Activity
From 06/07/2012 to 07/06/2012
07/06/2012
- 11:45 PM Revision 03c2dc24 (ceph): lockdep: increase max locks
- Hit this limit with the rados api tests.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:45 PM Revision b554d112 (ceph): config: add unlocked version of get_my_sections; use it internally
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:45 PM Revision 01da287b (ceph): config: fix lock recursion in get_val_from_conf_file()
- Introduce a private, already-locked version.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:45 PM Revision c73c64a0 (ceph): config: fix recursive lock in parse_config_files()
- The _impl() helper is only called from parse_config_files(); don't retake
the lock.
Signed-off-by: Sage Weil <sage@i... - 11:44 PM Revision b33553aa (ceph): rgw: handle response-* params
- Handle response-* params that set response header field values.
Fixes #2734, #2735.
Backport: argonaut
Signed-off-by... - 11:43 PM Revision 97c1562d (ceph): rgw: handle response-* params
- Handle response-* params that set response header field values.
Fixes #2734, #2735.
Backport: argonaut
Signed-off-by... - 11:43 PM Revision 6646e891 (ceph): rgw: initialize fields of RGWObjEnt
- This fixes various valgrind warnings triggered by the s3test
test_object_create_unreadable.
Signed-off-by: Sage Weil... - 10:17 PM Revision 74f68750 (ceph): osd: add missing formatter close_section() to scrub status
- Also add braces to make the open/close matchups easier to see. Broken
by f36617392710f9b3538bfd59d45fd72265993d57.
... - 08:45 PM Revision 020b2996 (ceph): pg: report scrub status
- Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
- 08:45 PM Revision db6d83b3 (ceph): pg: track who we are waiting for maps from
- Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
- 08:45 PM Revision e1d4855f (ceph): pg: reduce scrub write lock window
- Wait for all replicas to construct the base scrub map before finalizing
the scrub and locking out writes.
Signed-off... - 08:03 PM Feature #2743 (Resolved): new cond assertions, associated cleanups
- 09:41 AM Feature #2743 (Resolved): new cond assertions, associated cleanups
- 07:21 PM Revision 72bf66f6 (ceph): doc: added some discussion to libvirt.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:14 PM Revision 1316f868 (ceph): cond: cleanup
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:14 PM Revision 7c919e9b (ceph): workqueue: kick -> wake or _wake, depending on locking
- Break kick() into wake() and _wake() methods, depending on whether the
lock is already held. (The rename ensures tha... - 07:14 PM Revision b5693a6e (ceph): librados: take lock when signaling notify cond
- When we are signaling the cond to indicate that a notify is complete,
take the appropriate lock. This removes the po... - 07:14 PM Revision 9c6fdd5a (ceph): librados: drop unused local variables
- This is unused boilerplate cruft.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:14 PM Revision da7a3284 (ceph): cond: drop unused Wait variant
- This was used for debugging forever ago.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:07 PM Revision b486f2ff (ceph): client: fix locking for SafeCond users
- Need to wait on flock, not client_lock.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:07 PM Revision 8de0c227 (ceph): cond: assert that we are holding the same mutex as the waiter
- Try to verify that we are holding the same mutex that the waiter is
waiting on. Specifically:
* only wait on a sin... - 06:29 PM Revision 57463455 (ceph): Merge branch 'master' of github.com:ceph/ceph
- 06:29 PM Revision 540c2c3a (ceph): doc: Minor cleanup on deploy with Chef.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:18 PM Revision 3df51040 (ceph): rgw: don't store bucket info indexed by bucket_id
- Issue #2701. This info wasn't really used anywhere and we weren't
removing it. It was also sharing the same pool name... - 05:17 PM Revision 27409aa1 (ceph): rgw: don't store bucket info indexed by bucket_id
- Issue #2701. This info wasn't really used anywhere and we weren't
removing it. It was also sharing the same pool name... - 05:16 PM Revision 84ba6bf6 (ceph): Merge branch 'stable' into next
- 05:15 PM Revision 960c2124 (ceph): rados tool: copy object
- New rados command: rados cp <src-obj> [dest-obj]
Requires specifying source pool. Target pool and locator can be spe... - 05:15 PM Revision 16ea64fb (ceph): rados tool: copy entire pool
- A new rados tool command that copies an entire pool
into another existing pool.
Signed-off-by: Yehuda Sadeh <yehuda@... - 05:15 PM Revision d7510066 (ceph): rados tool: copy object in chunks
- Instead of reading the entire object and then writing it,
we read it in chunks.
Signed-off-by: Yehuda Sadeh <yehuda@... - 05:15 PM Revision 9814374a (ceph): test_rados_tool.sh: test copy pool
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:12 PM Revision d59b2db4 (ceph): Merge remote-tracking branch 'origin/stable' into next
- 05:05 PM Feature #2702 (Resolved): gitbuilder: sync each build as it completes
- 03:23 PM Feature #2702: gitbuilder: sync each build as it completes
- 09:43 AM Feature #2702 (In Progress): gitbuilder: sync each build as it completes
- 05:02 PM rgw Feature #2735 (Resolved): rgw: support response-* request params in GET obj
- 04:35 PM rgw Feature #2735: rgw: support response-* request params in GET obj
- Fixed, commit:b33553aae63f70ccba8e3d377ad3068c6144c99a.
- 05:02 PM Revision ed3bd211 (ceph): increase thrashosds timeout
- 04:48 PM Feature #2680: osd: report backfill progress via query
- not yet tested https://github.com/athanatos/ceph/tree/wip_recovery_query
- 04:45 PM Bug #2751 (Resolved): info can grow without bound but is kept on collection attribute
- in progress already https://github.com/athanatos/ceph/tree/wip_biginfo
blocked by 2748 - 04:35 PM Bug #2750 (Won't Fix): 1.14 scrub stat mismatch, got 4/4 objects, 0/0 clones, 8138/7467 bytes."...
- lavor: basic
owner: scheduled_sage@metropolis
success: false
ubuntu@teuthology:/a/sage-2012-07-06_11:03:15-regress... - 04:35 PM rgw Bug #2734 (Resolved): rgw: fails to authenticate preauthenticated requests with sub resource
- Fixed, commit:b33553aae63f70ccba8e3d377ad3068c6144c99a.
- 10:58 AM rgw Bug #2734: rgw: fails to authenticate preauthenticated requests with sub resource
- Fails only with specific sub resources (e.g., response-*) that were not hard coded.
- 04:34 PM Bug #2749: osd/ReplicatedPG.cc: 3436: FAILED assert(last_update_applied < repop->v)
- roles:
- - mon.a
- osd.0
- osd.1
- osd.2
- - mds.a
- osd.3
- osd.4
- osd.5
- - client.0
targets... - 04:32 PM Bug #2749 (Resolved): osd/ReplicatedPG.cc: 3436: FAILED assert(last_update_applied < repop->v)
- Saw on master
osd/ReplicatedPG.cc: 3436: FAILED assert(last_update_applied < repop->v)
ceph version 0.48argona... - 04:23 PM Bug #2748 (Resolved): include/CompatSet.h, osd/osd_types.h inconsistent use of mask argument
- 03:51 PM Bug #2600: osd: crazy long watch timeout?
- another instance:...
- 03:47 PM Revision 23d31d3e (ceph): ceph.spec.in: add ceph-disk-{activate,prepare}
- Reported-by: Jimmy Tang <jtang@tchpc.tcd.ie>
Signed-off-by: Sage Weil <sage@inktank.com> - 03:47 PM Bug #2747 (Resolved): osd/ReplicatedPG.cc: 3436: FAILED assert(last_update_applied < repop->v)
- ...
- 01:23 PM rgw Bug #2701 (Resolved): rgw: don't keep bucket info indexed by bucket_id
- Fixed, commit:3df51040b19b9c110e08f42befa0cae18cbb984c.
- 11:34 AM devops Feature #2697: crowbar: ISO generation, reproducible in a cloud image vm
- Thanks, updated the doc to increase the VM size.
- 10:24 AM Subtask #2737: mon: Single-Paxos: Sync: Force trimming to be proposed through Paxos
- Currently, Paxos own trimming is going through the Paxos proposal mechanism itself.
However, services do not do it... - 09:29 AM Subtask #2737 (Resolved): mon: Single-Paxos: Sync: Force trimming to be proposed through Paxos
- This includes Paxos' own trimming, so it done at the same time in all the quorum members. Furthermore, it allows the ...
- 10:18 AM Subtask #2738: mon: Single-Paxos: Sync: Add snapshot support to the monitor store
- Implemented, although it has not been tested yet.
- 09:31 AM Subtask #2738 (Rejected): mon: Single-Paxos: Sync: Add snapshot support to the monitor store
- Having snapshot support, and being able to iterate over it instead of iterating directly over the store's keys, allow...
- 10:09 AM CephFS Bug #1947: mds: SIGBUS during _mark_dirty
- latest logs:
/a/teuthology-2012-07-06_00:00:03-regression-next-testing-basic/6655 - 10:01 AM Subtask #2746 (Rejected): mon: Single-Paxos: Sync: Test message passing
- Make sure the message passing is working before starting to work on the store synchronization.
From the monitor's ... - 09:58 AM Subtask #2745 (Closed): mon: Single-Paxos: Sync: Add new message support to the Monitor class
- Three different "roles" on a monitor cluster regarding synchronization:
* Leader - responsible for disabling the P... - 09:53 AM Subtask #2744 (Resolved): mon: Single-Paxos: Sync: Create new Message type
- Create a new message type MMonSync, to dissociate it from the MMonProbe messages, and to allow us to use fields speci...
- 09:43 AM RADOS Feature #2706 (In Progress): crush: update kernel code to decode tunables
- 09:40 AM Feature #2742 (Resolved): qa: ms socket inject failures in regression suite
- 09:40 AM Subtask #2741 (Resolved): mon: Single-Paxos: Sync: Assess requirements for QA tests
- TBD
- 09:37 AM CephFS Bug #2740 (Resolved): mds: crash in Objecter when shutting down too early
- Jimmy Tang reported this on the mailing list....
- 09:36 AM Subtask #2739 (Resolved): mon: Single-Paxos: Sync: Synchronize the store of a drifted monitor
- Synchronize the store of a monitor (mon.X) that drifted away from the system (say, it failed for a considerable amoun...
- 09:22 AM Subtask #2736 (Resolved): mon: Single-Paxos: Sync: Implement message passing
- See subtasks.
- 04:28 AM Revision 668ce00a (ceph): osd: make on_removal() pure virtual
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:26 AM Revision 3d00130b (ceph): osd: fix PG dtor compile error
- We need at least none non-pure virtual method to tell gcc where the
vtable goes. The destructor wins!
libosd.a(libo... - 01:37 AM Bug #2267: Ceph client crashed after shutting down one mds and osd
- To which version do you plan to add this patch?
- 12:20 AM Revision 6e3fb20d (ceph): Merge remote-tracking branch 'gh/wip_osd_threading'
- 12:18 AM Revision bdf09f20 (ceph): OSD,ReplicatedPG::snap_trimmer: pg->put() in process, not snap_trimmer()
- This clarifies responsibility for the reference.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 12:18 AM Revision 0475ee45 (ceph): OSD,PG:;replica_scrub: move msg->put() into queue process
- This clarifies the ownership of the reference.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 12:18 AM Revision fe14c181 (ceph): OSD::PeeringWQ::_dequeue(PG*) drop pg refs
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 12:18 AM Revision 816d4247 (ceph): ReplicatedPG.cc: C_OSD_CommittedPushedObject move pg->put() to finish
- This should clarify the ownership of the pg ref.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 12:18 AM Revision 8e93e8b0 (ceph): OSD: ensure that OpSequencer lives through on_commit callback
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 12:18 AM Revision 69174198 (ceph): OSDMonitor: disable cluster snapshot
- The map handling changes broke cluster snapshot support.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 12:18 AM Revision 09af670b (ceph): PG,ReplicatedPG: on_removal must handle repop and watcher state
- on_removal is now in ReplicatedPG in order to handle watcher state
and repop state. Addionally, workqueue dequeues a... - 12:18 AM Revision cab7b75d (ceph): OSD: drop pg refcounts in OpWQ::_dequeue(PG*)
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 12:18 AM Revision 868168a5 (ceph): OSD: clean up revcovery_wq queueing and ref counting
- Previously, we tended to explicitely remove the pg from the queue uisng
remove_myself on the xlist::item. This cause...
07/05/2012
- 10:30 PM Feature #2692 (Resolved): stable testing debian repos
- 10:29 PM Revision c70392a8 (ceph): doc: minor typo
- Signed-off-by: Ross Turk <ross@inktank.com>
- 10:24 PM Revision 4d7bb075 (ceph): doc: update copyright notice in footer
- Signed-off-by: Ross Turk <ross@inktank.com>
- 10:16 PM Linux kernel client Bug #2716 (Resolved): crash when cluster goes down and new one comes up
- bad con->private = NULL in monc __close_session
- 09:38 PM Bug #2508: osdc/ObjectCacher.cc:761: void ObjectCacher::bh_write_commit(int64_t, sobject_t, loff_...
- easy to reproduce with...
- 08:44 AM Bug #2508: osdc/ObjectCacher.cc:761: void ObjectCacher::bh_write_commit(int64_t, sobject_t, loff_...
- I just reproduced this several times on master using the socket failure injection. This is probably socket errors br...
- 09:37 PM Bug #2022: osd: misdirectect request
- ugh, wrong bug.. ignore last two messages!
- 05:19 PM Bug #2022: osd: misdirectect request
- this is easily reproduced with...
- 05:18 PM Bug #2022 (In Progress): osd: misdirectect request
- ...
- 09:01 PM Revision 57bc8da9 (ceph): doc: minor updates to the restrucuredText file.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:00 PM Revision 0659f7c5 (ceph): doc: minor cleanup.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:47 PM Revision 1c9e1c61 (ceph): doc: Publishing as described. Still requires some verification and QA.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:43 PM Revision e5fb4991 (ceph): run: make -a short for --archive
- 06:18 PM devops Feature #2697: crowbar: ISO generation, reproducible in a cloud image vm
- The size of a VM is adjustable:...
- 05:49 PM devops Feature #2697: crowbar: ISO generation, reproducible in a cloud image vm
- Tested on vercoi/downburst
https://docs.google.com/a/inktank.com/document/d/1C1QLD54sbpRJ7o6M9ML2TrexXC5JIMecHJxOM... - 05:21 PM Cleanup #2041 (Resolved): osd: move peering into worker threads
- 05:15 PM Revision 87d1cdb5 (ceph): OSD: _remove_pg not ruin iterator consistency
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 7b5d8e8c (ceph): ReplicatedPG: on_activate for a peer might happen before flush
- We don't ensure for a peer that the flush completes before activation,
merely that we don't serve any ops until flush... - 05:15 PM Revision f0b2310f (ceph): ReplicatedPG: RepModify track epoch_started and bail on interval change
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 193f18f2 (ceph): FileStore: delete source collection if not replaying collection_rename
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 99c23b69 (ceph): OSD: split notify|info|query messages for old clients
- Old clients do not expect mixed epoch compound messages. Thus, we
send each sub-message independently.
Signed-off-b... - 05:15 PM Revision 4ce17cca (ceph): test/encoding/types.h: disable pg_query_t encoding test
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 9fc5db8c (ceph): ReplicatedPG::op_applied: update last_update_applied iff !aborted
- scrub state and last_update_applied will have been reset during
the interval change.
Signed-off-by: Samuel Just <sam... - 05:15 PM Revision 7f2354c7 (ceph): doc/scripts/gen_state_diagram.py: make parser a bit more forgiving
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 31db8ed0 (ceph): OSD::activate_map: don't publish map until pgs in deleted pools have be...
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 7e26d6df (ceph): PG: C_PG_MarkUnfoundLost put pg in finish
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 5dc45f77 (ceph): PG: PG now store its own PGPool
- Otherwise, we need to syncronize access to the shared PGPool objects.
The wasted memory is probably preferable to syn... - 05:15 PM Revision 5c0e8b46 (ceph): OSD: bail out of do_recovery if no longer primary and active
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 3ca6359c (ceph): common/WorkQueue.h: add BatchWorkQueue
- Rather than dispatching one item at a time to process, etc,
BatchWorkQueue dispatches up to a configurable number of
... - 05:15 PM Revision d8a68e76 (ceph): OSD: do_(notifies|infos|queries) must now be passed a map
- This removes the need to call them from within the osd lock.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 05:15 PM Revision c1f2a802 (ceph): OSD: peering_wq is now a BatchWorkQueue
- process_peering_events now handles multiple pgs at once to better
batch up notifes, etc.
Signed-off-by: Samuel Just ... - 05:15 PM Revision 0ee3d87f (ceph): OSD: process_peering_event check for new map on each pg
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 9b182d20 (ceph): OSD: maybe_update_heartbeat_peers, don't print pg
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision c6db1b2e (ceph): PG: delay ops in do_request, not queue_op
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 1b558fba (ceph): OSD: write_info/log during process_peering_events, do_recovery
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 392df3b7 (ceph): Revert "osd: reset last_peering_interval on replica activate"
- This reverts commit 17114f266a336b6edd7e98975d494fdd487eec20.
- 05:15 PM Revision f9282e6c (ceph): Revert "osd: check against last_peering_reset in _activate_committed"
- This reverts commit 86aa07d7a91ac23074e76551c3a6db3a5736cffa.
- 05:15 PM Revision 442b5583 (ceph): PG: pass activate epoch with Activate event
- This allows us to pass into activate() in which epoch the
message triggering activation occurred allowing us mark
the... - 05:15 PM Revision 311a061e (ceph): OSD: move watch into OSDService
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision b200710b (ceph): OSD,PG: clean up pg removal
- PG opsequencers will be used for removing a pg. If the pg is recreated
before the removal is complete, we need the n... - 05:15 PM Revision e8d09d02 (ceph): PG,OSD: prevent pg from completing peering until deletion is complete
- hobject_t must now be globally unique in the filestore. Thus, if we
start creating objects in a pg before the remova... - 05:15 PM Revision 35949c54 (ceph): ReplicatedPG: explicitely block on not active for certain ops
- Ops and some subops need to wait for active to ensure correct ordering
with respect to peering operations.
Signed-of... - 05:15 PM Revision 2552a7f4 (ceph): OSD,PG: _share_map_outgoing must not require osd_lock
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 4fec85f2 (ceph): OSD: activate_map() in handle_osd_map only when active
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 040a22b6 (ceph): OSD: map_cache should contain const OSDMap
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 3dcce50e (ceph): OSD: only do_(notify|info|query) for up osd
- pg may have an older map and attempt to notify|info|query on a down
osd.
Signed-off-by: Samuel Just <sam.just@inktan... - 05:15 PM Revision a5bf3d71 (ceph): OSD: lock recovery_wq before debug output on finish_recovery_op
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 8079a489 (ceph): OSD,PG: clean up _get_or_create_pg and set interval based on msg
- Previously, we set last_peering_reset based on the epoch in which the pg
is created. We now pass the map from the qu... - 05:15 PM Revision 7c1dc90a (ceph): OSD: don't advance_pg() if pg is up-to-date
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision 73f5ce94 (ceph): OSD,PG: issue pg removals in line, remove remove_list
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision c7581b69 (ceph): CrushWrapper: rmaps don't need to be mutable
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:15 PM Revision a67a874b (ceph): CrushWrapper: add locking around crush_do_rule
- crush_do_rule uses a cache on the bucket objects.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 05:15 PM Revision b242c565 (ceph): OSD: on pg_removal, project_pg_history to get current interval
- First, we don't really want to remove the pg if we can use it. Second,
there might be messages in the pg peering que... - 05:14 PM Revision f6fc1b30 (ceph): OSD: remove superfluous pg get/put around enqueue_op
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:14 PM Revision b6bf5736 (ceph): ReplicatedPG: do not eval_repop if aborted
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:14 PM Revision 91355fb7 (ceph): ReplicatedPG: change ReplicatedPG debug output to match PG
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:14 PM Revision 3d32712e (ceph): OSD: don't assume pending pg removals have flushed
- _create_lock_pg might encounter a preexisting pg collection simply
because the removal transaction had not yet comple... - 05:14 PM Revision 90e3727e (ceph): OSD: do not lock osd during dequeue_op
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:14 PM Revision 10ec5bc5 (ceph): OSD: push_waiters is no longer used
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:14 PM Revision 14381b38 (ceph): OSD: get map read lock during queue_want_up_thru
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:14 PM Revision 492e6351 (ceph): OSD: do not drop osd_lock in handle_osd_map
- PGs have their map updates done in a different thread. Thus, we no
longer need to grab the pg locks. activate_map n... - 05:14 PM Revision f68f52ce (ceph): OSD: queue_want_up_thru in process_peering_event
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:14 PM Revision 502c0335 (ceph): PG, OSD: info_map shouldn't contain the MOSDPGInfo*
- Rather, we will just pass the same type as the noties.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 05:14 PM Revision b80b5005 (ceph): OSD,PG: Move pg accesible methods, objects to OSDService
- In order to clarify data structure locking, PGs will now access
OSDService rather the the OSD directly. Over time, m... - 05:14 PM Revision 33b985dc (ceph): OSD,PG: added helper methods for creating and dispatching RecoveryCtxs
- This is simpler than having to update all of the RecoveryCtx users
whenever we change the types in RecoveryCtx.
Sign... - 05:14 PM Revision 9a4a9b9a (ceph): PG: flush ops by the end of peering without osr.flush
- Rather than explicitely flushing the filestore, send a noop through the
filestore at the beginning of peering and, at... - 05:14 PM Revision ddef446d (ceph): OSD,PG: Move Op,SubOp queueing into PG
- PG now handles delaying/discarding messages since pg map epoch may not
be the same as the OSD map.
