph/wip-7485

mon/MDSMonitor: Cope with failures during creation

Reviewed-by: Greg Farnum <greg@inktank.com

Merge pull request #1264 from ceph/wip-mds-dencoder

mds: Add encode/decode/dump for use with dencoder

Reviewed-by: Greg Farnum <greg@inktank.com>

Merge pull request #1280 from ceph/wip-7374-wusui

Fix sub check() to not exit if rgw is running.

Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>

Merge pull request #1279 from ceph/wip-7375-wusui

Fixed sub check() to say okay if rgw is running.

Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>

Fixed get_status() to find client.radosgw fields inside of ps output.
Fixes: 7375
Signed-off-by: Warren Usui <warren.usui@inktank.com>

Fix get_status() to find client.rados text inside of ps command results.
Added port (fixed value for right now in teuthology) to hostname.
Fixes: 7374
Signed-off-by: Warren Usui <warren.usui@inktank.com>

mds: add mds_kill_create_at for testing

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

Merge pull request #1303 from ceph/port/temp-failure-retry

compat: avoid unused warn with TEMP_FAILURE_RETRY

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

compat: avoid unused warn with TEMP_FAILURE_RETRY

The version of TEMP_FAILURE_RETRY found on Linux has a GNU extension
that squashes the unused return value warning where applicable. This
adds a VOID_TEMP_FAILURE_RETRY to make the case explicit, casting the
expression value to void to avoid the warning.

Signed-off-by: Noah Watkins <noahwatkins@gmail.com>

Merge pull request #1287 from kdreyer-inktank/redhat-files

packaging: file list adjustments

Tested-by: Huang Jun <hjwsm1989@gmail.com>

Merge pull request #1265 from ceph/wip-mds-misc

MDS misc. cleanup

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

os/ObjectStore: fix rebase errors

These were goofed by d74f1282cd268b4b04cfd9e90ddeac6d1dc6be7e.

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

README: add build dep

Technically it's a 'make check' dep, but close enough.

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

Merge remote-tracking branch 'gh/firefly'

Merge pull request #1290 from ceph/wip-os-doc

os/ObjectStore: document interface

os/ObjectStore: document interface

Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Haomai Wang <haomaiwang@gmail.com>

Merge pull request #1294 from ceph/wip-librados-object-iterator

fix bugs in librados::ObjectIterator

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

Merge pull request #1295 from yuyuyu101/keyvaluestore-enhance

Keyvaluestore enhance(backport to firely)

Pulling this into firefly because it doesn't (substantiatively) touch anything outside of KeyValueStore.

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

Merge pull request #1297 from ceph/wip-ec-bugs

Wip ec bugs

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

unittest_ecbackend: fix signed/unsigned warnings

In file included from test/osd/TestECBackend.cc:20:0:
../src/gtest/include/gtest/gtest.h: In instantiation of ‘testing::AssertionResult testing::internal::CmpHelperEQ(const char*, const char*, const T1&, const T2&) [with T1 = long unsigned int; T2 = int]’:
../src/gtest/include/gtest/gtest.h:1300:30: required from ‘static testing::AssertionResult testing::internal::EqHelper::Compare(const char*, const char*, const T1&, const T2&) [with T1 = long unsigned int; T2 = int; bool lhs_is_null_literal = false]’
test/osd/TestECBackend.cc:30:281: required from here
warning: ../src/gtest/include/gtest/gtest.h:1263:3: comparison between signed and unsigned integer expressions [-Wsign-compare]

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

Merge pull request #1301 from ceph/wip-scrub-primary

mon/PGMonitor: fix primary osd check on deep-scrub

gitbuilders are now passing

mon/PGMonitor: fix primary osd check on deep-scrub

s/!=/==/.  Logic was reversed.

Broken in 40bdcb88504aea6288d461d29d24d5b0bf7aeebc.

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

Merge pull request #1300 from ceph/wip-7513

PGLog::activate_not_complete typo

Reviewed-by: David Zafman <david.zafman@inktank.com>

PGLog::activate_not_complete: fix log.complete_to increment typo

info.last_complete should be the entry before log.complete_to.

This appears to have been a typo introduced in
dd71051a8f6ec611b3559f8e2aff3c001be37792.