Signed-off-by: Sa... - 05:14 PM Revision bbd8af02 (ceph): osd/: Make pg osdmap be independent of osd, other pg maps
- This will allow handle_osd_map to not stop other work queues.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 05:14 PM Revision 12e22b3d (ceph): OSD,PG: handle pg map advance in process_peering_event
- The pg map will now be advanced in process_peering_event (in advance_pg)
to allow handle_osd_map to not grab pg locks... - 05:14 PM Revision c7e34951 (ceph): PG: include info and query by value in peering events
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:14 PM Revision 65abfc07 (ceph): OSD: initialize pgs in get_or_create_pg via handle_create
- Previously, pgs were initialized via Info/Log/etc. Since the event
which triggered the pg creation may now be queued... - 05:14 PM Revision b081bd4c (ceph): PG: CephPeeringEvents can now be descriptively printed
- The CephPeeringEvt constructor is now templated to allow
storing a description string for debugging.
Signed-off-by: ... - 05:14 PM Revision e10e81c0 (ceph): PG: compound messages must carry epoch_sent for each part
- Query and Notify messages include logical messages from multiple
pgs. Each logical message (pg_query_t and pg_notify... - 05:14 PM Revision fff0874c (ceph): PG: use osd->requeue_ops for ops, pg->queue_for_peering to requeue pg
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:14 PM Revision 64b71c69 (ceph): OSD: check for deleting in process_peering_event
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:14 PM Revision b5078bb2 (ceph): PG,OSD: add OSD::queue_for_op, use in PG::queue_op
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:14 PM Revision b0cb96bf (ceph): PG,OSD: fix op checking in pg, take_waiters during ActMap
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:14 PM Revision 18fec69a (ceph): OSD,PG::scrub() move pg->put() into queue process
- This clarifies ownership of the pg reference.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 05:14 PM Revision 1ffd190e (ceph): PG: CephPeeringEvt
- CephPeeringEvt is now the supertype for all peering state machine
events. This will allow us to generalize checking ... - 05:14 PM Revision 3691e3ca (ceph): PG: Move handle_* methods to PG
- PG now calls handle_event in RecoveryState.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 05:14 PM Revision 7c414c5d (ceph): OSD: Remove handle_pg_missing, MOSDPGMissing no longer used
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 05:14 PM Revision d0158230 (ceph): OSD,PG: push message checking to pg
- old_peering_evt now checks CephPeeringEvts generically in
PG::handle_peering_event().
Signed-off-by: Samuel Just <sa... - 05:14 PM Revision 6922f9cf (ceph): osd/: move history update from handle_pg_query into pg
- Previously, replica history was updated in OSD::handle_pg_query.
Updating the history is now handled in the pg state ... - 05:14 PM Revision 36d1381a (ceph): PG: use intrusive_ptr in CephPeeringEvt
- Properly disposing of the event_base member of CephPeeringEvt
requires use of intrusive_ptr.
Signed-off-by: Samuel J... - 05:14 PM Revision 33bcbb33 (ceph): PG: process peering events in a queue
- Peering events are now queued via queue_peering_event in the
peering_queue.
Signed-off-by: Samuel Just <sam.just@ink... - 05:08 PM Linux kernel client Bug #2523 (Resolved): xfs: xfs_iolock_reclaimable
- patches from hch fix this up. added them to testing branch.
- 04:18 PM rbd Bug #2488 (Can't reproduce): rbd: EIO from rbd map
- 04:18 PM Bug #2693 (Resolved): osd/ReplicatedPG.cc: 4293: FAILED assert(info.last_update <= active_rep_scr...
- 04:18 PM Bug #2453 (Resolved): osd/OSD.h: 840: FAILED assert(last_scrub_pg.count(p))
- 04:13 PM Messengers Bug #2569 (Resolved): msgr: connect_rank crash
- 04:12 PM devops Feature #2698: crowbar: Guide for using "front" network
- I verified that this causes no trouble before crowbar is installed and that eth1 does come up automatically after reb...
- 03:11 PM rgw Feature #2735 (Resolved): rgw: support response-* request params in GET obj
- 03:10 PM rgw Bug #2734 (Resolved): rgw: fails to authenticate preauthenticated requests with sub resource
- 02:32 PM Revision ea11c7f9 (ceph): Allow URL-safe base64 cephx keys to be decoded.
- In these cases + and / are replaced by - and _ to prevent problems when using
the base64 strings in URLs.
Signed-off... - 02:11 PM Feature #2733 (Resolved): osd: fadvise replica data don't use
- This should help quite a bit with cache pressure.
- 01:56 PM Feature #2485 (Resolved): crush: validate hash function
- 01:29 PM Feature #2730: [Also for argonaut] OSD dump detailed info about in progress ops
- We can also keep data about the last N slow requests on the OSD to allow easier debugging.
- 01:16 PM Feature #2730 (Resolved): [Also for argonaut] OSD dump detailed info about in progress ops
- syntax should be something along the lines of:
ceph tell osd <num> query_ops
Result should be a json formatted ... - 01:20 PM Bug #2711 (Resolved): chef does not install apache2/fastcgi on plana23
- The apt-get update command I added said "apt-key update", which isn't the same at all. Fixed in
commit:6d351b0b2... - 01:18 PM Feature #2732 (Resolved): Idempotency tester
- Add proper support for:
* omap
* xattr
* collection_rename - 01:17 PM Cleanup #2731 (Closed): ceph tell osd <num> should be ceph osd <subcommand> to match ceph pg <sub...
- 11:41 AM Feature #2727: filestore: add split
- On second thought, that would be hard to encode into a transaction, it'll probably just take a
[(hash_prefix, bits... - 11:06 AM Feature #2727 (Resolved): filestore: add split
- Add split functionality to filestore. The existing collection structure should be already in place.
Interface coul... - 11:20 AM Documentation #2729 (Resolved): doc: OSD internals
- Broad overview of OSD internals:
* Threading/wq model
* Message handling
* Message ordering (wait for map, pg wait... - 11:18 AM Feature #2728 (Resolved): OSD: handle split
- OSD message handling needs to handle messages for pgs between the map epoch creating them and the actual split (shoul...
- 11:17 AM rbd Documentation #2670 (In Progress): Docs shouldn't direct users to echo to /sys/bus/rbd for normal...
- 11:06 AM Bug #2725 (Duplicate): filestore: add split
- 11:04 AM Bug #2725 (Duplicate): filestore: add split
- Add split functionality to filestore. The existing collection structure should be already in place.
Interface cou... - 11:05 AM rbd Feature #2609 (In Progress): librbd: new image name -> image head indirection
- 11:05 AM rbd Feature #2609 (Resolved): librbd: new image name -> image head indirection
- 11:04 AM rbd Feature #2726 (Resolved): krbd: clean up bio_pair leak/whatever
- 11:03 AM Bug #2721: Ceph status does not work in 0.48 even if it is still documented
- I have restarted ceph mon with invoke-rc.d ceph restart mon and now it works! However I am 100% sure that I did it af...
- 10:59 AM Bug #2721: Ceph status does not work in 0.48 even if it is still documented
- you can just restart, or to verify in the future, 'ceph --admin-daemon /var/run/ceph/ceph-mon.a.asok version' (adjust...
- 10:59 AM Bug #2721: Ceph status does not work in 0.48 even if it is still documented
- Oh! The monitor is still running the old version.
- 10:57 AM Bug #2721: Ceph status does not work in 0.48 even if it is still documented
- ...
- 10:55 AM Bug #2721: Ceph status does not work in 0.48 even if it is still documented
- Weird! Two things:
- does 'ceph status' work? (this is identical to -s now)
- can you try with commit:b53cdb9... - 10:45 AM Bug #2721: Ceph status does not work in 0.48 even if it is still documented
- # ceph -v
ceph version 0.48argonaut (commit:c2b20ca74249892c8e5e40c12aa14446a2bf2030) - 10:44 AM Bug #2721: Ceph status does not work in 0.48 even if it is still documented
- can you include 'ceph -v' output? this works for me......
- 10:05 AM Bug #2721 (Resolved): Ceph status does not work in 0.48 even if it is still documented
- ...
- 10:22 AM rbd Feature #2724 (Resolved): rbd: add protect/unprotect command
- See http://ceph.com/docs/master/dev/rbd-layering/#protection
- 10:12 AM rbd Feature #2723 (Resolved): librbd: protect/unprotect as appropiate during cloning
- See http://ceph.com/docs/master/dev/rbd-layering/#protection
- 10:10 AM rbd Feature #2722 (Resolved): cls_rbd: add class methods to get/set protected status
- The possible settings are: protected, unprotected, and protecting. See http://ceph.com/docs/master/dev/rbd-layering/ ...
- 10:02 AM rbd Feature #2720 (Resolved): rbd: add children command
- This should list all direct children of a given snapshot.
- 10:01 AM rbd Feature #2719 (Resolved): librbd: provide functions for listing parents and their children
- Wrap the class methods for listing parents and children of parents.
- 09:57 AM rbd Feature #2718 (Resolved): librbd: map parent -> child in a per-pool rbd_children object when cloning
- 09:55 AM rbd Feature #2717 (Resolved): cls_rbd: add methods for maintaining mapping from parent to child images
- From http://ceph.com/docs/master/dev/rbd-layering/#cls-rbd:...
07/04/2012
- 10:23 PM Linux kernel client Bug #2716: crash when cluster goes down and new one comes up
- ...
- 10:21 PM Linux kernel client Bug #2716 (Resolved): crash when cluster goes down and new one comes up
- - vstart cluster
- mount uml
- do some stuff (dbench, control-c, sync)
- stop vstart cluster
- (waited a while)
... - 09:47 PM Revision 6dbf53e2 (ceph): nuke: nuke based on archive path
- Use path/config.yaml for targets, path/pid for pid to kill, and
path/owner for job owner. - 09:47 PM Revision 132dc006 (ceph): nuke: be more careful about kill; simplify
- If the archive dir is specified, make sure we are killing the right
process.
Also drop the kill_process helper; it's... - 09:47 PM Revision 2499bd3f (ceph): watch-suite: stupid script to watch teuth run progress
- 09:29 PM Revision 45fcca1f (ceph): valgrind: add strptime suppressions
- Precise's strptime triggers valgrind false positives.
Use ship_utilities to push the valgrind.supp file over, which ... - 09:24 PM rbd Bug #2715 (Resolved): krbd: spinlock wrong CPU
- ...
- 08:59 PM Revision 7fa85790 (ceph): osd: add missing formatter close_section() to scrub status
- Also add braces to make the open/close matchups easier to see. Broken
by f36617392710f9b3538bfd59d45fd72265993d57.
... - 07:47 PM Revision 12a1f623 (ceph): move other ffsb workloads to marginal suite
- 04:30 PM Revision c0b01cda (ceph): Merge branch 'stable'
- Conflicts:
src/test/cli/radosgw-admin/help.t - 04:21 PM Revision f67fe4e3 (ceph): librados: Bump the version to 0.48
- Signed-off-by: Wido den Hollander <wido@widodh.nl>
Signed-off-by: Sage Weil <sage@inktank.com> - 03:34 PM Feature #2714 (Resolved): teuthology: store monitor data in archives
- Sage suggested we might want to have teuthology archive the monitor's data directory, since that information is often...
- 02:52 PM Bug #2593: logmonitor: decode failure
- nope.
i wonder if we should make teuthology archive the mon data directory... that info is often useful, even for ... - 02:49 PM Bug #2675 (Resolved): osd: segfault during log trim
- 02:32 PM Revision bcfcf8ef (ceph): librados: add assert_version as an operation on an ObjectOperation
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 02:31 PM Bug #2712 (Resolved): osd: small write performance regression from 0.47.*
- Several reports on the ML about small writes going slower than before, generating 'slow request' warnings where previ...
- 02:29 PM Revision 39eaa230 (ceph): ReplicatedPG: do not set reply version to last_update
- The version should be oi.user_version as set above.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 02:27 PM Revision e6e36c0a (ceph): rgw: initialize fields of RGWObjEnt
- This fixes various valgrind warnings triggered by the s3test
test_object_create_unreadable.
Signed-off-by: Sage Weil... - 02:02 PM Bug #2711 (Resolved): chef does not install apache2/fastcgi on plana23
- i saw this on at least one other node as well. why? (this manifests itself has a 100-continue s3test failure in qa....
- 01:45 PM Linux kernel client Bug #2710 (Resolved): freeze from dbench in uml
- 01:16 PM Linux kernel client Bug #2710: freeze from dbench in uml
- this was a problem with 3df5c88d0d469c71c43f2379f6a375fc2d314eb7, fixed and re-pushed testing.
the fix f28dfe91f5f... - 11:32 AM Linux kernel client Bug #2710 (Resolved): freeze from dbench in uml
- Current testing and about 3 seconds of dbench 2 locks up
- 08:19 AM Feature #2709 (Resolved): teuthology: create xfs fs with large inodes
- 07:22 AM Linux kernel client Bug #2708 (Can't reproduce): spinlock lockup in queue_con, queue_work
- ...
- 12:39 AM Revision fb9d39d5 (ceph): move locktest to marginal suite
- This fails 1 in 10 times or something like that.
07/03/2012
- 11:49 PM Revision f6cdd852 (ceph): Merge remote-tracking branch 'gh/wip-crush'
- 11:24 PM Revision 35b9ec88 (ceph): rgw-admin: use correct modifier with strptime
- Bug #2658: used %I (12h) instead of %H (24h)
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 11:24 PM Revision da251fe8 (ceph): rgw: send both swift x-storage-token and x-auth-token
- older clients need x-storage-token, newer x-auth-token
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 11:23 PM Revision 4c19ecb9 (ceph): rgw: radosgw-admin date params now also accept time
- The date format now is "YYYY-MM-DD[ hh:mm:ss]". Got rid of
the --time param for the old ops log stuff.
Signed-off-by... - 11:10 PM Revision 6958aeb8 (ceph): rgw-admin: fix usage help
- s/show/trim
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 11:04 PM Revision e07b7113 (ceph): Added a debug message
- The debug message is to print the string that should be JSON.
This is to track a nightly run failure.
Signed-off-by:... - 10:36 PM Bug #2707 (Can't reproduce): mkcephfs failing on v0.48 "argonaut"
- Firstly, well done guys on achieving this version milestone. I successfully upgraded to the 0.48 format uneventfully ...
- 10:25 PM Revision ad97415e (ceph): ceph-disk-prepare: Partition and format OSD data disks automatically.
- Uses gdisk, as it seems to be the only tool that can automate GPT uuid
changes. Needs to run as root.
Adds Recommend... - 09:20 PM Revision a1696fe0 (ceph): doc: removed /srv/osd.$id.journal from ceph.conf example.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:16 PM Revision 8f646478 (ceph): CrushTester.cc: remove BOOST dependencies.
- remove calls to BOOST libraries for computing Chi-squared statistics and
producing discrete random variables with a g... - 09:14 PM Revision 7e23aad6 (ceph): doc: Updates to 5-minute quick start.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:07 PM Revision 83c043f8 (ceph): radosgw-admin: fix clit test
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:04 PM Revision ec0588e7 (ceph): Merge branch 'wip-config'
- 08:04 PM Revision c667f5d7 (ceph): lockdep: increase max locks
- Hit this limit with the rados api tests.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:49 PM Revision b99d11c4 (ceph): schedule_suite: use the sha1, not branch name
- Keep the entire suite run on the same commit. We were resolving the sha1,
but not using it. - 07:23 PM Revision f3c24517 (ceph): nuke - optionally kill the process hung
- Added a function kill_process to kill the process hung in the nightly runs.
It takes in pid as an optional argument.
... - 07:07 PM Revision 12ba580f (ceph): config: add unlocked version of get_my_sections; use it internally
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:51 PM Revision 56741581 (ceph): ceph: fix cli help test
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:48 PM Revision c11ca33b (ceph): Merge branch 'master' of github.com:ceph/ceph
- 06:48 PM Revision fc18cca0 (ceph): doc: Clean up of 5-minute quick start.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:30 PM Revision 151bf0ee (ceph): ReplicatedPG: remove faulty scrub assert in sub_op_modify_applied
- This assert assumed that all ops submitted before MOSDRepScrub was
submitted were processed by the time that MOSDRepS... - 06:30 PM Revision 8ade74b2 (ceph): ReplicatedPG: remove faulty scrub assert in sub_op_modify_applied
- This assert assumed that all ops submitted before MOSDRepScrub was
submitted were processed by the time that MOSDRepS... - 06:21 PM Revision 09dd8cad (ceph): doc: Updating Getting Started with 5-minute quick start.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:20 PM Revision 32833e88 (ceph): ceph: better usage
- Signed-off-by: Kyle Bader <kyle.bader@dreamhost.com>
- 06:18 PM Revision da24208d (ceph): Merge branch 'master' of github.com:ceph/ceph
- 06:17 PM Revision 8c95b5c8 (ceph): doc: restructuring quick start section.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:10 PM Revision 4bd7c05b (ceph): IoCtxImpl: pass objver pointer to aio_operate_read
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:45 PM RADOS Feature #2706 (Resolved): crush: update kernel code to decode tunables
- 04:44 PM RADOS Feature #2705 (Resolved): crush: graceful transition to new default tunables
- 04:44 PM RADOS Bug #2214 (Resolved): crush: pgs only mapped to 2 devices with replication level 3
- 04:44 PM RADOS Bug #2047 (Resolved): crush: with a rack->host->device hierarchy, several down devices are likely...
- 04:43 PM RADOS Bug #187 (Rejected): crush: high variance, latency for straw buckets
- 04:43 PM RADOS Feature #2422 (Resolved): crush: test that mapping result is uncorrelated
- 04:39 PM rgw Bug #2106: failed s3tests.functional.test_s3.test_100_continue
- recent logs from the nightly run: /a/teuthology-2012-07-03_00:00:09-regression-next-testing-basic/5054
- 04:34 PM CephFS Bug #1947: mds: SIGBUS during _mark_dirty
- Tamilarasi muthamizhan wrote:
> latest logs:
> /a/teuthology-2012-07-03_00:00:09-regression-next-testing-basic/5019... - 04:33 PM CephFS Bug #1947: mds: SIGBUS during _mark_dirty
- latest logs:
/a/teuthology-2012-07-03_00:00:09-regression-next-testing-basic/5019
config.yaml:
++++++++++++
k... - 04:24 PM Revision 4e774fbc (ceph): ceph-disk-prepare: Take fsid from config file.
- Closes: #2546.
Signed-off-by: Tommi Virtanen <tv@inktank.com> - 04:21 PM Revision cd0314d1 (ceph): config: remove bad argparse_flag argument in parse_option()
- This is wrong, and thankfully valgrind picks it up.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:20 PM Revision 67455c21 (ceph): debian: strip new ceph-mds package
- Reported-by: Amon Ott <a.ott@m-privacy.de>
Signed-off-by: Sage Weil <sage@inktank.com> - 03:53 PM devops Feature #2704 (Closed): sepia: Use ``names`` as resolver on plana, burnupi, vercoi
- 03:46 PM Revision 6bb19e74 (ceph): doc: Cleaned up rbd snapshots.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:45 PM Feature #2702 (Resolved): gitbuilder: sync each build as it completes
- 03:27 PM devops Feature #2549: ceph-disk-prepare: take fstype, mkfs and mount options from ceph.conf
- As of commit ad97415ef72b55934adfa5024fd9af8fd1f0f82d, this now needs mount options too.
- 03:26 PM devops Feature #2547 (Resolved): ceph-disk-prepare: handle partitioning and mkfs
- commit ad97415ef72b55934adfa5024fd9af8fd1f0f82d
Author: Tommi Virtanen <tv@inktank.com>
Date: 2012-07-03 15:24:26... - 03:20 PM Revision ad61bbd1 (ceph): config: fix lock recursion in get_val_from_conf_file()
- Introduce a private, already-locked version.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:15 PM Revision 7009c32e (ceph): config: fix recursive lock in parse_config_files()
- The _impl() helper is only called from parse_config_files(); don't retake
the lock.
Signed-off-by: Sage Weil <sage@i... - 02:24 PM rbd Bug #2457 (Resolved): libvirt: migration fails with rbd in 0.9.11 and 0.9.12
- Fixed by upstream libvirt commit 78290b1641e95304c862062ee0aca95395c5926c.
- 02:08 PM rbd Bug #2457: libvirt: migration fails with rbd in 0.9.11 and 0.9.12
- Fixed in 0.9.12-3(debian naming) and later. Also recently in-list reports told the same, so issue may be closed safely.
- 02:17 PM rgw Bug #2701 (Resolved): rgw: don't keep bucket info indexed by bucket_id
- 02:15 PM rbd Bug #2700 (Resolved): blkdeviotune method at libvirt doesn`t work on RBD volumes
- Since qemu implemented its own i/o limiting mechanism rather than cgroups, all block backends may be controlled over ...
- 01:46 PM Revision b53cdb97 (ceph): config: remove bad argparse_flag argument in parse_option()
- This is wrong, and thankfully valgrind picks it up.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:17 PM Messengers Bug #2569: msgr: connect_rank crash
- i've merged fix for this into master, commit:204bc594be1a6046d1b362693d086b49294c2a27 (with possible side-effects fro...
- 12:16 PM Bug #2682 (Resolved): config lockdep error (recursive lock?) in LibRadosAio.SimpleWritePP
- 10:48 AM devops Feature #2699 (Rejected): crowbar: change barclamp-glance to use rbd
- 10:38 AM devops Feature #2698: crowbar: Guide for using "front" network
- We need an easy way to drop a "dhclient eth1" upstart job into a crowbar server installation. Just a sudo tee /etc/in...
- 10:28 AM devops Feature #2698 (Closed): crowbar: Guide for using "front" network
- 10:26 AM devops Feature #2697 (In Progress): crowbar: ISO generation, reproducible in a cloud image vm
- 10:16 AM devops Feature #2697 (Resolved): crowbar: ISO generation, reproducible in a cloud image vm
- 10:12 AM devops Feature #2696 (Rejected): chef: Automated QA
- Use downburst vms on vercoi to automatically bring up ceph clusters, do basic RADOS/RBD functionality testing, tear d...
- 10:11 AM devops Feature #2695 (Closed): crowbar: Automated QA
- Use downburst vms on vercoi to automatically bring up ceph clusters, do basic RADOS/RBD functionality testing and Ope...
- 10:10 AM rgw Bug #2642 (Resolved): rgw: show/trim usage using also time (not just date)
- Done, commit:80a939a99db64f7802a4a3c1320316c91720f5d9
- 10:08 AM rgw Bug #2658 (Resolved): rgw-admin: usage show fails when specifying hour > 12
- Fixed, commit:c5d19b6df0bcb238e5e68732b4d252b06f2d9e56.
- 10:05 AM devops Feature #2584 (Resolved): sepia: provide networking, DHCP for dynamic virtual machines
- 10:05 AM devops Feature #2584: sepia: provide networking, DHCP for dynamic virtual machines
- Split the DNS part to #2694, this is already providing value to users.
- 09:59 AM devops Feature #2584: sepia: provide networking, DHCP for dynamic virtual machines
- Status update: missing DNS updates, all the strictly required components are there; vms attached to the front network...
- 10:04 AM devops Feature #2553: crowbar: open question: What's the correct way to add RBD support to the Nova barc...
- (Wrong ticket, ignore)
- 10:04 AM devops Feature #2694 (Closed): sepia: provide DNS for dynamic vms
- 09:24 AM devops Feature #2546 (Resolved): ceph-disk-prepare: take fsid from ceph.conf (support --cluster=name)
- commit 4e774fbcb38fd6883232b72352512a5f8e4a66e8
Author: Tommi Virtanen <tv@inktank.com>
Date: 2012-07-03 09:22:28... - 08:04 AM Bug #2693 (Resolved): osd/ReplicatedPG.cc: 4293: FAILED assert(info.last_update <= active_rep_scr...
- ...
- 04:24 AM Revision d347cc89 (ceph): Merge tag 'v0.48argonaut'
- v0.48argonaut
- 04:08 AM Revision 14ec7782 (ceph): client: improve dump_cache output
- Hunting #1737.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:20 AM Revision 8b462019 (ceph): doc: release notes for 0.48
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:18 AM Revision 562cad66 (ceph): doc: 'Configuring a Storage Cluster' -> 'Configuration'
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:54 AM Revision 030478e2 (ceph): Merge branch 'wip-msgr'
- 12:54 AM Revision b5287c19 (ceph): lockdep: enable in common_init
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:54 AM Revision 204bc594 (ceph): msgr: do not try to reconnect con with CLOSED pipe
- If we have a con with a closed pipe, drop the message. For lossless
sessions, the state will be STANDBY if we should... - 12:54 AM Revision 2429556a (ceph): msgr: fix pipe replacement assert
- We may replace an existing pipe in the STANDBY state if the previous
attempt failed during accept() (see previous pat... - 12:54 AM Revision 0dbc5416 (ceph): msgr: make D_CONNECT constant non-zero, fix ms_handle_connect() callback
- A while ago we inadvertantly broke ms_handle_connect() callbacks because
of a check for m being non-zero in the dispa... - 12:54 AM Revision 03445290 (ceph): msgr: move incoming queue to separate class
- This extricates the incoming queue and its funky relationship with
DispatchQueue from Pipe and moves it into Incoming... - 12:54 AM Revision 1f3a722e (ceph): msgr: move dispatch_entry into DispatchQueue class
- A bit cleaner.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:54 AM Revision b7007a15 (ceph): msgr: preserve incoming message queue when replacing pipes
- If we replace an existing pipe with a new one, move the incoming queue
of messages that have not yet been dispatched ... - 12:54 AM Revision 5dfd2a51 (ceph): msgr: choose incoming connection if ours is STANDBY
- If the connect_seq matches, but our existing connection is in STANDBY, take
the incoming one. Otherwise, the other e... - 12:54 AM Revision f7d4e397 (ceph): msgr: restart_queue when replacing existing pipe and taking over the queue
- The queue may have been previously stopped (by discard_queue()), and needs
to be restarted.
Fixes consistent failure... - 12:53 AM Revision e6ad6d25 (ceph): msgr: move to STANDBY if we replace during accept and then fail
- If we replace an existing pipe during accept() and then fail, move to
STANDBY so that our connection state (connect_s...
07/02/2012
- 11:06 PM Revision b5098b38 (ceph): ceph.spec.in: Change license of base package to GPL and use SPDX format
- LGPLv2 in spec file is not correct, because some of the included
packages/binaries are GPLv2. For example:
src/moun... - 11:06 PM Revision c2b20ca7 (ceph): v0.48argonaut
- 11:05 PM Revision a1fe5892 (ceph): mon: initialize quorum_features
- This could cause us to incorrectly encode new features into the monstore
that an old mon won't understand.
This is o... - 09:25 PM Feature #2692 (Resolved): stable testing debian repos
- 09:18 PM Revision f2d37c52 (ceph): librbd: handle NULL old_format pointer in detect_format()'s logging
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 09:18 PM Revision 6f096b6c (ceph): librbd: use new class methods to access rbd_directory
- Since we only use the new interface with new format images,
old clients won't be able to list them.
Signed-off-by: J... - 09:18 PM Revision 0ad14c95 (ceph): qa: add rbd command rename tests
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 09:18 PM Revision 288bde3f (ceph): qa: restructure rbd cli tests
- Move tests into functions and remove all images at the end of each.
Signed-off-by: Josh Durgin <josh.durgin@inktank.... - 09:18 PM Revision aa3255b8 (ceph): qa: add tests for rbd ls with old and new formats
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 09:18 PM Revision 1c096a80 (ceph): qa: run rbd tests against old and new formats
- Now it's not the caller's responsibility to specify the format,
and we can eliminate a job from the qa suite.
Signed... - 09:18 PM Revision d04b2fb7 (ceph): cls_rbd_client: check return code of operate
- This lets us get a more useful error, like -ENOENT, instead
of a failure to decode the empty output buffer.
Signed-o... - 09:18 PM Revision d82a5026 (ceph): qa: add rbd remove tests
- These check that removing an image still works if an rbd rm
command was interrupted partway through.
Signed-off-by: ... - 09:08 PM Revision 9278e231 (ceph): smoke: add msgr failures
- 08:05 PM Revision 2628530e (ceph): doc: fixed --cap error and a few additional bits of cleanup.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:26 PM Revision b9414b6c (ceph): fewer hosts for mon tests
- 06:49 PM rbd Bug #2689 (In Progress): qemu iozone test hangs
- 02:51 PM rbd Bug #2689 (Resolved): qemu iozone test hangs
- ...
- 05:07 PM Bug #2691: osd/ReplicatedPG.cc: 5888: FAILED assert(latest->is_update())
- took down osd.2 and osd.3 with same crash. coredumps are on the hosts..
- 05:06 PM Bug #2691 (Won't Fix): osd/ReplicatedPG.cc: 5888: FAILED assert(latest->is_update())
- ...
- 04:51 PM Revision 2472034c (ceph): OSD::do_command: unlock pg only if we had it
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:49 PM Revision 841451f2 (ceph): MOSDSubOp: set hobject_incorrect_pool in decode_payload
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:40 PM Bug #2690 (Won't Fix): mon: persist quorum features
- currently the non-leaders do not know the quorum features, and encode everything with a minimal (0) feature set.
... - 03:55 PM Revision b91becad (ceph): doc: Added sudo and cleaner instruction for unmap.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:44 PM Revision 38aa344d (ceph): ceph: fix valgrind error check
- grep all the logs, not the dir... doh!
- 03:35 PM Revision f16a9c46 (ceph): doc: updated usage on RBD kernel object commands.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:07 PM Revision 82abe00e (ceph): Merge pull request #15 from fghaas/wip-rgw-doc
- radosgw documentation improvements
- 03:03 PM Revision e1a385bb (ceph): Merge pull request #17 from fghaas/rgw-manpage
- doc: drop mention of MDS capabilities from radosgw man page
- 02:54 PM Revision e1860134 (ceph): doc: drop mention of MDS capabilities from radosgw man page
- Signed-off-by: Florian Haas <florian@hastexo.com>
- 02:26 PM Linux kernel client Bug #2688 (Duplicate): lockup on ffsb + thrashing
- ...
- 02:10 PM Revision deceb709 (ceph): filestore: initialize m_filestore_do_dump
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:54 PM Bug #2687: FileStore crashes when "osd_journal_size" is larger than the filesystem
- for files, i think the right approach is to fallocate(), which will reserve the space. we shouldn't have to look at ...
- 12:47 PM Bug #2687 (Resolved): FileStore crashes when "osd_journal_size" is larger than the filesystem
- See: http://permalink.gmane.org/gmane.comp.file-systems.ceph.devel/7282
If a user (on tmpfs, in this case) specifies... - 12:49 PM Bug #2476: osd: watch timeout depends on operations to an object
- fix qa/workunits/rbd/copy.sh when this is fixed !!!
- 12:36 PM rbd Feature #2556: rbd tool: break image locks
- The current progress in is wip-rbd-locking. Still needs tests and docs, plus a small cleanup as noted on github.
- 12:32 PM rbd Feature #2686 (Resolved): rbd: let users specify a usage for shared locks
- If existing lockers have the same usage, the lock succeeds. Otherwise, it fails. This could let you use locks with e....
- 11:28 AM rbd Feature #2685 (Rejected): Support QEMU migration with caching enabled
- This is a libvirt problem, it's not related to qemu at all. I already looked into and tested whether qemu was doing f...
- 11:21 AM rbd Feature #2685 (Rejected): Support QEMU migration with caching enabled
- See http://permalink.gmane.org/gmane.comp.file-systems.ceph.devel/7524
Apparently newer versions of QEMU refuse to... - 09:44 AM Documentation #2684 (Won't Fix): doc: ceph and all daemons take --show-config
- Quoting Sage:
For future reference, you can get a dump of all these values with
ceph-osd -i 123 --show-... - 09:30 AM Bug #2593: logmonitor: decode failure
- Do we know if the log in question actually existed on disk or not?
- 07:28 AM Bug #2593: logmonitor: decode failure
- saw this again on next:...
- 07:37 AM Bug #2683: ceph-fuse: crash during fsstress
- ...
- 07:31 AM Bug #2022 (Need More Info): osd: misdirectect request
- apparently there is a different cause for this:...
- 05:57 AM Subtask #2621 (In Progress): mon: Single-Paxos: synchronize the MonitorDBStore of oblivious monitor
07/01/2012
- 09:46 PM Feature #2651: mon: race calling tick() when doing slurping
- making this a cleanup so that it stops confusing me :)
- 09:27 PM Revision 96ccb060 (ceph): add rbd_xfstests to kernel suite
- 08:57 PM Bug #2683 (Can't reproduce): ceph-fuse: crash during fsstress
- ...
- 07:48 PM Bug #2682 (Resolved): config lockdep error (recursive lock?) in LibRadosAio.SimpleWritePP
- ...
- 03:06 PM CephFS Bug #2681: client: got push without mds session
- this was with 'ms inject socket failure = 200'
- 03:06 PM CephFS Bug #2681 (Resolved): client: got push without mds session
- ...
- 02:41 PM Bug #2599 (Can't reproduce): osd: crash in ReplicatedPG::C_OSD_OndiskWriteUnlock::finish
- chalking this up to the bugs in next a couple weeks back
- 09:22 AM Feature #2680 (Resolved): osd: report backfill progress via query
- ...
- 07:09 AM CephFS Bug #2679 (Can't reproduce): POSIX file lock not released on process termination
- I obtained a POSIX file lock with the following code:
> --- snip ---
>
> ...
> std::string x = "/tmp/ceph_mount... - 04:45 AM Revision 31ad2639 (ceph): doc: add design doc for rbd layering
- I'm still not sure about the names for the command line
operations, but they can be changed later if better ones
come...
06/30/2012
- 10:52 PM rbd Documentation #2670: Docs shouldn't direct users to echo to /sys/bus/rbd for normal use
- 10:51 PM rbd Feature #2279 (Resolved): rbd: trivial layering design doc
- 05:31 PM Revision 398a229c (ceph): filestore: set min flush size
- If a write is smaller than some threshold, do not bother to flush it; let
the fs do that (efficiently, we hope) at co... - 11:34 AM Bug #2675: osd: segfault during log trim
- and ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2012-06-28_19:00:12-regression-master-testing-gcov/3450
- 02:56 AM Revision 0810ab6d (ceph): osdmap: check new pool name on rename
- Ensure the new pool name doesn't already exist, both in the current and
project map.
Signed-off-by: Sage Weil <sage@... - 02:54 AM Revision 5a935509 (ceph): osd: handle pool name changes properly
- * Remove the old name from the name->id map.
Fixes: #2676
Signed-off-by: Sage Weil <sage@inktank.com>
06/29/2012
- 11:38 PM Revision d15385b0 (ceph): CrushTester: add Monte Carlo generator to more accurately simulate a
- CRUSH mapping using a RNG
Signed-off-by: caleb miles <caleb.miles@inktank.com> - 11:37 PM Revision 5de9af55 (ceph): crush: style changes
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 10:49 PM Revision cc4955a5 (ceph): PG: reset_recovery_pointers in activate if missing is empty
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:25 PM Revision 657e86c5 (ceph): vstart.sh: don't clobber keyring if not -n
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 09:51 PM Revision a8d7fd95 (ceph): mon: 'osd pool rename <oldname> <newname>'
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:44 PM Bug #2675: osd: segfault during log trim
- and ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2012-06-28_19:00:12-regression-master-testing-gcov/3441...
- 03:39 PM Bug #2675: osd: segfault during log trim
- and ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2012-06-28_19:00:12-regression-master-testing-gcov/3435
- 03:37 PM Bug #2675: osd: segfault during log trim
- and ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2012-06-28_19:00:12-regression-master-testing-gcov/3437
- 03:33 PM Bug #2675: osd: segfault during log trim
- also:...
- 03:30 PM Bug #2675 (Resolved): osd: segfault during log trim
- ...
- 09:22 PM Revision 02f1b0a6 (ceph): doc: document new 'osd crush move ...' command
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:16 PM Revision f5e3a675 (ceph): mon: fix 'osd crush move <item> <loc ...>'
- - fix arg count check
- avoid updating crush map if it is already correct
Signed-off-by: Sage Weil <sage@inktank.com> - 09:02 PM Feature #2471 (Resolved): osd: add prefix match to OSDCaps
- 09:00 PM Feature #2678 (Rejected): osd, objecter: redirect misdirected requests
- Generic mechanism to refer the client to the correct osd when they misdirect their requests. This will allow the clu...
- 08:59 PM Bug #2676 (Resolved): mon: cannot create pool with old renamed name
- commit:5a9355091296121823156de7d3160de45328a0cc
- 04:46 PM Bug #2676 (Resolved): mon: cannot create pool with old renamed name
- renaming a pool name, and then trying to create a new pool with the old name fails.
- 07:36 PM Revision e89dec78 (ceph): Merge branch 'master' of github.com:ceph/teuthology
- 07:36 PM Revision 2e5853f4 (ceph): Now using daemon-helper
- Signed-off-by: Mark Nelson <nhm@clusterfaq.org>
- 07:34 PM Revision 8d53965a (ceph): Merge branch 'wip-crushwrapper2'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 07:33 PM Revision 5e454bbd (ceph): mon: add 'osd crush move <name> <loc ...>' command
- Move an existing bucket to a new position in the hierarchy.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:32 PM Revision a2d0cff1 (ceph): crush: add move_bucket() method
- Move an existing bucket to a new location in the hierarchy.
Signed-off-by: Caleb Miles <caselim@gmail.com> - 07:32 PM Revision d22529d1 (ceph): crush: get_loc -> get_immediate_parent
- Signed-off-by: Caleb Miles <caselim@gmail.com>
- 07:27 PM rbd Bug #2677 (Resolved): librbd: create does not clean up well
- A create that fails part way through does not remove objects it created or undo modifications it does, for example ad...
- 07:23 PM rbd Feature #2279 (Fix Under Review): rbd: trivial layering design doc
- See wip-rbd-layering-doc
- 06:08 PM Revision d7c18c13 (ceph): PG::merge_old_entry: handle clone prior_version case
- A clone can have a prior_version after log_tail and still not have
a corresponding log entry since the prior_version ... - 06:06 PM Revision b907c881 (ceph): ReplicatedPG: adjust log.complete_to based on rmissing
- log.complete_to can actually move backwards due to objects
missing because of divergent entries.
Signed-off-by: Samu... - 06:05 PM Revision 143afcf9 (ceph): ReplicatedPG: clear peer_(missing|log)_requested in check_recovery_sources
- Otherwise, we might fail to re-request the information from a
previously down osd.
Signed-off-by: Samuel Just <sam.j... - 06:02 PM Revision 3321700a (ceph): qemu_iozone: use a larger image
- The default is not large enough.
- 05:41 PM Revision 090e5109 (ceph): PG: check_recovery_sources on each map
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 PM Revision 74b1468f (ceph): kernel suite
- 03:26 PM Messengers Bug #2569: msgr: connect_rank crash
- fix for this is in wip-msgr, still testing
- 02:16 PM RADOS Feature #2541 (Resolved): crush: move command to adjust non-leaf node position
- 12:54 PM Feature #2575 (Resolved): perf: 0.48 numbers
- 12:53 PM Feature #2582 (Resolved): set up chart.io + mysql (or equivalent) infrastructure for tracking perf
- 12:51 PM Feature #2577 (Resolved): teuthology: blktrace task
- 12:29 PM Subtask #2674: mon: Single-Paxos: mon commits suicide after remove&add
- Tried this on master. Although at first I triggered something else, the bottom line is that this works, and the monit...
- 12:14 PM Subtask #2674 (Rejected): mon: Single-Paxos: mon commits suicide after remove&add
- Yep. Makes sense. I was afraid this was cause by my changes.
Rejecting it then. - 11:30 AM Subtask #2674: mon: Single-Paxos: mon commits suicide after remove&add
- Yeah.. basically we're changing the mon's ip by removing and re-adding it, and the mon isn't smart enough to realize ...
- 11:12 AM Subtask #2674: mon: Single-Paxos: mon commits suicide after remove&add
- I believe this is intended behavior, note the last line:...
- 03:07 AM Subtask #2674 (Rejected): mon: Single-Paxos: mon commits suicide after remove&add
- Pre-conditions:
3 mons: a=127.0.0.1:6789 ; b=127.0.0.1:6790 ; c=127.0.0.1:6791
* remove 'c' with ./ceph mon rem... - 11:09 AM Bug #2646: mon:update_from_paxos: error parsing incremental update: buffer::end_of_buffer
- commit:840ae244499496d543d634713bdee7c7884ce527
The tick happened at the same time as slurping, which meant the di... - 10:54 AM Bug #2646 (Resolved): mon:update_from_paxos: error parsing incremental update: buffer::end_of_buffer
- 10:53 AM Bug #2264 (Can't reproduce): mon: failed assert in bump_epoch
- 06:19 AM Bug #2618: error: unable to open OSD superblock
- Thanks, but that didn't help.
I did notice that drives get mounted a little weird.
Don't know if that's a problem... - 05:50 AM Revision c3a02ea0 (ceph): doc: radosgw: further simplify Apache rewrite rule
- Sufficient to just pass the query string, drop params.
Signed-off-by: Florian Haas <florian@hastexo.com> - 05:25 AM Revision fb4ce538 (ceph): Merge pull request #16 from fghaas/doc-osd
- doc: document osd tell bench
06/28/2012
- 10:06 PM Bug #2664 (Resolved): osd: extra attr _path, extra attr snapset from scrub
- 07:34 PM Revision 76c657e3 (ceph): cls_rbd: add methods for dealing with rbd_directory objects
- These hide the structure of the directory from clients, and provide
mappings from id to name and name to id. These ma... - 07:33 PM Revision 5ae6e71f (ceph): cls_rbd: add {get,set}_id methods
- These will be used on a new rbd id object to provide a level of
indirection so that header objects don't need to move... - 07:33 PM Revision a1d477b9 (ceph): librbd: add indirection between name and header object
- This adds a new rbd_id.$name object that contains the id of an image.
Rename the header in new-format images to rbd_... - 07:33 PM Revision 41107078 (ceph): cls_rbd: use already defined local var instead of constant
- This occurrence was meant to be replaced in the original commit.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 07:33 PM Revision de62c4c4 (ceph): objclass: add create method
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 07:07 PM Revision 0a6ee694 (ceph): doc: document osd tell bench
- Signed-off-by: Florian Haas <florian@hastexo.com>
- 06:41 PM Revision 147114da (ceph): doc: minor edits.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:28 PM Revision 15ebf202 (ceph): rest-bench: mark request as complete later
- We marked a request as complete in the callback, however
it might be that we're still inside S3_runall_request_contex... - 06:27 PM Revision 5c23d357 (ceph): buffer.h: fix operator> and operator>= increment error
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:14 PM Revision f81feade (ceph): schedule_suite.sh: drop -x
- 06:14 PM Revision c6b2e93d (ceph): add cleanup-user.sh script
- big hammer, use with care
- 04:53 PM Revision 335b918d (ceph): DBObjectMap: clones must inherit spos from parent
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:53 PM Revision cc1da958 (ceph): filestore: sync object_map object in lfn_remove when nlink > 1
- In the following sequence:
1) create (a, 1)
2) setattr (a, 1)
3) link (a, 1), (b, 1)
4) remove (a, 1)
If we play 1-... - 04:47 PM Revision 8c453cce (ceph): cleaned up commented code
- Signed-off-by: Mark Nelson <nhm@clusterfaq.org>
- 11:29 AM Bug #2673 (Resolved): ReplicatedPG::prepare_transaction: don't crash on empty ops
- 11:26 AM Cleanup #2672 (Rejected): PG::find_best_info cleanup
- see 253033cd720db86e7c8372fd4184de7d4c43bce2
- 11:26 AM Cleanup #2671 (Resolved): buffer.h: do efficient buffer comparisons
- 10:15 AM rbd Documentation #2670 (Resolved): Docs shouldn't direct users to echo to /sys/bus/rbd for normal use
- A naive user looking for "rbd map" will instead find this:
http://ceph.com/docs/master/rbd/rados-rbd-cmds/
with... - 10:04 AM Linux kernel client Bug #2260: libceph: null pointer dereference at try_write+0x638+0xfb0
- Lots of work on the messenger client, but still not completely
clear this particular bug is fixed. There are a few ... - 09:42 AM Linux kernel client Bug #147: lockdep: possible irq lock inversion dependency w/ osdc->request_mutex and con->mutex
- I suppose this really ought to get fixed at some point.