Signed-off-by: Samuel Just <sam.just@inktank.com>

Merge pull request #1298 from ceph/wip-subscribe

osd: fix off-by-one is boot subscription

Reviewed-by: Samuel Just <sam.just@inktank.com>

Merge pull request #1299 from ceph/wip-repair

osd/PG: fix assert when a shallow repair has fixed all errors.

Reviewed-by: David Zafman <david.zafman@inktank.com>

osd/PG: fix assert when deep repair finds no errors

If there are no deep repairs, we don't want to assert.
Fixes:

    -1> 2014-02-21 21:13:56.393087 7f0258ff9700  0 log [INF] : 0.0 repair ok, 0 fixed
     0> 2014-02-21 21:13:56.428703 7f0258ff9700 -1 osd/PG.cc: In function 'void PG::scrub_finish()' thread 7f0258ff9700 time 2014-02-21 21:13:56.393127
osd/PG.cc: 4294: FAILED assert(deep_scrub)

Signed-off-by: David Zafman <david.zafman@inktank.com>
Signed-off-by: Sage Weil <sage@inktank.com>

PGLog: test for missing using the correct shard value

Signed-off-by: Samuel Just <sam.just@inktank.com>

OSD: fix query for ec pgs

We need to parse a pg_t and translate it into an spg_t.

Signed-off-by: Samuel Just <sam.just@inktank.com>

Objecter: make is_pg_changed static and const for old/newacting

Signed-off-by: Samuel Just <sam.just@inktank.com>

OSDMap: make calc_pg_rank/role const for acting

Signed-off-by: Samuel Just <sam.just@inktank.com>

Objecter: resend op if primary role changed

Fixes: #7508
Signed-off-by: Samuel Just <sam.just@inktank.com>

ECTransaction: require hash_infos for deleted objects

Otherwise, an append preceded by a delete may not see the
correct HashInfo state since it won't have been cached
until the delete is applied.

Fixes: #7506
Signed-off-by: Samuel Just <sam.just@inktank.com>

ECUtil: clear() should reset hashes to -1, not 0

Signed-off-by: Samuel Just <sam.just@inktank.com>

ReplicatedPG::cancel_pull: ECBackend might cancel_pull on a non-missing object

Signed-off-by: Samuel Just <sam.just@inktank.com>

ECBackend::filter_read_op: clean up read state properly

Fixes: #7494
Signed-off-by: Samuel Just <sam.just@inktank.com>

osd: fix off-by-one is boot subscription

If we have osdmap N, we want to onetime subscribe
starting at N+1.  Among other things, it means we
hear when the NOUP flag is cleared.

This appears to have broken somewhere around
3c76b81f2f96b790b72f2088164ed8e9d5efbba1.

Fixes: #7511
Signed-off-by: Sage Weil <sage@inktank.com>

Rename keyvaluestore_check_backend to keyvaluestore_debug_check_backend

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>

Add KeyValueStore op thread options

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>

Remove eio inject codes in KeyValueStore

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>

Add config tracker to KeyValueStore

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>

Add backend check option to KeyValueStore

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>

Remove filestore_inject_stall

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>

Remove m_eio in KeyValueStore

KeyValueStore use kv backend to detect errors and nearly can't know the actual
reason for error.

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>

Make SequencePosition sync by each transaction

Each object modify will increase SequencePosition and sync it to disk

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>

Implement collection_rename interface in KeyValueStore

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>

Remove unnecessary "check_coll" check

The goal of "check_coll" is aimed to ensure the collection is exists. But
the create and delete of collection already ensured by OSD, just remove check.

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>

Optimize write call add enhance error detect

A single write call may need several keys in the backend kv store. Let get these
keys one time.

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>

Unify object level lock in GenericObjectMap

Before we copy lock implementation from DBObjectMap which provide with two locks
for header. Here just unify it to make ease.

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>

Fix incorrect read and truncate

If the first chunk of object is not read entirely, the current implementation
will contain it entirely which make wrong.

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>

Return 0 when the offset of read exceed the length of object

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>

Add read/write operation to store_test.cc

Signed-off-by: Haomai Wang <haomaiwang@gmail.com>