For now, it looks like Sage has implemented a workaround
th... - 09:41 AM rbd Bug #1070: krbd: ^C doesn't work
- No progress on this. None expected unless it gets
reprioritized and planned. - 09:40 AM Linux kernel client Feature #1699: debug symbols in autobuilt (sepia) kernels
- No progress on this. I have a vague memory that someone
else might have looked at this problem a while back (Dan?).... - 09:39 AM Feature #2127: Save kernel core dumps on all of our test machines
- My work on this was pretty much complete a few months ago.
It included a shell script that leverages Ubuntu kdump
... - 09:32 AM Linux kernel client Bug #2261 (Can't reproduce): paging error in libceph after crashed osd comes back online
- the osd_client refcounting bug fix may explain this one, too... commit:0d47766f14211a73eaf54cab234db134ece79f49
an... - 09:16 AM Linux kernel client Bug #2261: paging error in libceph after crashed osd comes back online
- No progress on this.
There has been a lot of work on the messenger code since this bug was
reported. One change ... - 09:31 AM Linux kernel client Cleanup #2130: ceph: xattr: complete cleanups following review
- No progress on this, but I still have the patches. I'll
try to sneak them in as I'm working on RBD. I believe
the... - 09:29 AM Linux kernel client Cleanup #2131: ceph: xattr: use the generic kernel xattr code
- No progress on this. It should be put on our roadmap as a task
to complete, maybe within the next 6 months. - 09:12 AM Bug #2267 (Closed): Ceph client crashed after shutting down one mds and osd
- A recent fix supplied by Zheng Yan of Intel seems to have fixed
this problem, so I'm closing this bug.
rbd: C... - 09:05 AM rbd Feature #2326 (In Progress): krbd: use new class interfaces, new image format
- I've finally begun work on this, following some in-person discussion
with Josh, Dan, and Sage this week.
I will u... - 09:00 AM Linux kernel client Feature #2374: ceph-client: start laying the groundwork for Linux tracepoints
- No progress on this yet.
However, I got this e-mail from Jim Schutt shortly after creating
this bug, and just wan... - 08:44 AM Bug #2386: xfstests: failed #34
- I've been trying to find out whether this is still a problem or
if it was transient. But teuthology has had a strin... - 07:46 AM Revision 218dd5ad (ceph): radosgw Apache configuration: simplify rewrite rule
- Use a simpler RewriteRule as suggested here:
http://marc.info/?l=ceph-devel&m=133951986510085&w=2 - 07:43 AM Revision 5a06af78 (ceph): Fix example radosgw Apache configuration
- Follow RFC2606, use example.com everywhere.
- 07:41 AM Linux kernel client Bug #2424 (Resolved): ceph-client: messenger: badness in prepare_write_connect()
- This bug was fixed in May, by a small series of changes that
culminated in this one:
commit 3da54776e2c0385c3... - 07:37 AM Linux kernel client Cleanup #2432: ceph-client: messenger: refactor to simplify state model
- I had worked out on paper some notes about a longer-term state/event
model that could be used for the client messeng... - 07:33 AM Linux kernel client Cleanup #2432: ceph-client: messenger: refactor to simplify state model
- I worked on doing this for a good month but the job really isn't
complete. Nevertheless I think there was some prog... - 07:23 AM Linux kernel client Cleanup #2438: ceph-client: use BUG_ON() for null auth_client->ops pointers
- Touching all my bugs today. This one's a good idea but
very low priority. - 07:20 AM rbd Bug #2608: rbd: hung xfstest 270
- Just to summarize what I just added...
There are some recent XFS problems that might explain this,
irrespective o... - 07:16 AM rbd Bug #2608: rbd: hung xfstest 270
- I looked at this on Tuesday, and sent a note to Sage that should
have instead been put here. Here it is.
I w... - 07:18 AM Revision f969b59a (ceph): cls_rbd: fix signed-ness warning
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 07:18 AM Revision 6a5c1555 (ceph): objclass: remove unused variable from cls_cxx_map_get_vals
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 04:54 AM Feature #2668 (Resolved): Build linux-tools-common package for perf
- It'd be really nice if we built linux-tools-common with our gitbuilder kernels so we can install perf on our test box...
- 03:25 AM Revision 89492329 (ceph): debian: build with libnss instead of crypto++
- Signed-off-by: Laszlo Boszormenyi (GCS) <gcs@debian.hu>
- 03:25 AM Revision 0d9b558f (ceph): debian: arch linux-any
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:25 AM Revision 915f3210 (ceph): debian: move mount.ceph and cephfs into ceph-fs-common
- Based on patches from Laszlo Boszormenyi (GCS) <gcs@debian.hu>.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:25 AM Revision 9d6013e0 (ceph): debian: move metadata server into ceph-mds
- Also adjust the recommends and depends, so that libcephfs1 and ceph-fuse
hang off of ceph-mds instead of ceph.
Signe... - 12:49 AM Revision 9d7f0480 (ceph): doc/config-cluster/authentication: keyring default locations, simplify ...
- - keyrings have new default locations that everyone should use.
- the user key setup is vastly simplified if you use ... - 12:38 AM Revision 1a43c344 (ceph): Added blktrace task
- Signed-off-by: Mark Nelson <nhm@clusterfaq.org>
06/27/2012
- 11:28 PM Revision f3661739 (ceph): pg: report scrub status
- Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
- 11:28 PM Revision c94583e5 (ceph): pg: track who we are waiting for maps from
- Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
- 11:28 PM Revision ecd7ffe7 (ceph): pg: reduce scrub write lock window
- Wait for all replicas to construct the base scrub map before finalizing
the scrub and locking out writes.
Signed-off... - 11:20 PM Revision 16d55651 (ceph): mon: MonmapMonitor: Use default port when the specified on 'add' is zero
- Fixes a bug triggered by using the ceph tool to 'mon add' with a port set
to zero. We now default to the monitor's de... - 10:59 PM Revision 04e1c301 (ceph): rest-bench: mark request as complete later
- We marked a request as complete in the callback, however
it might be that we're still inside S3_runall_request_contex... - 08:48 PM Revision c5d19b6d (ceph): rgw-admin: use correct modifier with strptime
- Bug #2658: used %I (12h) instead of %H (24h)
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:10 PM Bug #2618: error: unable to open OSD superblock
- I noticed an issue in your ceph.conf - you have keyring = /etc/ceph/keyring.admin in the global section, and the osd ...
- 05:19 PM rbd Bug #2667 (Won't Fix): librbd: create_snap on a closed image segfaults
- I wrote silly code, and in reordering it, managed to attempt rbd_snap_create() on an
image that I had rbd_close()d. ... - 05:13 PM Feature #2651: mon: race calling tick() when doing slurping
- oops, stronger fix, yes!
- 05:13 PM Feature #2651 (Resolved): mon: race calling tick() when doing slurping
- 05:01 PM Feature #2661 (Resolved): mon: do not allow monitors to be added to the map with port 0
- Merged into dho and next. Thanks Joao!
- 11:25 AM Feature #2661 (Resolved): mon: do not allow monitors to be added to the map with port 0
- Last week, somebody used the "ceph mon add" command without specifying a port, and it defaulted to port 0. This cause...
- 04:48 PM Feature #2666 (Resolved): rados tool: copy pool
- A new operation to copy the entire content of a pool into a different pool. For each object we'd copy the locator, da...
- 04:04 PM rgw Bug #2665 (Resolved): rest-bench hangs periodically
- rest-bench seems to hang periodically with the following spit out the console on a regular basis:
plana83: 2012-06... - 04:04 PM Bug #2656 (Rejected): rados-bench hangs periodically
- 04:03 PM Bug #2656: rados-bench hangs periodically
- gah,
this is what I get for submitting bugs at the end of the day. You are correct, rest-bench. - 03:29 PM devops Feature #2587 (Resolved): sepia: isolated networking on vercoi (manual, a handful)
- 03:28 PM devops Feature #2587: sepia: isolated networking on vercoi (manual, a handful)
- Confirmed: isolated0..isolated9 work even if Crowbar wants to put VLANs in them. They pass between vercoi as packets ...
- 02:17 PM devops Feature #2662: crowbar: Make barclamp-ceph set mon initial members, monitor-secret, fsid
- More on where that snippet should live:
- for standalone chef deployment, we want the admin run something similar,... - 02:14 PM devops Feature #2662: crowbar: Make barclamp-ceph set mon initial members, monitor-secret, fsid
- This python snippet creates ceph keys in the right format (for now). Where it should live is still an open question.
... - 01:38 PM devops Feature #2662 (Resolved): crowbar: Make barclamp-ceph set mon initial members, monitor-secret, fsid
- Without this, multi-mon bring-up is racy.
At proposal save time, the barclamp should inspect the roles, and assign... - 02:12 PM Bug #2664: osd: extra attr _path, extra attr snapset from scrub
- full logs at metropolis:~sage/bug-2664
- 02:11 PM Bug #2664 (Resolved): osd: extra attr _path, extra attr snapset from scrub
- ...
- 02:10 PM Revision 17f433aa (ceph): OSD: disconnect_session_watches: handle race with watch disconnect
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Tested-by: Stefan Priebe ... - 01:43 PM devops Feature #2663 (Closed): crowbar: UI for setting generic ceph.conf values
- This needs to be some sort of an extensible list of key: value pairs.
Do we need to support sections too? Probably... - 01:17 PM devops Feature #2589 (Resolved): crowbar: Update barclamp-ceph for Essex, new ceph-cookbooks
- Tyler reported success as of b2c5d3307eef0ca44fd4b001136e9af043b322bd.
- 01:16 PM devops Feature #2588: downburst: multiple, configurable networks to libvirt
- For historical value: https://github.com/ceph/downburst/commit/de494eeefad0f0c72916d5dab8ba015b441a94f0
- 11:30 AM devops Feature #2588 (Resolved): downburst: multiple, configurable networks to libvirt
- 11:26 AM Linux kernel client Bug #2590: possible irq lock inversion dependency with con->mutex and osdc->request_mutex
- Recent log location: /a/teuthology-2012-06-27_00:00:07-regression-next-testing-basic/3076
2012-06-27T01:25:05.11... - 10:17 AM rbd Feature #2660 (New): qa: test resizing an rbd image while a vm has it open
- Make sure the resize is visible to the guest. This works with the virtio driver after doing e.g. 'echo 1 | sudo tee /...
- 10:02 AM Subtask #2659 (Can't reproduce): mon: Single-Paxos: ceph tool -w subscriptions not being updated
- how to reproduce:...
06/26/2012
- 07:30 PM Revision e34dfc3b (ceph): doc: removing old 'todo' configuration reference.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:24 PM Revision efb74a90 (ceph): doc: converted daemon references from nasty tables to lines.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:16 PM rgw Bug #2658 (Resolved): rgw-admin: usage show fails when specifying hour > 12
- using wrong modifier on for parsing it.
- 05:11 PM Bug #2453: osd/OSD.h: 840: FAILED assert(last_scrub_pg.count(p))
- possibly fixed by commit:0d8970fc813b33e7c6ba2484fbc43cce947d3f4d
- 04:31 PM CephFS Bug #2657 (Resolved): kclient: direct io write larger than 8MiB fails
- Writes larger than 8MiB get EFAULT, e.g.:...
- 03:28 PM Revision 4142ac44 (ceph): doc: a few minor tweaks to radosgw to cleanup navigation.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:21 PM Revision 0be26111 (ceph): doc: Published RADOS GW docs and install as is for now. Needs more work.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 02:13 PM Bug #2656: rados-bench hangs periodically
- rados-bench or rest-bench?
- 01:27 PM Bug #2656 (Rejected): rados-bench hangs periodically
- rados-bench seems to hang periodically with the following spit out the console on a regular basis:
plana83: 2012-0... - 01:45 PM Bug #2563 (Can't reproduce): leveldb corruption
- It looks like one of the leveldb store files was corrupted, possibly by the filesystem. It may be possible to recove...
- 09:36 AM Bug #2655 (Resolved): scrub slows writes more than it should
- 09:34 AM Subtask #2616 (Closed): mon: Single-Paxos: AuthMonitor: key_server has no entries
- 09:34 AM Subtask #2616 (Resolved): mon: Single-Paxos: AuthMonitor: key_server has no entries
- 09:33 AM Subtask #2620 (Closed): mon: Single-Paxos: MDSMonitor: MMDSBeacon from entity with insufficient p...
- Note: turns out this was the same bug as #2643
Had to do with the AuthMonitor losing some infos when reading versi... - 09:32 AM Subtask #2643 (Closed): mon: Single-Paxos: mds: Strange message behavior on peon
- Had to do with the AuthMonitor losing some infos when reading versions from the store.
This is fixed. - 09:01 AM Linux kernel client Bug #2523: xfs: xfs_iolock_reclaimable
- ...
- 07:05 AM Revision 93425734 (ceph): CrushTester.cc: removed last broken bits of obsolete method
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 07:02 AM Revision 6d551c17 (ceph): CrushTester.cc: removed obsolete method for collapsing a CRUSH map
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 06:58 AM Revision df7729e5 (ceph): CrushTester: eliminated compiler warning
- Signed-off-by: caleb miles <caselim@gmail.com>
- 06:39 AM Revision 88e31546 (ceph): radosgw-admin: improve man page
- * remove "OpenStack user" information (deprecated, should no
longer be used. No reason to keep mentioning it)
* fix... - 06:37 AM Revision 63b562f9 (ceph): doc: explain how to configure Ceph for radosgw
- * explain creating auth creds for radosgw
* explain Apache config for radosgw
* explain starting daemons for radosgw
... - 06:15 AM rbd Bug #2654 (Won't Fix): Stale rbd volume cannot be unmaped
- /dev/rbd0 exists in system but /dev/rbd/winnie-test/postgresql not...
- 06:14 AM Revision d82357df (ceph): Merge branch 'master' of github.com:ceph/ceph
- 04:21 AM Revision 1db84ddd (ceph): include ceph task in librbd collection
- 03:45 AM Revision 07029a4f (ceph): rgw: send both swift x-storage-token and x-auth-token
- older clients need x-storage-token, newer x-auth-token
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 03:45 AM Revision 80a939a9 (ceph): rgw: radosgw-admin date params now also accept time
- The date format now is "YYYY-MM-DD[ hh:mm:ss]". Got rid of
the --time param for the old ops log stuff.
Signed-off-by... - 03:45 AM Revision c87c83f3 (ceph): rgw-admin: fix usage help
- s/show/trim
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
06/25/2012
- 10:30 PM Revision aa89e6ab (ceph): move kclient_workunit_suites_ffsb to marginal suite
- until #1947 is fixed
- 10:20 PM Revision cc380dee (ceph): ignore DEADLOCK line inside lockdep splat
- 10:14 PM Revision 77fcf064 (ceph): upstart: fix regex
- Signed-off-by: Tommi Virtanen <tv@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 10:01 PM rbd Bug #2608: rbd: hung xfstest 270
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2012-06-23_00:00:02-regression-next-testing-basic/1471
m... - 09:56 PM Bug #2536 (Need More Info): librados crashed while getting stat of an object
- 09:56 PM Bug #2536: librados crashed while getting stat of an object
- Have you seen this problem since then? It looks like it could be due to racing with rados startup or shutdown...
- 09:45 PM Revision 0cd21ea1 (ceph): Merge branch 'next'
- 09:45 PM Revision 840ae244 (ceph): mon: don't tick the PaxosServices if we are currently slurping.
- They aren't prepared to deal with the on-disk state being inconsistent.
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:44 PM Revision ef6beec9 (ceph): objecter: do not feed session to op_submit()
- The linger_send() method was doing this, but it is problematic because the
new Op doesn't get its pgid or acting vect... - 09:41 PM Bug #2346 (Resolved): xfs filesystem on top of rbd volume corrupts
- No news is good news!
- 09:40 PM Bug #2602 (Resolved): osd: push failed because local copy is X
- 05:09 PM Messengers Bug #2569: msgr: connect_rank crash
- All three mon nodes and a client node on the second aging cluster died over the weekend (kernel and all). Looks like ...
- 10:25 AM Messengers Bug #2569: msgr: connect_rank crash
- Saw the following while debugging my aging test scripts. Seems to have happened when the mon was started. No core d...
- 03:33 PM Bug #2649: osd: log bound mismatch
- ...
- 03:31 PM CephFS Bug #1947: mds: SIGBUS during _mark_dirty
- moved test to marginal suite; move back to regression when this is resolved!
- 03:31 PM CephFS Bug #1947: mds: SIGBUS during _mark_dirty
- ubuntu@teuthology:/a/teuthology-2012-06-24_00:00:07-regression-next-testing-basic$ ...
- 03:28 PM Bug #2593: logmonitor: decode failure
- I wonder if this is also due to tick() colliding with slurping — the first one definitely could be (not sure about th...
- 03:27 PM Bug #2653 (Resolved): Web docs point to obsolete "fusermount" page
- The page http://ceph.com/docs/master/man/8/mount.ceph/ has a link at the bottome that points to "fusermount" descript...
- 03:21 PM Bug #2618: error: unable to open OSD superblock
- attaching my ceph.conf.
Can't get to IRC from work - I'll try in the evenings.
thanks - 02:54 PM rgw Bug #2652 (Resolved): Segmentation fault in rest-bench
- This happened while running rest-bench during aging tests on the burnupi cluster.
--
plana83: *** Caught signal... - 02:48 PM Bug #2022 (Resolved): osd: misdirectect request
- 02:40 PM Feature #2651 (Rejected): mon: race calling tick() when doing slurping
- Right now the monitor calls tick() on all the PaxosService implementations when it's doing slurping. This introduces ...
- 09:19 AM rgw Bug #2650 (Resolved): rgw: swift key creation overrides subuser access mask
- # radosgw-admin subuser create --uid=johndoe --subuser=johndoe:swift
--access=full
{ "user_id": "johndoe",
"rados...
06/24/2012
- 08:33 PM Revision 4e45d60f (ceph): ObjectStore::Transaction: initialize pool_override in all constructors
- use_pool_override and pool_override weren't initialized in these two
constructors.
Signed-off-by: Samuel Just <sam.j...
06/23/2012
- 05:34 PM Revision ff67210e (ceph): objecter: do not feed session to op_submit()
- The linger_send() method was doing this, but it is problematic because the
new Op doesn't get its pgid or acting vect... - 04:56 PM Bug #2649 (Resolved): osd: log bound mismatch
- ...
06/22/2012
- 07:14 PM Bug #2648 (Resolved): removing a monitor from the map while it's running causes a crash
- ...
- 05:27 PM Bug #2647 (Can't reproduce): osd: old request, waiting for subops
- primary:...
- 11:43 AM Bug #2618: error: unable to open OSD superblock
- John, can we see your ceph.conf file? If you have time, try chatting in #ceph on irc.oftc.net as well; perhaps we ca...
- 11:30 AM Bug #2646 (Resolved): mon:update_from_paxos: error parsing incremental update: buffer::end_of_buffer
- ...
- 08:17 AM Subtask #2645 (Rejected): mon: Single-Paxos: Could not decrypt ticket info (immediately after run...
- There was a lingering monitor still running, from a previous install.
Apparently, holding the wrong keys will lead... - 08:09 AM Subtask #2645 (Rejected): mon: Single-Paxos: Could not decrypt ticket info (immediately after run...
- ...
- 02:23 AM Revision 48e8e0a7 (ceph): Add script to create a vm image with extra packages
- 01:44 AM Revision 38f6a78c (ceph): Add a task to run a test against rbd inside of qemu.
- For now this task does not setup networking for the vm,
and simply runs an executable downloaded from a specified url... - 01:18 AM Revision 94a6ab8f (ceph): Add some tests inside qemu for the librbd suite
- 01:16 AM Revision a92306a4 (ceph): Move librbd tests to rbd suite
- This lets us generate jobs with different caching settings instead of
hardcoding them. - 12:24 AM Bug #2602: osd: push failed because local copy is X
- Hi Sage,
just updated to your wip_rolling_upgrade branch.
FileStore update worked ( 100GB => 30 minutes on XFS ) ... - 12:10 AM Revision c399d903 (ceph): mon: conditionally encode PGMap[::Incremental] with quorum features
- This allows a mon cluster to transition to the new encoding during a
rolling upgrade.
Signed-off-by: Sage Weil <sage... - 12:10 AM Revision de5b3236 (ceph): mon: conditionally encode mon features for remote mon
- The only time we encode these is when forwarding messages. Encoding using
the destination's feature set.
Signed-off... - 12:10 AM Revision 77d836c5 (ceph): mon: encoding new monmap using quorum feature set
- It is probably unlikely that someone will expand the mon cluster with a
mixed feature set, but we know the quorum fea... - 12:10 AM Revision 80649d08 (ceph): mon: note that monmap may be reencoded later
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:10 AM Revision 9fcc3dee (ceph): osd_types.cc: remove hobject_t decode asserts
- These asserts were useful for ensuring that pool is passed
in in the correct places, but they prevent the encoder
tes... - 12:10 AM Revision 2fe98163 (ceph): OSD,PG,ObjectStore: handle messages with old hobject_t encoding
- Messages that embed an hobject_t need to have the pool field fixed
on messages from old peers.
Signed-off-by: Samuel... - 12:10 AM Revision 2355b233 (ceph): mon: conditionally encode old monmap when peer lacks feature
- This allows a rolling upgrade from 0.47.2 to 0.48.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:10 AM Revision 06288a9d (ceph): mon: track intersection of quorum member features
- When we form a quorum, also note the intersection of the quorum members'
feature bits. This will inform decisions ab... - 12:10 AM Revision 0aaf7334 (ceph): mon: conditionally encode auth incremental with quorum feature bits
- If the quorum does not yet all have the MONENC feature, stick to the old
encoding.
It might be more polite to requir...
06/21/2012
- 09:33 PM Revision 03597ca6 (ceph): Check for machine args based on local, not ctx.machines
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 08:29 PM Revision ddf7e836 (ceph): doc: ceph osd crush add is now ceph osd crush set
- Mailing list thread: http://www.spinics.net/lists/ceph-devel/msg06199.html
Signed-off-by: Travis Rhoden <trhoden@gma... - 08:20 PM Revision 7773a93e (ceph): whitelist current lockdep warnings in syslog
- These are causing too much noise in the qa runs to leave, and #2617 is
sufficiently non-trivial to do this in the int... - 07:43 PM Revision 448f5b02 (ceph): logrotate: reload all upstart instances
- upstart doesn't let you wildcard all instances of a given job, so we
slog through initctl list output, and reload any... - 06:55 PM rbd Feature #2566 (Duplicate): teuthology: task to run rbd workunits in a vm
- Same as #1713.
- 06:53 PM rbd Feature #1713 (Resolved): teuthology: qemu tasks, tests
- Basic teuthology task is done in 38f6a78c71910a39b7f1890316c0a134ced8b0ec. Making a gitbuilder for qemu seems less im...
- 06:52 PM rbd Feature #2644 (Rejected): qa: gitbuilder for qemu
- This should build qemu with rbd support for regression testing new versions of qemu.
- 06:49 PM rbd Feature #2567 (Resolved): qa: add qemu+rbd jobs to qa suite
- Added in 94a6ab8ff3637f68c03261cf845b402d6bfa8e76
- 06:35 PM Revision 58db045a (ceph): docs: clarify example in radosgw-admin
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:17 PM Revision 990febd9 (ceph): mon: make pool deletion dne error code consistently ENOENT
- This matches the check in _prepare_remove_pool() now.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:17 PM Revision 7044192d (ceph): filestore: remove btrfs start/end transaction ioctl code
- This was an ill-conceived approach to getting atomic transactions out of
btrfs. It doesn't offer rollback, which mea... - 05:47 PM Revision 62a4ad66 (ceph): docs: update usage logging info
- added some text under radosgw, examples under radosgw-admin
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 04:30 PM Subtask #2643: mon: Single-Paxos: mds: Strange message behavior on peon
- This is what can be seen on the Leader:...
- 04:24 PM Subtask #2643 (Closed): mon: Single-Paxos: mds: Strange message behavior on peon
- Just for future reference.
When checking how things were going with the monitors, we noticed that the following sn... - 03:37 PM Subtask #2633: mon: Single-Paxos: ceph tool unable to connect to monitor
- Has something changed in the last five hours that you think fixed this?
- 03:28 PM Subtask #2633 (Closed): mon: Single-Paxos: ceph tool unable to connect to monitor
- It appears to be fixed.
The ceph tool is able to obtain the status from the monitors.
The 'watch' command doesn... - 10:11 AM Subtask #2633 (Closed): mon: Single-Paxos: ceph tool unable to connect to monitor
- This is what usually happens on the monitor side. Every now and then, the ceph tool is able to connect, but we haven'...
- 03:20 PM Revision a85a15fe (ceph): Merge remote-tracking branch 'gh/stable' into next
- 01:54 PM rgw Bug #2642 (Resolved): rgw: show/trim usage using also time (not just date)
- 01:42 PM Feature #2577 (In Progress): teuthology: blktrace task
- 01:41 PM Feature #2581 (Resolved): perf: investigate 0.47.2 precise vs 0.46 oneiric discrepancy
- 01:40 PM Feature #2576 (Resolved): perf: 0.48 on long-term clusters
- 01:17 PM Linux kernel client Bug #2302 (Can't reproduce): xfs: warning at mutex_remove_waiter
- 12:38 PM Bug #2550 (Resolved): logrotate: SIGHUP upstart jobs too, not just sysvinit
- 12:06 PM rbd Feature #2641 (Duplicate): qa: regression tests for rbd openstack volume driver
- This should include:
* booting a vm from an rbd device
* attaching/detaching an rbd device to a running guest
* ad... - 11:30 AM rbd Feature #2640 (Duplicate): qa: regression tests for rbd glance backend
- This should run against development versions of openstack to verify that the glance backend continues to work. Namely...
- 11:26 AM Bug #2042 (Duplicate): mon: crash in LogMonitor::update_from_paxos
- Indeed!
- 11:21 AM Bug #2042: mon: crash in LogMonitor::update_from_paxos
- Hrm, I think that this is duplicated by #2593?
- 11:16 AM Bug #2042 (Can't reproduce): mon: crash in LogMonitor::update_from_paxos
- 11:13 AM Cleanup #2623 (Resolved): filestore btrfs trans should be removed
- 11:07 AM Feature #1494 (Resolved): openstack: vm can boot off rbd
- This has been possible for a long time.
- 11:03 AM Bug #2638 (Resolved): mon: make pool ops idempotent
- for example, deleting a pool fails with ENOENT (or ENODATA :/) if the pool doesn't exist, but if we lose our mon sess...
- 11:02 AM rbd Feature #2637 (New): teuthology: task for running a vm using libvirt
- This should have similar semantics to the qemu task that runs qemu directly, but configure and run the vm via libvirt...
- 10:59 AM rbd Feature #2636 (New): qa: regression tests for qemu monitor commands
- Test attach/detach of rbd devices and snapshot operations executed directly by the qemu monitor. This is probably eas...
- 10:40 AM Bug #2602 (Need More Info): osd: push failed because local copy is X
- Hi Simon-
This looks like something that could be caused by the broken rolling osd upgrade support in the branch y... - 10:14 AM rgw Feature #2635 (New): benchmark for measuring rgw metadata operations
- We need to come up with a benchmark that will measure the following operations:
* Service:
1. List buckets
*... - 10:11 AM rbd Feature #2634 (Resolved): teuthology: add networking to qemu task
- Let the guest speak to the outside world so test scripts can e.g. check out git repos and download test programs to c...
- 06:32 AM Bug #2618: error: unable to open OSD superblock
- I manually created the directory.
Then I ran the mkcephfs command.
The directory has some files in it (journal, mag...
06/20/2012
- 10:10 PM Revision 1e539daf (ceph): doc: Normalized shell script syntax. Added generic cookbook path.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:39 PM Feature #2631 (Resolved): mon: kill rm -rf --mkfs behavior
- 09:29 PM Revision 7d38758a (ceph): doc: Changed libvirt-dev to libvirt-bin, and cleaned up ./autogen.sh
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:02 PM Bug #2593: logmonitor: decode failure
- ...
- 07:55 PM Revision 3e32dd08 (ceph): doc: Typo.
- Signed-off-by: Tommi Virtanen <tv@inktank.com>
- 06:55 PM rbd Feature #2630 (Resolved): teuthology: add task to run qemu-iotests against rbd
- qemu-iotests are included in upstream qemu.git. They exercise qemu's block layer to test correctness. They use existi...
- 06:44 PM rbd Feature #2629 (New): qa: test performance during live migration
- This could be done after #2628 by running iozone during the migration, parsing its output, and checking that throughp...
- 06:41 PM rbd Feature #2628 (New): qa: test live migration with qemu
- Run something like fsstress in the vm during the migration, and verify that it completes successfully. To do this we'...
- 06:37 PM rbd Feature #2627 (New): qa: regression tests for libvirt rbd storage pool
- Libvirt storage pools allow you to create, delete, and list volumes. Wido wrote a backend that uses librbd to do this...
- 06:35 PM Revision c8e1ec6a (ceph): record owner at start of run
- So that we can clean up easily even when we don't finish and there is no
summary.yaml. - 06:30 PM rbd Feature #2626 (New): qa: regression tests for basic rbd libvirt integration (disks)
- Test using rbd disks with vms through libvirt.
This includes:
* booting a vm backed only by rbd
* attaching rb... - 06:23 PM Revision 845e6c28 (ceph): move cfuse + dbench task that triggers #1737 to marginal suite
- 06:15 PM rbd Feature #2625 (Rejected): qa: gitbuilder for libvirt
- Create a gitbuilder for libvirt packages so we can regression test rbd against upstream releases. Base this on the ub...
- 05:57 PM Revision c467d9d1 (ceph): v0.47.3
- 05:36 PM Bug #2600: osd: crazy long watch timeout?
- In another recurrence, there are no objecter requests:...
- 05:13 PM Revision 218b6924 (ceph): teuthology-ls: tolerate non-existent 'success' key in summary file
- 05:02 PM Revision 17dcf605 (ceph): filestore: disable 'filestore fiemap' by default
- We've seen this failing on both btrfs (Guido) and XFS (Oliver). This works
around #2535.
Signed-off-by: Sage Weil <... - 04:34 PM Bug #2524 (Won't Fix): librados crashed while connecting to cluster
- 04:34 PM Bug #2456 (Resolved): librbd: failed LibRBD.TestIOToSnapshot
- Haven't seen this in a while. Maybe some of the race cleanups fixed it...
- 04:32 PM Documentation #2624: OpenStack creation instructions should recommend non-default number of pg's ...
- It'll have to be ceph osd pool create <pool> <num_pgs> until #2519 is done.
- 04:25 PM Documentation #2624 (Resolved): OpenStack creation instructions should recommend non-default numb...
- http://ceph.com/docs/master/rbd/rbd-openstack/ recommends
sudo rados mkpool nova
This should probably be
su... - 03:46 PM Cleanup #2623 (Resolved): filestore btrfs trans should be removed
- On Wed, 20 Jun 2012, Stefan Priebe - Profihost AG wrote:
> Hello list,
>
> i've looked at the wiki (http://ceph.co... - 03:01 PM Subtask #2622 (Resolved): mon: Single-Paxos: convert existing, old MonitorStore to a brand new Mo...
- The new monitor design does not support the old MonitorStore, nor does it store the versions and their values in the ...
- 02:58 PM Subtask #2621 (Resolved): mon: Single-Paxos: synchronize the MonitorDBStore of oblivious monitor
- *Objective:* synchronize monitor stores over the network whenever a given monitor mon.X falls too far behind.
*Sol... - 02:50 PM Subtask #2615 (Closed): mon: Single-Paxos: MDSMap::get_health() asserting
- 02:49 PM Subtask #2615: mon: Single-Paxos: MDSMap::get_health() asserting
- This issue stopped popping up after we changed the criteria to propose queued proposals and restarted testing with a ...
- 03:59 AM Subtask #2615 (Closed): mon: Single-Paxos: MDSMap::get_health() asserting
- MDSMap infos, dumped on MDSMap::get_health() just before the assert is triggered:...
- 02:47 PM Subtask #2616: mon: Single-Paxos: AuthMonitor: key_server has no entries
- Appears to be fixed.
The ceph tool is able to connect to the cluster and obtain status information.
However, th... - 11:01 AM Subtask #2616: mon: Single-Paxos: AuthMonitor: key_server has no entries
- Although this appears to be fixed, we still are unable to authenticate clients.
My current suspicion is that we ar... - 09:00 AM Subtask #2616: mon: Single-Paxos: AuthMonitor: key_server has no entries
- We were encoding an empty "full version" of the key server during AuthMonitor::encode_pending(), along side with the ...
- 08:36 AM Subtask #2616: mon: Single-Paxos: AuthMonitor: key_server has no entries
- The problem appears to affect all mon clients, and it may be the reason why our OSDs do not work as well.
Log snip... - 08:00 AM Subtask #2616 (Closed): mon: Single-Paxos: AuthMonitor: key_server has no entries
- The Monitor's key_server has no entries, even though we made sure to populate mon.X/keyring with every single service...
- 02:45 PM Subtask #2614: Single Paxos instance shared across the existing services
- 03:48 AM Subtask #2614 (Closed): Single Paxos instance shared across the existing services
- One Paxos to propose them all.
- 02:44 PM Subtask #2620 (Closed): mon: Single-Paxos: MDSMonitor: MMDSBeacon from entity with insufficient p...
- ...
- 02:06 PM Bug #2550: logrotate: SIGHUP upstart jobs too, not just sysvinit
- Please mention https://bugs.launchpad.net/upstart/+bug/1012938 in the "sucks" comment, so someone can some day nicely...
- 01:47 PM Bug #2550: logrotate: SIGHUP upstart jobs too, not just sysvinit
- repushed upstart-vs-logrotate branch
- 12:25 PM Bug #2550: logrotate: SIGHUP upstart jobs too, not just sysvinit
- yeah, that'll work. only solves the logrotate case, but that's fine by me.
- 11:39 AM Bug #2550: logrotate: SIGHUP upstart jobs too, not just sysvinit
- That killall thing is hideous, and I'm utterly unconvinced having even more upstart jobs for Ceph is helpful in any w...
- 12:30 PM Feature #2619 (Resolved): filejournal: instrument with perfcounters
- 12:09 PM Bug #2618: error: unable to open OSD superblock
- Hi John,
Did you create the /data/ceph/osd0 directory? mkcephfs doesn't do it for you because of the potential for... - 11:31 AM Bug #2618 (Can't reproduce): error: unable to open OSD superblock
- I am new at this.
I installed ceph.
When I do a service ceph start, mon.0 and mds.(machine name) seem ok.
When it ... - 11:13 AM Bug #2022: osd: misdirectect request
- here is the smoking gun. note that teh pgid goes to 0.0 when linger tid 1 is resending the watch op 4:...
- 03:45 AM Subtask #2613: Sandbox PaxosServices accesses to the store
- I messed up the formatting and don't seem to be able to edit it. So here goes a decent version of it....
- 03:41 AM Subtask #2613 (Resolved): Sandbox PaxosServices accesses to the store
- Each service used to have direct access to the MonitorStore, and they could mess around wherever they wanted, allowin...
- 03:25 AM Subtask #2612 (Resolved): Monitor key/value store
- Create a key/value store, with transaction support, to be used on the monitor subsystem.
Its interface should refl... - 03:21 AM Feature #2611 (Resolved): mon: Single-Paxos
- The ceph-mon is (roughly) composed by a Monitor class, responsible for all things monitor-ish, and several monitor se...
- 12:34 AM Revision 88c7629e (ceph): OSD: clear_temp: split delete into many transactions
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 12:29 AM Revision 233bc8dd (ceph): schedule_suite: enable kdb
- Among other things, you can attach to the console after the fact and type
'dmesg' to see wtf happened. - 12:24 AM Revision 286e6397 (ceph): kernel: enable/disable kdb
- This hard-codes ttyS1, which is what we use on sepia.
06/19/2012
- 10:19 PM Revision 6948af02 (ceph): Merge branch 'wip-clsrbd'
- Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 10:17 PM Revision b84e1ed5 (ceph): doc: document usage log
- Modify radosgw, radosgw-admin man page
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 10:08 PM Revision 986d0e11 (ceph): cls_rbd: clean up doxygen, whitespace a bit
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:08 PM Revision 156879f4 (ceph): cls_rbd: fix uninitialized var in cls_rbd_parent
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:08 PM Revision 25311e96 (ceph): cls_rbd: note overlap units
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:08 PM Revision 3948e069 (ceph): cls_rbd: handle parent overlap
- Two things:
* when we set a parent, the overlap is the min of our size and the
parent's size.
* when we resize,... - 10:08 PM Revision 87cadffd (ceph): cls_rbd: rename parent size -> overlap
- The use of 'size' to describe the amount that we overlap with the parent
was confusing; overlap is more intuitive (to... - 10:08 PM Revision 4e73ca45 (ceph): cls_rbd: include dumpers, test instances for our types
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:08 PM Revision 2f75b466 (ceph): cls_rbd: implement get_parent, set_parent, remove_parent
- Implement methods to get/set/remove the parent pointer on child images.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:08 PM Revision f87c441f (ceph): cls_rbd: check for LAYERING feature for parent methods
- You need to set the feature on the image before you can use these methods.
We *could* allow get_parent, but that just... - 10:08 PM Revision e8b36ed9 (ceph): cls_rbd: make snapshots inherit the head's parent
- When you take a snapshot, the snap gets the current parent of the head, if
any.
Signed-off-by: Sage Weil <sage@inkta... - 09:35 PM Revision c7f91e6c (ceph): cls_rbd_client: use snapid_t type
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:30 PM Revision ab42b8dd (ceph): add usage log tests to radosgw-admin tasks
- tests 'usage show' and 'usage trim'
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:29 PM Revision c70c09f6 (ceph): Merge remote-tracking branch 'gh/next'
- Conflicts:
src/osd/PG.cc - 08:26 PM Revision 145d1c14 (ceph): rgw: set s->header_ended before flushing formatter
- otherwise we don't account the formatter in s->bytes_sent.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 08:26 PM Revision 8a4e2a11 (ceph): rgw: log user and not bucket owner for service operations
- For operations that are done on the service (e.g., list buckets)
we need to log the user that did the operation, and ... - 08:25 PM Revision 282e2260 (ceph): rgw: initalize s->enable_usage_log
- Missing initialization, we ended up not logging every operation.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 07:04 PM rbd Feature #2556: rbd tool: break image locks
- Argh. I don't seem to be getting my email notifications from you and Josh on Github, and I don't know why.
- 06:57 PM rbd Feature #2556: rbd tool: break image locks
- https://github.com/ceph/ceph/commit/3c05629691deb800e3c6e62e81f444a748e8857c#src-rbd-cc-P108
just making sure i un... - 06:48 PM rbd Feature #2556: rbd tool: break image locks
- Your commits look good to me (sorry I missed the cli tests; I need to get into the habit of running those), but I don...
- 05:46 PM rbd Feature #2556: rbd tool: break image locks
- rebase, fixed up ENOENT vs ENOEXEC behavior. one clarification about the purpose/scope of 'rbd lock', but otherwise ...
- 03:13 PM rbd Feature #2556 (Fix Under Review): rbd tool: break image locks
- wip-rbd-locking has this now, but it also merges in wip-clsrbd for an unrelated change, so you might want to wait to ...
- 05:49 PM Revision 4ec96336 (ceph): PG: improve find_best_info
- 07f853db3982e68b952a337cf91cbf7ec0709de9 is actually too conservative,
it suffices to find any info with a last_updat... - 05:15 PM Revision 992faa42 (ceph): doc: Added a snapshot page with outline. Needs additional info.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:12 PM Revision f3f144ad (ceph): osd: use derr (instead of cerr) for convertfs
- This will appear in the log *and* stderr (if we're running in the
foreground).
Signed-off-by: Sage Weil <sage@inktan... - 05:11 PM Revision 74658dfa (ceph): osd: close stderr on daemonize
- This spams stderr in an ugly way. Users should look at the logs.
In particular, filestore upgrades spam the console... - 05:10 PM Revision 2be02918 (ceph): doc: Added prerequisite of running Ceph cluster.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:06 PM Bug #2610 (Resolved): osd: pg stuck at scrubbing
- Happened on congress, pg was stuck at scrubbing state for two and a half days....
- 04:39 PM Revision 5435a4de (ceph): osdcap: make grammar build on spirit 2.2/boost 1.42
- This is a stupid workaround, but it makes the compilation error go away.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:20 PM rbd Feature #2558 (Resolved): cls_rbd: child/parent methods
- 04:05 PM devops Feature #2584 (In Progress): sepia: provide networking, DHCP for dynamic virtual machines
- 04:04 PM Feature #2576 (In Progress): perf: 0.48 on long-term clusters
- 04:04 PM Feature #2575 (In Progress): perf: 0.48 numbers
- 03:52 PM rbd Feature #2609 (Resolved): librbd: new image name -> image head indirection
- To prevent rename from disrupting clients with images open,
* put header in rbd_head.$id
* put $id in rbd_id.$nam... - 02:32 PM rgw Feature #2516 (Resolved): rgw: new bandwidth-only per-user log
- 02:28 PM rbd Bug #2608 (Closed): rbd: hung xfstest 270
- Logs are available in ubuntu@teuthology:/a/teuthology-2012-06-19_00:00:09-regression-next-testing-basic/1792
2012-... - 01:25 PM Bug #2022: osd: misdirectect request
- latest run log: ubuntu@teuthology:/a/teuthology-2012-06-18_19:00:05-regression-master-testing-gcov/1586
- 12:54 PM CephFS Bug #1947: mds: SIGBUS during _mark_dirty
- ubuntu@teuthology:/a/teuthology-2012-06-18_19:00:05-regression-master-testing-gcov/1579
- 11:31 AM Messengers Bug #1985: msgr: creating new Pipe for pre-existing connection leaks Pipe if they don't replace
- I've still got this sitting around in my workspace. Since we seem to have pushed back a messenger re-do, perhaps we s...
- 09:57 AM rbd Feature #2607 (Resolved): librbd: copyup helper
- copyup helper to perform a copyup from parent to child. will be used by both the rbd command-line copyup command, an...
- 09:57 AM rbd Subtask #2606 (Resolved): librbd layering: copyup on missing child object
- 09:57 AM rbd Subtask #2605 (Resolved): librbd layering: guard writes
- 09:56 AM rbd Subtask #2604 (Resolved): librbd layering: read path
- 09:56 AM rbd Subtask #2603 (Resolved): librbd layering: open parent on open
06/18/2012
- 10:07 PM Bug #2550 (Fix Under Review): logrotate: SIGHUP upstart jobs too, not just sysvinit
- Sigh. See branch upstart-vs-logrotate.
- 09:33 PM Revision 0d8970fc (ceph): PG: reg_last_pg_scrub on pg resurrection
- This may solve the unreg_last_pg_scrub assert.
see #2453.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 09:33 PM Revision b0e66b70 (ceph): ceph_osd: move auto-upgrade to after fork
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:30 PM Revision 6feeff95 (ceph): librbd: simplify refresh sequence checks
- - incremental seq each request
- set last to the last completed seq
- drop the now-redundant bool
Signed-off-by: Sag... - 09:29 PM Revision 6c88ff59 (ceph): Merge branch 'master' of github.com:ceph/ceph
- 09:29 PM Revision b101f4ce (ceph): doc: first cut of OpenStack/RBD w/out cephx. Authentication coming soon.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:07 PM Revision 37e56e01 (ceph): filestore: make disk format upgrade warning less scary, more informative
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Sam Just <sam.just@inktank.com> - 09:02 PM Revision 030a2e3b (ceph): mon: include quorum in ceph status
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:00 PM Revision 2fc2cf03 (ceph): mon: gracefully handle slow 'ceph -w' clients
- If we are sending log updates to a client (ceph -w), and they are far
enough behind to drop behind first_committed, i... - 08:57 PM rbd Feature #2556: rbd tool: break image locks
- Greg Farnum wrote:
> Team RBD needs more to do! Pulling this forward. :)
Go team! :) - 06:26 PM rbd Feature #2556 (In Progress): rbd tool: break image locks
- Team RBD needs more to do! Pulling this forward. :)
- 08:22 PM Revision 8b96b9c7 (ceph): doc: Added libvirt installation.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:18 PM Revision 51fcef24 (ceph): PG: best_info must have a last_epoch_started as high as any other info
- We disregard incomplete infos during find_best_info, but we can't an
info with a last_epoch_started less that of the ... - 05:56 PM rbd Feature #2585 (In Progress): rbd: clone command
- 05:34 PM rbd Feature #2585: rbd: clone command
- 05:36 PM Revision 2b92c73b (ceph): doc: btrfs and parted chef recipes are not needed.
- They were removed in ceph-cookbooks.git commit
a77b418b95df8f2b6f56d9a90e47dc62100cdf4d.
Signed-off-by: Tommi Virtan... - 05:35 PM rbd Feature #2559: cls_rbd: copyup method
- 01:50 PM rbd Feature #2601: rbd: Show image size with an "ls"
- We've also heard from others that having a better estimate of rbd usage and expected usage would be good; taking into...
- 06:09 AM rbd Feature #2601 (Resolved): rbd: Show image size with an "ls"
- On the mailinglist the request came if the "rbd" tool could be modified to not only show image names when doing an ls...
- 01:34 PM rgw Bug #2542 (Resolved): rgw: support S3 update of metadata
- 01:32 PM rgw Bug #2542: rgw: support S3 update of metadata
- Resolved, commit:343cc792e847ca8901f6c08e41799a2fbbd2ca92
- 11:04 AM Bug #2602: osd: push failed because local copy is X
- Updated another osd to 'next' and same errors happened.
I've attached the log with debug osd = 20 set. - 08:46 AM Bug #2602: osd: push failed because local copy is X
- Is this reproducible with 'debug osd = 20'?
- 08:44 AM Bug #2602 (Resolved): osd: push failed because local copy is X
- Hi,
filestore updated completed.
When i start the "updated" OSD the whole cluster starts lagging.
Is the next br... - 08:45 AM Bug #2598: filestore: error during upgrade
- Simon Frerichs wrote:
> Hi,
>
> filestore updated completed.
> When i start the "updated" OSD the whole cluster ... - 08:42 AM Bug #2598 (Resolved): filestore: error during upgrade
- THanks!
- 01:29 AM Bug #2598: filestore: error during upgrade
- Hi,
filestore updated completed.
When i start the "updated" OSD the whole cluster starts lagging.
Is the next br... - 12:56 AM Bug #2598: filestore: error during upgrade
- Thanks.
The bug seems to be fixed. - 08:43 AM Bug #2595: filestore: error creating filestore during mkcephfs
- 2012-06-18 17:42:16.232924 7f54292fb780 -1 filestore(/srv/osd.20) could not find 23c2fcde/osd_superblock/0//-1 in ind...
- 08:29 AM Bug #2599: osd: crash in ReplicatedPG::C_OSD_OndiskWriteUnlock::finish
- commit:5efaa8d7799347dfae38333b1fd6e1a87dc76b28
- 07:25 AM CephFS Bug #2596: mds: spinning on restart
- gdb is not helpful here, process seems to be spinning in syscall:
(gdb) thread apply all bt
Thread 1 (process 148...
06/17/2012
- 10:40 PM Bug #2600: osd: crazy long watch timeout?
- Possibly related to #2476
- 09:37 PM Bug #2600 (Resolved): osd: crazy long watch timeout?
- ...
- 09:34 PM CephFS Bug #1737: ceph-fuse crash in xlist::remove
- see ubuntu@teuthology:/a/teuthology-2012-06-17_19:00:03-regression-master-testing-gcov/1303 for a failure with logs!
- 09:00 PM Revision 10c57b5a (ceph): Merge branch 'next'
- 08:21 PM Revision 95ac5bae (ceph): debian: fix python-ceph depends
- Signed-off-by: Laszlo Boszormenyi (GCS) <gcs@debian.hu>
- 08:21 PM Revision d7fe0e3f (ceph): debian: update homepage url
- Signed-off-by: Laszlo Boszormenyi (GCS) <gcs@debian.hu>
- 08:20 PM Revision 82cb3d61 (ceph): filestore: fix 'omap' collection skipping
- The if/else if/... structure was skipping this test if the file system
didn't support d_type.
Fixes: #2598
Signed-of... - 07:16 PM Revision 372fbe0e (ceph): sync clock at start of every run
- 07:00 PM Revision 343cc792 (ceph): run-cli-test: use new pip incantation
- http://www.pip-installer.org/en/latest/news.html#id1
Signed-off-by: Sage Weil <sage@inktank.com> - 06:15 PM Revision e3b6957d (ceph): run-cli-test: use new pip incantation
- http://www.pip-installer.org/en/latest/news.html#id1
Signed-off-by: Sage Weil <sage@inktank.com> - 04:07 PM Revision 3d4ba431 (ceph): cls_rbd: do not pass snapid_t to vargs
- On squeeze,
warning: cls_rbd.cc:534: cannot pass objects of non-POD type ‘struct snapid_t’ through ‘...’; call will ... - 03:58 PM Revision a4589c6a (ceph): don't dup ceph task for new fsx jobs
- 02:33 PM RADOS Feature #2422 (In Progress): crush: test that mapping result is uncorrelated
- 02:32 PM Bug #2598: filestore: error during upgrade
- Ah... should have tested on another filesystem.
- 02:21 PM Bug #2598: filestore: error during upgrade
- Oh, der.. pretty sure commit:82cb3d61ff4f200e0a9040e6381a9eed32db9de1 fixes this.
- 02:29 PM Bug #2022: osd: misdirectect request
- Last two failures were the rados api tests:...
- 06:50 AM CephFS Bug #2385: max mds = 2, mds hang and crash
- ...
- 06:45 AM CephFS Bug #2385: max mds = 2, mds hang and crash
- ...
- 03:14 AM Revision f7ee34b5 (ceph): tolerate 250ms clock drift
- 03:09 AM Revision 5efaa8d7 (ceph): msg: fix buffer overflow in ipv6 addr parsing
- Noticed because of failing i386 unit tests for long addrs; x86_64 passed
fine. Sigh. FTR, the failing address was
...
06/16/2012
- 10:05 PM Revision 9929ceb4 (ceph): include suite in archive dir
- 09:50 PM Revision d9e902f9 (ceph): ceph.newdream.net -> ceph.com
- wiki url -> docs url
- 08:59 PM Revision abd7d183 (ceph): whitelist 'slow request' in qa runs
- 02:42 PM Revision 150e1fc5 (ceph): Merge branch 'next'
- Conflicts:
src/cls_rbd.cc - 02:34 PM Revision f8a196fb (ceph): cls_rbd: drop useless snapshot metadata helpers
- Now that cls_rbd_snap is encodable, we don't need these helpers; get_key()
will suffice.
Signed-off-by: Sage Weil <s... - 02:33 PM Revision b08d7ba9 (ceph): cls_rbd: use encode macros for on-disk snap metadata
- This will let us version this encoding later when we add new information
and features, like a per-snap parent.
Signe... - 11:34 AM Bug #2598: filestore: error during upgrade
- That's odd, it's updating the omap directory as a collection. list_collections should not have returned omap as a co...
- 08:04 AM Bug #2598 (Resolved): filestore: error during upgrade
- from ML:...
- 08:25 AM Bug #2462 (Resolved): osd/PG.cc: 402: FAILED assert(log.head >= olog.tail && olog.head >= log.tail)
- I'm going to optimistically call this resolved. If we see this crash again, though, we'll need to reopen, and hopefu...
- 08:24 AM rbd Bug #2535: rbd: random data corruption in vm
- We've disabled fiemap, which appears to be the culprit. Josh is still tracking down which kernel releases are affect...
- 08:21 AM Bug #2599 (Can't reproduce): osd: crash in ReplicatedPG::C_OSD_OndiskWriteUnlock::finish
- from ml:...
- 07:59 AM Bug #2595 (Resolved): filestore: error creating filestore during mkcephfs
- 07:59 AM Bug #2595: filestore: error creating filestore during mkcephfs
- commit:1e899d08e61bbba0af6f3600b6bc9a5fc9e5c2e9
- 06:40 AM Bug #2595: filestore: error creating filestore during mkcephfs
- Yes
- 12:39 AM Revision dac9f223 (ceph): Merge branch 'wip-rbd-locking'
- Conflicts:
src/cls_rbd.cc
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 12:30 AM Revision 07f853db (ceph): PG: best_info must have a last_epoch_started as high as any other info
- We disregard incomplete infos during find_best_info, but we can't an
info with a last_epoch_started less that of the ... - 12:27 AM Revision c88a4550 (ceph): cls_rbd: add locking functions.
- Users can now place shared or exclusive locks, can remove their own
locks, can break the locks of others, and can lis... - 12:27 AM Revision 71e1b1fd (ceph): cls_rbd: add failure logging to all callers of read_key.
- Previously, read_key was printing out error messages when it failed.
But because some callers are fine with it failin... - 12:27 AM Revision 71c7ed3f (ceph): cls_rbd_client: expose locking operations
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 12:27 AM Revision 48d2376e (ceph): test: add rbd image locking tests to test_cls_rbd
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 12:27 AM Revision 668aa786 (ceph): librbd: include the image lockers in the ImageCtx mutable metadata
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 12:27 AM Revision b018befd (ceph): librbd: add cooperative image locking to the C and C++ interfaces
- While we're at it, increment the version number.
Signed-off-by: Greg Farnum <greg@inktank.com> - 12:27 AM Revision 5b1b02b6 (ceph): librbd: remove the set-r-and-return idiom from some functions.
- Josh hates this, and I have to admit it seems silly.
Signed-off-by: Greg Farnum <greg@inktank.com>
06/15/2012
- 09:48 PM Revision 1e899d08 (ceph): filejournal: make less noise about open failures
- The callers report errors and pass up errors, so do not spam stderr with
this. Fixes the confusion that sparked #259... - 08:44 PM Revision b415fd21 (ceph): rgw: obj copy respects -metadata-directive
- Fixes #2542. The old behavior just merged src object attrs
and provided attributes. The new (and correct) behavior lo... - 08:06 PM Revision 2dd17988 (ceph): librbd: only clear the needs_refresh flag on successful updates.
- To support this, add a refresh_seq counter which is incremented every
time we get a notify. This way we can handle th... - 06:59 PM Revision 0c40b24c (ceph): Run fsx on rbd with thrashing
- 06:55 PM Revision 50e01c18 (ceph): Increase number of ops done by fsx against rbd.
- Especially in the no-cache case, this should detect more races. The
fiemap problem is detectable on plana after ~5000... - 06:54 PM Revision b5de8398 (ceph): osd: optional verify that sparse_read holes are zero-filled
- This should help us track down/verify #2535. It seems to happen on several
different systems, but we haven't figured... - 06:54 PM Revision 1156f943 (ceph): buffer: add list and ptr is_zero() method
- Simple helper to check if a buffer is all zeros.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:10 PM Revision 6fd91381 (ceph): Merge remote-tracking branch 'gh/wip-osdcap'
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 05:58 PM rbd Feature #1480 (Resolved): librbd: image locking
- Okay, discussed and merged in commit:dac9f223598c5f67b228403e514f202280d56488
- 05:49 PM rbd Feature #1480: librbd: image locking
- And after thorough review from Josh, this should be ready for merge (commit:5b1b02b60a253092700f364dca77bb6b1065e3e0)...
- 05:10 PM Revision 614d5a7b (ceph): LFNIndex.cc: escape null in append_[un]escaped
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:00 PM Revision 9d4ce4bc (ceph): filestore: disable 'filestore fiemap' by default
- We've seen this failing on both btrfs (Guido) and XFS (Oliver). This works
around #2535.
Signed-off-by: Sage Weil <... - 02:40 PM rgw Bug #1643 (Rejected): radosgw-admin log show should accept --time
- 02:03 PM Bug #2595: filestore: error creating filestore during mkcephfs
- Oh, it looks like it's just noise from checking the journal. The mkcephfs succeeded, right?
- 01:57 PM Bug #2595: filestore: error creating filestore during mkcephfs
> Can you reproduce with 'debug filestore = 20' and attach the log to this
> bug?
Log:...- 10:32 AM Bug #2595: filestore: error creating filestore during mkcephfs
- FYI, I saw this once when I was working on the OSD hotplug code paths. Mine might have been caused by a missing "osd ...
- 09:29 AM Bug #2595 (Resolved): filestore: error creating filestore during mkcephfs
- from ML:...
- 11:48 AM rbd Bug #2597 (Resolved): Import of image from file appears to succeed, but image not present in the ...
- I have been testing with storing an image file, a basic QCOW2 image of latest Ubuntu distro on a pool, which is used ...
- 10:44 AM rbd Feature #2558: cls_rbd: child/parent methods
- wip-clsrbd
- 10:44 AM rbd Feature #2558 (Fix Under Review): cls_rbd: child/parent methods
- 09:44 AM CephFS Bug #2596 (Can't reproduce): mds: spinning on restart
- from ML:...
06/14/2012
- 11:47 PM Revision dbbbe21f (ceph): osdcap: 'allow rwx pool foo' or 'allow pool foo rwx'
- Make the match vs spec order not matter.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:38 PM Revision 1bd5d240 (ceph): nightly push to local repo
- 11:36 PM Revision 66df6be8 (ceph): ceph-authtool: update docs to reflect no more osdcap deny
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:35 PM Revision f9161688 (ceph): osdcap: make caps additive
- Make 'allow pool foo r, allow pool foo w, allow x' sufficient when you
require rwx for pool foo.
Signed-off-by: Sage... - 10:17 PM Revision 01f48039 (ceph): Merge branch 'wip-radosgw-upstart'
- 10:09 PM Revision b44092f5 (ceph): radosgw: stop startup timer on failed start
- This fixes crashes like
-1> 2012-06-14 15:04:31.733009 7f544e18c780 -1 Couldn't init storage provider (RADOS)
... - 10:04 PM Revision 6f30f1fc (ceph): upstart: make id charset include - _ and .
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:03 PM Revision 7bfcc7c4 (ceph): radosgw: takes --id, but not -i
- The -i short versio doesn't work on 'client' code that tend to use it for
input files.
Signed-off-by: Sage Weil <sag... - 09:19 PM Revision 92589f88 (ceph): objclass: allow class methods to retrieve their triggering entity_inst
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:18 PM Revision 7515b05e (ceph): doc: added qemu-img documentation for rbd.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:12 PM Revision 5db4509b (ceph): rgw: limit number of buckets per user
- Adding a configurable max_buckets per user. Bucket creation
verifies that max_buckets has not reached.
Backport: dho... - 09:06 PM Revision 9aeac5de (ceph): add radosgw-admin test to regression suite
- We wrote this test ages ago, but forgot to add it! Fixed up a few things
that have changed since then. - 09:04 PM Revision 57da2794 (ceph): schedule_suite.sh: add flavors, check/fix sha1s, optional templates
- This should be everything we need to use this for the nightlies, with the
exception of updating the git trees, which ... - 09:04 PM Revision 83f8f3d1 (ceph): radosgw-admin: fix swift subuser/key tests
- Need to do 'subuser (add|rm)', not 'key (add|rm)'.
- 09:04 PM Revision 474f8da4 (ceph): radosgw-admin: remove buckets before user
- Otherwise user delete will fail.
- 09:04 PM Revision 697c3b94 (ceph): radosgw-admin: test max buckets limit
- 09:04 PM Revision 3bd387f9 (ceph): radosgw-admin: fix for non-numeric bucket ids
- 09:02 PM Linux kernel client Bug #2389 (Duplicate): rbd: hung xfstest 67
- 09:01 PM Linux kernel client Bug #2359 (Can't reproduce): xfstest 62 failing
- haven't seen this in a while
- 07:59 PM Revision 41488c02 (ceph): Merge branch 'master' of github.com:ceph/ceph into wip-2543
- 05:55 PM Feature #2571 (Resolved): sepia: enable virtualization
- 11:34 AM Feature #2571 (In Progress): sepia: enable virtualization
- BIOS settings changed on all plana; one reboot test shows good results. One can tell if
virtualization is enabled w... - 04:46 PM Revision 0adb33d8 (ceph): doc: Added steps for OpenStack install with DevStack
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 04:35 PM Revision 446e5d8e (ceph): doc: fixed bash syntax error.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 04:12 PM Bug #2593 (Resolved): logmonitor: decode failure
- Saw this while trying to reproduce #2569. Sadly teuthology cleaned everything up before I could get to the data.
<pr... - 04:07 PM Revision 97c9f014 (ceph): qa: disable xfstest 68 for now
- Stop the qa noise we fix #2410. Looks like a freeze/thaw thing.
Maybe Jan's new freeze/thaw code will address this?... - 04:01 PM Revision 7f4d1710 (ceph): qa: disable xfstest 219 for now
- The cause of 219 failing is non-obvious. Disable it for now. :(
Avoids #2522.
Signed-off-by: Sage Weil <sage@inkt... - 03:24 PM Feature #2581 (In Progress): perf: investigate 0.47.2 precise vs 0.46 oneiric discrepancy
- 03:13 PM devops Feature #2415 (Resolved): upstart: support radosgw
- 03:06 PM rbd Bug #2534: librbd: make sure watch is established on same header version as initial read was
- Okay, this is blocked by #2592.
- 03:06 PM Bug #2563: leveldb corruption
- It's triggerable without ceph, I've filed a bug below with leveldb and I'm continuing to look into it.
http://code... - 03:05 PM Bug #2592: osd and all clients: watch version parameter is ignored
- Alternatively, maybe the OSD should just enforce the version with those checks when setting a watch? It looks to me a...
- 03:01 PM Bug #2592 (Resolved): osd and all clients: watch version parameter is ignored
- Watch operations have a version parameter that is supposed act like an assert_version op. This could easily be done i...
- 02:38 PM Feature #2471 (In Progress): osd: add prefix match to OSDCaps
- you can have this one too, given your wip-osdcap branch.
- 02:37 PM rbd Feature #1480 (Fix Under Review): librbd: image locking
- wip-rbd-locking
- 02:09 PM rgw Feature #2517 (Resolved): rgw: limit number of buckets per user (configurable per user)
- added teuth tests, in master, backported to dho
- 02:04 PM rgw Bug #2591 (Resolved): misc rgw s3tests failures
- Should be ok for now. I've set boto to 2.4.1, we can change that later once upstream fixes its issues.
- 10:15 AM rgw Bug #2591: misc rgw s3tests failures
- boto 2.5.0 issue. For some reason it doesn't set the error.reason on 400 responses.
- 07:57 AM rgw Bug #2591 (Resolved): misc rgw s3tests failures
- 2012-06-13T12:51:42.657 INFO:teuthology.orchestra.run.err:s3tests.functional.test_headers.test_bucket_create_bad_auth...
- 12:59 PM rbd Bug #2535: rbd: random data corruption in vm
- Sage Weil wrote:
> Just a bit of context: rbd without caching does a 'sparse-read' operation, which uses FIEMAP to d... - 12:52 PM rbd Bug #2535: rbd: random data corruption in vm
- Just a bit of context: rbd without caching does a 'sparse-read' operation, which uses FIEMAP to determine which parts...
- 12:50 PM rbd Bug #2535: rbd: random data corruption in vm
- Let's try a different tack: I pushed a osd-verify-sparse-read-holes branch to ceph.git (based on 0.47.2) that reads ...
- 09:09 AM rbd Bug #2535: rbd: random data corruption in vm
- Status update:
I tried modifying the iotester so that it would work directly on the block device, in the hopes I c... - 10:14 AM Feature #2472: osd: add opaque 'class <name> <foo>' cap that class can interpret/enforce
- wip-osdcap is doing this way better than I was, although I'm happy to take it back to do the OSD changes if need be.
- 09:09 AM rbd Bug #2410: hung xfstest #68
- disabled 68 in qa for the time being.
- 09:03 AM rbd Bug #2522: xfstest #219
- Sigh.. took a quick look and it's non-obvious why the repquota output doesn't match. Disabling this for now, but lea...
- 12:15 AM Revision 051e1686 (ceph): osdcap: move semantics of cap check into OSDCap class
- The class needs to understand the semantics of possible actions in enough
detail to apply the capabilities it describ...
06/13/2012
- 11:30 PM Revision 3dbad22c (ceph): Makefile: fix leveldb includes for system library case
- Use the installed headers, not ours.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:30 PM Revision 529c4844 (ceph): Makefile: fix leveldb dep for system library case
- We conditionally add this below only if using the bundled version.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:23 PM Revision e48dab43 (ceph): doc: Multi-monitor support means ceph::single_mon was renamed.
- This changed in ceph-cookbooks.git commit
8e56551b11fe28cc4f29f4fcdcf6c38516bdc833.
Signed-off-by: Tommi Virtanen <t... - 08:57 PM Linux kernel client Bug #2590 (New): possible irq lock inversion dependency with con->mutex and osdc->request_mutex
- i thought this was #147, but on closer inspection it's something else;...
- 08:55 PM Revision 762f6d95 (ceph): osdcap: whitespace to make grammar more readable
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:42 PM Revision 1cfd65b1 (ceph): osdcap: use static const instead of #define
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:42 PM Revision bf72a00e (ceph): osdcap: drop unused 'auid' arg from get_cap(), is_match()
- The intent was to do a cap like 'allow pools-that-i-own ...', but in
practice you just do 'allow pool <myuid> ...'.. ... - 07:17 PM Bug #2550: logrotate: SIGHUP upstart jobs too, not just sysvinit
- Filed upstream: https://bugs.launchpad.net/upstart/+bug/1012938
- 06:24 PM Revision 67710a65 (ceph): rbd: fix usage test
- Fixes: #2347
Signed-off-by: Sage Weil <sage@inktank.com> - 06:17 PM rgw Feature #2516: rgw: new bandwidth-only per-user log
- I think the last thing we need here is to add it to the radosgw-admin test so that we don't break these commands in t...
- 12:26 PM rgw Feature #2516 (In Progress): rgw: new bandwidth-only per-user log
- 06:05 PM Revision 66553d25 (ceph): Makefile: link gtest statically
- The problem:
- the unittests link against gtest, and gtest is not installed. that's
normally fine, but...
- rb... - 05:04 PM rgw Feature #2473: rgw: revisit operation logging
- Not the top priority, but we can have an async flush, similar to the one we have for the usage logging.
- 05:03 PM Revision 395c4468 (ceph): Merge branch 'master' of github.com:ceph/ceph into wip-2543
- 04:22 PM Revision 282277de (ceph): radosgw: upstart support
- Like the other upstart configs, these assume the default value for
'rgw data'. Same pattern as ceph-mon and ceph-mds... - 04:22 PM Revision d1fc562d (ceph): debian: install radosgw upstart configs, daemon dir
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:20 PM Linux kernel client Bug #2573: libceph: many "socket closed" messages
- In that case, if you want to run this with the osd messenger debug at 5 and can gather logs next time I'll be happy t...
- 02:35 PM Linux kernel client Bug #2573: libceph: many "socket closed" messages
- The test takes on the order of a minute to complete one pass
of test 049. During that time I typically see 10-20 so... - 10:46 AM Linux kernel client Bug #2573: libceph: many "socket closed" messages
- The sockets have a default timeout of 15 minutes, after which they will close — the idea being that if the socket is ...
- 10:40 AM Linux kernel client Bug #2573 (Resolved): libceph: many "socket closed" messages
- While trying to reproduce a null pointer problem in the client
messenger code I was running xfstests #049 over RBD d... - 02:46 PM Revision c4a607aa (ceph): CrushTester.cc: eliminated old compiler warning of uninitialized pointer.
- Signed-off-by: caleb miles <caselim@gmail.com>
- 02:31 PM Feature #988 (Duplicate): librbd: trivial layering
- replaced by other tasks
- 02:31 PM Feature #988 (Rejected): librbd: trivial layering
- 02:31 PM devops Feature #2589 (Resolved): crowbar: Update barclamp-ceph for Essex, new ceph-cookbooks
- 02:30 PM devops Feature #2588 (Resolved): downburst: multiple, configurable networks to libvirt
- Right now, it hardcodes that a vm only has the "default" network. Make that configurable.
- 02:29 PM devops Feature #2587 (Resolved): sepia: isolated networking on vercoi (manual, a handful)
- One-time switch & linux configuration for a handful of VLANs, manually allocated to people who want to run Crowbar.
- 02:28 PM rbd Feature #2586 (Rejected): rbd: check/take locks on --lock
- if you pass --lock to rbd, take an exclusive lock, do whatever, unlock
- 02:20 PM rbd Feature #2585 (Resolved): rbd: clone command
- A command for the rbd tool to create a child image from a parent. Example:
rbd clone --parent pool/image@snap pool... - 01:56 PM rbd Feature #2467 (Rejected): qemu: implement bdrv_invalidate_cache
- I've tested migration with caching, and read the code, and it looks like this is unnecessary. qemu is doing a flush b...
- 01:47 PM devops Feature #2584 (Resolved): sepia: provide networking, DHCP for dynamic virtual machines
- downburst can provision them really nicely, but right now only static networking works. To fix that, we need DNS to w...
- 01:40 PM devops Feature #2583 (Resolved): crowbar: change barclamp-nova to use rbd
- The nova proposal needs to point to a ceph proposal. Look at how nova&glance use mysql.
barclamp-chef should inclu... - 01:25 PM Feature #1964 (Rejected): ferro: Create a cloud-init OVF config that reimages a machine
- Dell's vMedia functionality is awfully buggy, aborting this plan (for now?).
- 01:25 PM Feature #1965 (Rejected): ferro: Machine management state machine (fake actions)
- Dell's vMedia functionality is awfully buggy, aborting this plan (for now?).
- 01:24 PM Feature #1966 (Rejected): ferro: Connect actions to state machine
- 01:20 PM Feature #1966: ferro: Connect actions to state machine
- Dell's vMedia functionality is awfully buggy, aborting this plan (for now?).
- 01:21 PM Feature #1967 (Rejected): ferro: Single API endpoint that delegates to machine managers
- 01:20 PM Feature #1967: ferro: Single API endpoint that delegates to machine managers
- Dell's vMedia functionality is awfully buggy, aborting this plan (for now?).
- 01:20 PM Feature #1968 (Rejected): ferro: Batch resource allocation (not fair, no quotas yet)
- Dell's vMedia functionality is awfully buggy, aborting this plan (for now?).
- 01:20 PM rbd Bug #2522: xfstest #219
- The problem here appears to be that the output of the repquota
command is not what's expected. I think the group qu... - 01:17 PM Feature #1962 (Rejected): ferro: Trigger vMedia boot via IPMI/DRAC
- Dell's vMedia functionality is awfully buggy, aborting this plan (for now?).
- 01:16 PM Feature #1961 (Rejected): ferro: Python wrapper for vmcli (using gevent)
- Dell's vMedia functionality is awfully buggy, aborting this plan.
- 01:12 PM Feature #1963 (Closed): ferro: OVF Environment creation as a library
- downburst actually ended up containing this logic, not OVF but still cloud-init.
- 01:04 PM rgw Feature #2517 (Fix Under Review): rgw: limit number of buckets per user (configurable per user)
- 01:03 PM Feature #2582 (Resolved): set up chart.io + mysql (or equivalent) infrastructure for tracking perf
- 12:44 PM Linux kernel client Bug #2287 (Resolved): rbd: crashes with 10Gbit network and fio
- This looks like the bio->iter problem, which is now fixed by commit:43643528cce60ca184fe8197efa8e8da7c89a037 in ceph-...
- 12:38 PM Feature #2581 (Resolved): perf: investigate 0.47.2 precise vs 0.46 oneiric discrepancy
- 12:37 PM Feature #2580 (Resolved): perf: investigate poor performance at 10 osds per node
- 12:32 PM Feature #2578 (New): rados ager
- aging function that is invoked (probably) similarly to rados bench, ideally using the same bencher abstraction so tha...
- 12:30 PM Feature #2577 (Resolved): teuthology: blktrace task
- * run blktrace on the osds' disks.
* put results in the archive dir
* maybe an optional start delay, duration, ... - 12:30 PM Feature #2576 (Resolved): perf: 0.48 on long-term clusters
- 12:29 PM Feature #2575 (Resolved): perf: 0.48 numbers
- populate the spreadsheet with values from 0.48
- 11:43 AM Messengers Bug #2569 (Need More Info): msgr: connect_rank crash
- I'm attempting to reproduce this, but what's available right now is just the teuthology log — it didn't pull off any ...
- 09:57 AM Messengers Bug #2569 (Resolved): msgr: connect_rank crash
- ...
- 11:31 AM devops Feature #2574 (Resolved): crowbar: use data disks automatically, journal inside data directory
- Crowbar sets node['crowbar']['disks'] to an array of disks. First one is used for the OS, and disk['usage'] is set to...
- 11:20 AM rbd Cleanup #2347 (Resolved): The rbd help text is misleading on required arguments
- commit:67710a65c7cd1173c73c40241572d615dd7da1f3
- 11:06 AM devops Feature #2415 (Fix Under Review): upstart: support radosgw
- 11:02 AM Cleanup #2331 (Resolved): Makefile.am:182: `lib/libgtest.a' is not a standard libtool library name
- commit:66553d25f09f0d0cea735a862a228060b72c0ce6
- 10:30 AM rbd Bug #2572 (Resolved): krbd: writeback errors?
- While trying to reproduce a null pointer messenger problem,
I kept hitting messages like this after some (fairly ran... - 10:29 AM Feature #2571 (Resolved): sepia: enable virtualization
- 10:27 AM rbd Bug #2535: rbd: random data corruption in vm
- Sage Weil wrote:
> Guido Winkelmann wrote:
> > Sage Weil wrote:
> > > Are there multiple partitions or is LVM on t... - 10:03 AM Linux kernel client Bug #2389: rbd: hung xfstest 67
- ubuntu@teuthology:/a/nightly_coverage_2012-06-13-a/7559
- 09:55 AM Linux kernel client Bug #2389: rbd: hung xfstest 67
- ubuntu@teuthology:/a/master-2012-06-12_16:17:15/7465
- 10:02 AM Linux kernel client Bug #147: lockdep: possible irq lock inversion dependency w/ osdc->request_mutex and con->mutex
- ubuntu@teuthology:/a/nightly_coverage_2012-06-13-a/7579
ubuntu@teuthology:/a/nightly_coverage_2012-06-13-a/7587
<... - 09:59 AM CephFS Bug #1947: mds: SIGBUS during _mark_dirty
- ubuntu@teuthology:/a/nightly_coverage_2012-06-13-a/7526
- 09:23 AM rbd Feature #2568 (Resolved): qa: run xfstests on qemu+rbd
- This will build on #2566:
* stage xfstests on vdb, like a regular workunit, and:
* map additional rbd images to r... - 09:21 AM rbd Feature #2567 (Resolved): qa: add qemu+rbd jobs to qa suite
- Add a bunch of workunits to the qa suite that will run on top of rbd inside a vm.
- 09:20 AM rbd Feature #2566 (Duplicate): teuthology: task to run rbd workunits in a vm
- teuthology task that will:
* download workunit vm
* create and format rbd image
* mount, stage a workunit in rbd... - 02:16 AM Revision c06e4075 (ceph): osd: reimplement OSDCap struct
- The old OSDCaps had a few undesireable features:
- deny
- weird 'default permissions' semantics when auid matches ...
06/12/2012
- 08:58 PM Revision 6e551f73 (ceph): init-ceph: make 'status' report running version
- Try to report the running version with 'status'.
Backport: dho
Signed-off-by: Sage Weil <sage@inktank.com> - 08:48 PM Feature #2564 (Resolved): teuthology: install kernels from local dir
- 08:01 PM Revision f822c025 (ceph): PG: track purged pgs during active
- See bug #2462.
The following sequence could cause a log assuming a non-empty pg
to an empty replica:
1. primary sen... - 07:48 PM Revision e9390bb4 (ceph): Merge branch 'wip-keyrings'
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 06:50 PM Revision 4ec4b477 (ceph): ceph_argparse: make entityname parsing error more helpful
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:50 PM Revision 8b5336a1 (ceph): osd: simplify session peer type check
- Check the authenticated peer name directly; don't store a copy in the
OSDCaps struct. Also set the entity_name membe... - 06:50 PM Revision 72edd353 (ceph): osdcaps: drop dead peer_type code
- Not sure what this wasn intended for.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:50 PM Revision 500c72e8 (ceph): config: make meta expansion in set_val optional
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:50 PM Revision d422bf15 (ceph): config: expand any config variable in config
- This is currently broken wrt 'foo' vs 'foo_bar', but otherwise works.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:50 PM Revision ce79f9e6 (ceph): config: improve variable substitution
- - allow ${foo_bar}
- prevent $foogarbage from substitution variable 'foo'
- use std::string throughout
- improve test... - 06:50 PM Revision eeeb5993 (ceph): mds: add mds_data config
- This is where the keyring will live. Eventually more may move in too.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:50 PM Revision e958efa2 (ceph): new default keyring location for daemons
- $osd_data/keyring
$mds_data/keyring
Fixes: #2498
Signed-off-by: Sage Weil <sage@inktank.com> - 06:50 PM Revision ca2010ee (ceph): vstart.sh: set data dirs instead of keyring locations
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:50 PM Revision 6f9ecef7 (ceph): rgw: default keyring to $rgw_data/keyring
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:50 PM Revision 4cc122cc (ceph): entity_name: is_*() methods
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:29 PM Revision b88a5e53 (ceph): crush: fix retry histogram array overflow due to indexing error
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 06:28 PM Revision 37dea2d8 (ceph): cls_rgw: use updated internal omap api
- These were changed by 23ebc093a64a9c9812124ba6b87e301f95a53a5c.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:27 PM Revision 6fd80d3e (ceph): cls_rgw: fix CLS_LOG macro usage
- Now takes a level.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:19 PM Revision 42539daf (ceph): Merge branch 'wip-2543' of github.com:ceph/ceph into wip-2543
- 06:15 PM Revision 1fdd411a (ceph): crush: fix retry histogram array overflow due to indexing error
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 05:54 PM Revision ddc9b279 (ceph): mapper.c: fixed array indexing error.
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 05:10 PM Revision c31b4e31 (ceph): remove ceph-kdump-copy
- Moved to its own repo.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:08 PM Revision d64600df (ceph): debian: limit build archs
- We depend on leveldb, which only builds on
amd64 armel armhf i386 ia64 mipsel
Reported-by: Laszlo Boszormenyi (GCS... - 02:58 PM Bug #2462 (Need More Info): osd/PG.cc: 402: FAILED assert(log.head >= olog.tail && olog.head >= l...
- f822c0257e4c7fad181332cd149205ad15a8b9db
See the commit description. Unfortunately, I don't really have evidence ... - 02:55 PM Bug #2563 (Resolved): leveldb corruption
- This was also mentioned once in the mailing list.
ceph version 0.47.2 (commit:8bf9fde89bd6ebc4b0645b2fe02dadb1c17a... - 02:40 PM rbd Feature #2561: rbd: copyup command
- What? How does a class function of any kind provide atomicity in cross-OSD data copies?
- 02:37 PM rbd Feature #2561: rbd: copyup command
- 'rbd copyup pool/image' command to copy any missing objects up from the parent. simple O(n) operation that leverages...
- 02:11 PM rbd Feature #2561 (Resolved): rbd: copyup command
- 'rbd copyup pool/image' command to copy any missing objects up from the parent. simple O(n) operation that leverages ...
- 02:39 PM rbd Feature #2562 (Resolved): librbd: open parent images, read path, write path
- - when we open an image, open the parent image too.
- make reads fall through to parent
- guard writes beyond paren... - 02:05 PM rbd Feature #2560 (Resolved): rbd: safe parent deletion
- - maintain map of parent/child pairs in each child pool...
- 02:04 PM rbd Feature #2531: rbd: fencing broken clients
- As I see it, we have two options that we need to choose between.
1) We can add fencing to librbd and let anybody do ... - 01:58 PM Bug #2550: logrotate: SIGHUP upstart jobs too, not just sysvinit
- The instance jobs make this a bit trickier. Either process "initctl list" output or copy the logic that walks the /va...
- 01:04 PM Bug #2550 (Resolved): logrotate: SIGHUP upstart jobs too, not just sysvinit
- 01:55 PM rbd Feature #2559 (Resolved): cls_rbd: copyup method
- - client provides object content
- if object exists, fail with EEXIST (or 0, or something)
- if object does not exi... - 01:54 PM rbd Feature #2558 (Resolved): cls_rbd: child/parent methods
- On the new image header:
- set_parent(poolid, image (maybe id, maybe name), snapid)
On the per-pool child list:
... - 01:52 PM rbd Feature #2557 (Rejected): QEMU support for image locking
- We should convert QEMU to make use of rbd cooperative locking, once it's done (#1480).
And any other appropriate c... - 01:50 PM rbd Feature #2556 (Resolved): rbd tool: break image locks
- Once #1480 is done, expose lock breaking via the rbd tool.
- 01:47 PM devops Feature #2555 (Rejected): chef: SECURITY: Re-evaluate where configuration & key handoff gets stored
- The current setting seems to mean root on all chef nodes (even ones not running Ceph), and all knife users, have full...
- 01:44 PM devops Feature #2554 (Rejected): chef: open question: How do we discover what disks we should use as Cep...
- For Crowbar, see #2574.
- This is somewhat a dangerous operation, run accidentally it will clobber a lot of data. ... - 01:43 PM devops Feature #2553 (Closed): crowbar: open question: What's the correct way to add RBD support to the ...
- We'll need to get set --volume-driver etc in nova.conf,
glance-api.conf, etc. So I guess we need to (temporarily) fo... - 01:36 PM devops Feature #2415 (In Progress): upstart: support radosgw
- 01:21 PM devops Feature #2552 (Rejected): chef: admin tool to generate config in json (uuid, secret)
- The environment needs things like...
- 01:12 PM Bug #2551 (Rejected): leveldb broke "make distcheck"
- ...
- 01:03 PM devops Feature #2549 (Resolved): ceph-disk-prepare: take fstype, mkfs and mount options from ceph.conf
- See #2548 for similar need.
- 01:02 PM devops Feature #2548 (Resolved): ceph-disk-activate: take mount options from ceph.conf
- 01:02 PM devops Feature #2547 (Resolved): ceph-disk-prepare: handle partitioning and mkfs
- spawn gdisk in a subprocess.
How much protection do admins need to avoid ceph-disk-prepare /dev/sda mistakes? - 01:00 PM devops Feature #2546 (Resolved): ceph-disk-prepare: take fsid from ceph.conf (support --cluster=name)
- 12:49 PM devops Feature #2498 (Resolved): standardize keyring locations for daemons
- 10:56 AM Bug #2545 (Resolved): init-ceph: stops if one instance fails to start
- 10:52 AM Bug #2543 (Resolved): crush: invalid pointer when outputting local retry histogram for large rang...
- 10:10 AM rbd Bug #2535: rbd: random data corruption in vm
- Guido Winkelmann wrote:
> Sage Weil wrote:
> > Are there multiple partitions or is LVM on the disk, or is the file ... - 10:07 AM rbd Bug #2535: rbd: random data corruption in vm
- Sage Weil wrote:
> Are there multiple partitions or is LVM on the disk, or is the file system on the raw device?
... - 09:29 AM rbd Bug #2535: rbd: random data corruption in vm
- Are there multiple partitions or is LVM on the disk, or is the file system on the raw device?
- 05:32 AM rbd Bug #2535: rbd: random data corruption in vm
- Am Montag, 11. Juni 2012, 09:30:42 schrieb Sage Weil:
> If you can reproduce it with 'debug filestore = 20' too, tha... - 05:29 AM rbd Bug #2535: rbd: random data corruption in vm
- The bug also does not seem to have any effect with the setting "filestore fiemap = false" in ceph.conf.
- 02:27 AM Bug #2544 (Closed): Help text for "usage show" identical to "usage trim"
- cerr << " usage show show usage (by user, date range)\n";
cerr << " usage trim ... - 01:36 AM Revision 6a3ec401 (ceph): Merge remote-tracking branch 'gh/wip-2516-2'
- Reviewed-by: Sage Weil <sage@inktank.com>
06/11/2012
- 11:39 PM Revision a3f86b80 (ceph): rgw: usage statistics also count num of ops/successful_ops
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 10:48 PM Revision d023cf5c (ceph): debian: move ./configure to correct rules section
- Signed-off-by: Laszlo Boszormenyi (GCS) <gcs@debian.hu>
- 10:48 PM Revision d63aca33 (ceph): debian: remove dup python build-dep
- Reported-by: Laszlo Boszormenyi (GCS) <gcs@debian.hu>
Signed-off-by: Sage Weil <sage@inktank.com> - 10:27 PM Revision af16f459 (ceph): upstart: Read crush location and weight from ceph.conf.
- This introduces two new config variables, osd_crush_location
and osd_crush_weight. Not currently included in config_o... - 10:22 PM Revision 8eb5c9b8 (ceph): mon: allow keys to be cleared in ceph osd crush set ... loc key/values
- If we encounter a 'key=' with no value, clear any previous value for that
key, so that
'a=foo b=bar a='
is equival... - 10:13 PM Revision 6d8d0592 (ceph): rgw: fix cli test
- Get it up to date with latest cli changes.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 10:09 PM Revision 9a1ea4ba (ceph): rgw: usage log cleanups
- Also, recalc_round_timestamp should be done under lock.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:59 PM Revision 5959798b (ceph): Merge pull request #13 from fghaas/rgw-manpage
- doc: update examples in radosgw-admin man page
- 09:49 PM Revision 753207c3 (ceph): doc: update examples in radosgw-admin man page
- * "user gen" is gone and is now "user create"
* --uid option is mandatory for "user create"
Mailing list thread: htt... - 09:25 PM Revision d2b6e49c (ceph): rgw: rgw_rados related fixes for usage logging
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:17 PM Bug #2543 (Resolved): crush: invalid pointer when outputting local retry histogram for large rang...
- buggered the memory when we are generating the histogram for a large range of x.
- 09:00 PM Revision 046395cb (ceph): rgw/rgw_cls_api.h cleanup
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:25 PM Revision ea2f9552 (ceph): rgw: new config options
- New config options for usage logging:
- rgw_enable_usage_log: enable usage logging
- rgw_usage_log_flush_threshold ... - 08:25 PM Revision baa3aff4 (ceph): rgw: access methods for new usage ops
- Wrappers for new rados class methods, and new RGWRados
methods to handle usage functionality.
Signed-off-by: Yehuda ... - 08:25 PM Revision 744a1b31 (ceph): rgw: usage logger
- Accumulate usage info and flush it periodically.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 08:25 PM Revision 9a56a5b8 (ceph): rgw_admin: usage admin commands
- - radosgw-admin usage show
- radosgw-admin usage trim
Both commands can get --start-date, --end-date, --uid
Signed... - 08:25 PM Revision 9a70ec94 (ceph): rgw: new class methods for handling usage information
- The new methods are:
- user_usage_log_add: add new usage information
- user_usage_log_read: get usage information
... - 07:56 PM Revision d265bb69 (ceph): rgw: don't fail initialization if socket path returns ENXIO
- ENXIO is expected when trying to read the unix domain socket
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 07:31 PM Revision 5792f137 (ceph): workunit: grab 'all' config from the right variable
- 06:57 PM rgw Bug #2542 (Resolved): rgw: support S3 update of metadata
- S3 metadata update is being done by copying of an object to itself with new metadata info.
- 05:36 PM Revision 78c35a44 (ceph): Merge remote-tracking branch 'gh/wip-crush-tunables'
- 04:58 PM Revision 98516834 (ceph): cls_rbd: add get_all_features method
- This is useful for reporting which features an osd supports, and for
testing rados_exec. Update the rados api tests t... - 04:55 PM Revision ee7a027b (ceph): mon: fix pg state logging
- PGMap->num_pg_by_state is a PG state to number of PG in the state
mapping. PGMonitor::update_logger wrongly interpret... - 04:22 PM Feature #1772 (Resolved): rbd: define new on-disk header format
- 11:31 AM Feature #1772 (In Progress): rbd: define new on-disk header format
- 03:17 PM Bug #2540 (Resolved): "ceph osd crush set" should treat "foo=" as if foo wasn't mentioned on the ...
- 03:12 PM Bug #2540 (In Progress): "ceph osd crush set" should treat "foo=" as if foo wasn't mentioned on t...
- 03:09 PM Bug #2540 (Resolved): "ceph osd crush set" should treat "foo=" as if foo wasn't mentioned on the ...
- The current behavior, using an empty string as the name, is quite confusing.
Instead of an error message, a better... - 03:13 PM RADOS Feature #2541 (Resolved): crush: move command to adjust non-leaf node position
- the add or update function is intentionally limited to leaves. allow the hierarchy to be adjusted using a different ...
- 03:08 PM Feature #2510 (Resolved): update on-disk hobject_t encoding to include pool and namespace fields
- 02:13 PM Feature #2539 (Duplicate): ceph should issue timeout message when it can't connect to mon
- I forgot to start the ceph service before issuing ceph -s to check its status. The tool happily
waited forever to c... - 11:31 AM Feature #2496 (Resolved): reinstall pudgy
- 10:32 AM RADOS Feature #2521 (Resolved): crush: control bucket vs device mark-down probabilities independently
- 09:50 AM Linux kernel client Bug #2392: First read of symlink after ceph filesystem mounted gives error
- This is going to be easy to fix once the atomic_open stuff is merged. Real Soon Now.
- 09:40 AM Linux kernel client Bug #2537 (Won't Fix): bad header for RHEL6-like kernels
- That backports tree is very old and not maintained. Assuming you do get it working, you'll have 1-2 year old code. ...
- 05:07 AM Linux kernel client Bug #2537: bad header for RHEL6-like kernels
- Sorry,
I forgot to mention that it implies caps.c and super.h files.
For detecting that kernel is RHEL it is mayb... - 04:28 AM Linux kernel client Bug #2537 (Won't Fix): bad header for RHEL6-like kernels
- Hello,
I tried to compile the kernel module (kclient-0.20) and get a problem with ceph_write_inode:
it is declared ... - 09:33 AM Feature #1773 (Resolved): rbd: class interface for header interaction
- 05:37 AM Revision 5012b73a (ceph): Add test for cls_rbd
- 05:01 AM Revision 5cd33cdd (ceph): workunits/rbd: add workunit for running cls_rbd tests
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 04:59 AM Revision 031d42ad (ceph): workunits/rbd: disable remove_with_watcher test
- This will fail until #2533 is fixed.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 04:45 AM Revision 68f14b40 (ceph): Test old and new rbd formats
- 04:26 AM Revision 04ef5dcc (ceph): Update for new workunit task syntax
- 04:01 AM Bug #2536 (Can't reproduce): librados crashed while getting stat of an object
- librados crashed while getting stat of an object:...
- 01:43 AM Revision 8af8d0e2 (ceph): workunit: allow setting environment variables
- This is useful for e.g. running the same tests against rbd in new and
old formats.
06/10/2012
- 09:58 PM Feature #1400 (Resolved): throw exceptions on unknown encoding
- 09:46 PM Feature #2088: msgr: refactor 2 threads to one
- 09:46 PM Feature #2149: osd: use omap for snap collections
- 09:22 PM Feature #1772: rbd: define new on-disk header format
- 09:12 PM Revision 720aa466 (ceph): Merge remote-tracking branch 'gh/wip-rbd-format'
- 05:47 PM Feature #1773: rbd: class interface for header interaction
- 05:47 PM Feature #1773 (Fix Under Review): rbd: class interface for header interaction
- 05:41 PM Linux kernel client Bug #2389: rbd: hung xfstest 67
- nightly_coverage_2012-06-10-a 6787
- 11:05 AM CephFS Bug #2444: null pointer deference in ceph_d_prune inside kvm
- hi,
same bug here on native x86 and amd64 machines.
It affects debian wheezy and ubuntu 12.04 LTS.
I did not check... - 07:14 AM Revision 3d225461 (ceph): librbd: remove unnecessary notify from add_snap()
- The only caller, snapshot_add(), already does a notify when add_snap()
succeeds.
Signed-off-by: Josh Durgin <josh.du... - 07:14 AM Revision 44e5f3dc (ceph): librbd: ignore RBD_MAX_BLOCK_NAME_SIZE when generating object ids
- The actual data object ids don't need to be artificially restricted in
length. RBD_MAX_BLOCK_NAME_SIZE just limits t... - 12:24 AM Revision 5b40b4b9 (ceph): librbd: add create2 to create an image with the new format
- This will fail if features are requested that the client or server
does not support. Currently there are no features ... - 12:24 AM Revision 857bbccc (ceph): rbd: update for the new format
- No features exist right now, so there are no extra options for them.
The old format is still used by default, and sin... - 12:24 AM Revision 074ffc59 (ceph): rbd.py: add support for creating images in the new format
- The new arguments are optional, so they are backwards compatible.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 12:24 AM Revision 123250b4 (ceph): test_librbd, test_rbd.py: optionally use the new format
- Read the desired features from an environment variable, RBD_FEATURES.
Signed-off-by: Josh Durgin <josh.durgin@inktan... - 12:24 AM Revision a5026303 (ceph): rados: add commands to interact with object maps
- The input values are stored as-is, and any values read are dumped in
hex. Rename listomap to listomapkeys to distingu... - 12:24 AM Revision 3d7925b1 (ceph): workunits/rbd: allow creating images in different formats
- This will allow adding more arguments for testing combinations
of features in the future.
Signed-off-by: Josh Durgin...
06/09/2012
- 09:45 PM Revision b25f2770 (ceph): doc: Segregated set up git from clone.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:06 PM rbd Bug #2535: rbd: random data corruption in vm
- The information that *should* let us fully diagnose:
* set
debug osd = 20
debug filestore = 20
debug ms = ... - 08:04 PM rbd Bug #2535 (Resolved): rbd: random data corruption in vm
- From ML:...
- 04:27 PM CephFS Bug #1947 (Need More Info): mds: SIGBUS during _mark_dirty
- It looks liek this one still lives on:...
- 05:30 AM Revision c5042fec (ceph): CrushTester: some whitespace
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:30 AM Revision f2fa31b3 (ceph): CrushTester: simplify, clean up mark down
- - put it in a separate function
- operate on temporary weight vector, not user-modified input
- guard the whole thing... - 05:30 AM Revision 24364579 (ceph): crushtool: drop useless clitest
- This is an ancient test for an old 'bug' in functionality we're removing.
Also, it is sensitive to tester output, whi... - 05:30 AM Revision 9b0195bf (ceph): CrushTester: randomize mark_down behavior
- When marking a batch of devices down, select which buckets to visit sort
of randomly.
Signed-off-by: caleb miles <ca... - 05:10 AM Revision 83377755 (ceph): debian: ceph depends on python
- Due to the new ceph-disk-* scripts. Newer dists are smart enough to figure
this out, but maverick is not.
Signed-of... - 04:37 AM Revision c526bdb5 (ceph): CrushTester: drop range marking
- This is subsumed by mark-down-ratio 1 with mark-down-bucket-ratio N.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:28 AM Revision 2deac081 (ceph): CrushTester: mark_down_ratio and mark_down_bucket_ratio
- Move functionality to allow user to control bucket vs device mark-down
probabilities independently.
Signed-off-by: c... - 04:28 AM Revision 72580769 (ceph): CrushTester: some cleanup
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 04:28 AM Revision 4921bbb9 (ceph): CrushTester: remove dead code
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 12:22 AM Revision 4551808f (ceph): mon: add 'auth get-or-create' variant that outputs a keyring
- This is more convenient when you're creating daemons, since you want to
write out a keyring file for them. This lets...
06/08/2012
- 11:38 PM Revision bfbed508 (ceph): librbd: use ImageCtx members instead of the old header in resize()
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 11:38 PM Revision 7376a773 (ceph): librbd: Update ImageCtx for new format
- Detect the format when an image is opened by the presence of the
original format header object. Use member variables ... - 11:38 PM Revision 4eb2138e (ceph): librbd: update ictx_refresh to work with both formats
- It now sets the member variables of ImageCtx so other functions
don't have to use the on-disk header. If the features... - 11:38 PM Revision 00f4e841 (ceph): librbd: check that the current snapid for a snap name matches
- Checking that it exists doesn't prevent you from having the snapshot
change out from under you in the following situa... - 11:38 PM Revision 8e51e060 (ceph): librbd: remove on-disk header argument from helper functions
- Make most of them take the parameters they actually use.
trim_image() now takes an ImageCtx, which means remove() mus... - 11:38 PM Revision f1d69639 (ceph): librbd: use cls_client functions for calling class methods
- Use the old or new methods make resize, snapshot add and snapsnhot
remove work with both old and new formats.
Signed... - 11:38 PM Revision ef38394f (ceph): librbd: make rename work with any header format
- Instead of interpreting the header, just copy all the data and
omap values from the original header to the newly name... - 11:38 PM Revision 127b4259 (ceph): librbd: rename md_oid parameters to header_oid
- This is more consistent with the rest of the code now,
and is a bit more clear.
Signed-off-by: Josh Durgin <josh.dur... - 11:38 PM Revision 5bc34f4a (ceph): librbd: validate order before creating an image
- The value must be passed, and it shouldn't be below 4k
(enforced by the command line tool already) or above the
range... - 11:38 PM Revision dcc7c963 (ceph): cls_rbd: add methods for interacting with the new header format
- Add the client side (cls_rbd_client) for testing as well.
librbd will use the functions in cls_rbd_client to interact... - 11:14 PM Bug #2524: librados crashed while connecting to cluster
- Thanks for the update. Yes, we do have different models, including a pool of set number of rados_t instances, etc. Bu...
- 10:37 PM Bug #2524: librados crashed while connecting to cluster
- Xiaopong Tran wrote:
> This is on my system:
> [...]
>
> Does it create a thread to every configured osd or only one... - 09:27 PM Bug #2524: librados crashed while connecting to cluster
- I bumped up the threads-max to:...
- 07:40 PM Bug #2524: librados crashed while connecting to cluster
- This is on my system:...
- 07:17 AM Bug #2524: librados crashed while connecting to cluster
- Sage Weil wrote:
> can you cat /proc/sys/kernel/threads-max ? on my system it's only 127837.
Yeah, for each libr... - 07:09 AM Bug #2524: librados crashed while connecting to cluster
- can you cat /proc/sys/kernel/threads-max ? on my system it's only 127837.
- 03:17 AM Bug #2524: librados crashed while connecting to cluster
- Ah, formatting... sorry...
- 03:15 AM Bug #2524: librados crashed while connecting to cluster
- Alright, more information. I was thinking, maybe it was the max number of open files, or the stack size is too low, s...
- 11:04 PM Feature #2496 (In Progress): reinstall pudgy
- 09:35 PM Revision 8c08482c (ceph): regression: fix new rados, rbd test yamls
- Don't start cluster twice!
- 09:31 PM Revision 60c684a4 (ceph): objclass: add indent settings header
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 09:31 PM Revision e0fda59d (ceph): objclass: pass strings as const references
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 09:31 PM Revision ba56d812 (ceph): cls_rgw: add indent settings header
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 09:31 PM Revision 5750e53e (ceph): test_librbd: don't include a .cc file
- Add it as a source like the rest of the gtests.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 09:31 PM Revision fe46a749 (ceph): class_debug: add indent settings header
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 09:31 PM Revision 715c1f13 (ceph): objclass: allow classes to log at different levels
- Add a logging level parameter to CLS_LOG, and a CLS_ERR that's
analagous to derr.
For now cls_rgw is all logging at ... - 09:31 PM Revision 23ebc093 (ceph): objclass: rename omap methods to be consistent with other interfaces
- The osd ops and the librados methods all distinguish between keys
and values. It's useful to be able to read a bunch ... - 09:31 PM Revision 49059b23 (ceph): objclass: add methods to get keys without values, and set multiple values
- These will be useful in the new rbd header format. This brings the
API into parity with the available OSD ops for oma... - 09:31 PM Revision 8c637f56 (ceph): vstart: debug osd classes when debugging is on
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 09:31 PM Revision 13aa578d (ceph): DBObjectMap: remove extra semicolon
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 09:31 PM Revision 70686c59 (ceph): librbd: remove useless ENOMEM checks
- There will be an exception if memory can't be allocated.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 09:31 PM Revision 92325d0f (ceph): cls_rbd: remove unused test_exec and snap_revert methods
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 09:31 PM Revision fefedc1b (ceph): cls_rbd: add indent settings header
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 09:03 PM Feature #2337 (Resolved): rgw and rados performance numbers
- 10:14 AM Feature #2337: rgw and rados performance numbers
- Actually, the specific sprint test is here:
https://docs.google.com/a/inktank.com/spreadsheet/ccc?key=0AnmmfpoQ1_9... - 09:53 AM Feature #2337: rgw and rados performance numbers
- Results are being posted here:
https://docs.google.com/a/inktank.com/folder/d/0B3mmfpoQ1_94amRLQW5YT3l3OG8/edit - 07:48 PM Revision b2793c42 (ceph): mon: require force argument for 'mds newfs ...'
- This is dangerous, make sure they know what they're doing. I bet <someone>
$1 that Greg asked me to do this original... - 06:55 PM Revision 6df344c7 (ceph): run rados, rbd api tests under thrashing
- 06:34 PM Revision 3eca3604 (ceph): Cleaned some lingering references to "verbose"
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 06:18 PM Revision 3876dbfd (ceph): Merge branch 'wip-crush-tunables'
- Reviewed-by: Sam Just <sam.just@inktank.com>
- 06:17 PM Revision c0a02a4a (ceph): crushtool: refine tunables warning message
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:02 PM Revision 978d5419 (ceph): re-include assert after boost::pool
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:58 PM Revision c04de2b3 (ceph): crush: generate histogram of choose tries
- Optionally populate a histogram of choose descent attempts.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:58 PM Revision dba70eed (ceph): CrushTester: dump histogram of choose attempts
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:58 PM Revision eaad9845 (ceph): CrushTester: clean up output interface
- Multiple accessors. Init in ctor. Avoid temp vars in crushtool.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:58 PM Revision cfbe34d5 (ceph): crushtool: --show-* instead of --output-*
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:58 PM Revision 1a2959ed (ceph): crushtool: add --enable-unsafe-tunables option
- This is required to adjust tunables.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:58 PM Revision 740aa3df (ceph): crush: compile/decompile tunables
- Lines like
tunable <name> <value>
will adjust tunables. Right now only three are defined.
--enable-unsafe-tunabl... - 05:58 PM Revision c4336a3a (ceph): crushtool: arguments to adjust tunables
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:58 PM Revision 48737114 (ceph): CrushTester: optionally output bad mappings
- Optionally dump bad inputs to stdout.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:58 PM Revision 4abb53d4 (ceph): crush: fix leaf recursion if we already collided
- This just saves us some cycles, but does not effect placement results at
all.
Signed-off-by: Sage Weil <sage@inktank... - 04:42 PM rbd Bug #2534 (Resolved): librbd: make sure watch is established on same header version as initial re...
- Right now there's a race where it doesn't.
- 11:16 AM Bug #2533 (Duplicate): osd: watchers tracked by entity_name_t, not by cookie
- In the object info, watchers are tracked in a map<entity_name_t, watch_info_t>, but if there are multiple watchers fr...
- 10:43 AM Feature #1711 (Resolved): chef: multiple monitor support
- Works as of ceph-cookbook.git commit b5cc21bf5b9c3f59474a7dfe38e04ee01b584fa3 and ceph.git commit 7332e9c717fb627d51e...
- 10:12 AM rbd Feature #2531: rbd: fencing broken clients
- I talked to Sam about the combination of blacklisting, bad client writes, and changing primaries that we discussed an...
- 10:11 AM Linux kernel client Feature #26 (Rejected): statlite
- 10:09 AM Linux kernel client Cleanup #2093 (Resolved): ceph-client: messenger: the "to" parameter to read_partial() needs to go
- 10:08 AM Linux kernel client Bug #2395 (Resolved): kernel crash after unmap a rdb device while the cluster is down
- I'm going go assume this is running the older code and close it. If not, let us know!
- 10:06 AM rbd Bug #2478 (New): krbd: unmap on 3.4.0: scheduling while atomic...
- 10:04 AM Linux kernel client Feature #949 (Rejected): rbd: async writes, flush/barrier
- 10:04 AM Linux kernel client Bug #2243 (Resolved): btrfs: warning in orphan_commit_root
- 09:51 AM rbd Bug #2532: rbd command allows passing in -K </path/to/secret>, but long version of (--secret) doe...
- That's probably best. It is always easier though when all subcommands under the main command, rbd in this case used o...
- 09:00 AM rbd Bug #2532: rbd command allows passing in -K </path/to/secret>, but long version of (--secret) doe...
- Oh, i see.
I think the right fix is to make '--secret' and synonym for '--keyfile', and fix up rbd to use the conf... - 08:20 AM rbd Bug #2532: rbd command allows passing in -K </path/to/secret>, but long version of (--secret) doe...
- When I try to use --keyfile=<file> with map, it seemingly fails, but using --secret=<file> succeeds. ...
- 08:13 AM rbd Bug #2532: rbd command allows passing in -K </path/to/secret>, but long version of (--secret) doe...
- This is part of the rbd cmd helper message. It seems that for the map command one uses --secret....
- 07:00 AM rbd Bug #2532: rbd command allows passing in -K </path/to/secret>, but long version of (--secret) doe...
- the option is --keyfile <file>... where did you see --secret <file> documented?
- 05:49 AM rbd Bug #2532 (Resolved): rbd command allows passing in -K </path/to/secret>, but long version of (--...
- While rolling back a snapshot I succeed when I pass in `-K with location of key file, but it looks like I fail when I...
06/07/2012
- 10:57 PM Revision 8b796974 (ceph): crush: make magic numbers tunable
- We have three magic numbers in crush_choose that are now tunable. The
first two control the local retry behavior, in... - 09:38 PM rbd Feature #2531 (Resolved): rbd: fencing broken clients
- 08:57 PM Revision 7332e9c7 (ceph): mon: use mode 0600 throughout
- Fixes: #2526
Signed-off-by: Sage Weil <sage@inktank.com> - 08:50 PM Revision 4fa665c1 (ceph): --summary: add total counts, also note free machines
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 07:22 PM Revision 80939977 (ceph): Merge remote-tracking branch 'gh/mon-auth'
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 06:45 PM Bug #2524: librados crashed while connecting to cluster
- objdump on the NIF shared library.
- 06:29 PM Bug #2524: librados crashed while connecting to cluster
- This is weird, if the problem is caused by resource exhaustion. I run this app on a machine with i7 CPU (with 8 cores...
- 09:24 AM Bug #2524: librados crashed while connecting to cluster
- This assert means that either a malloc or a call to pthread_create failed. It's probably resource exhaustion of some ...
- 04:23 AM Bug #2524 (Won't Fix): librados crashed while connecting to cluster
- Librados crahsed while connecting to the cluster.
Here is some log information. Unfortunately, I don't have more i... - 06:35 PM Revision 07169d2e (ceph): doc: Added mount cephfs with fstab.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:21 PM Revision 7d1b32a0 (ceph): osd: include past_intervals in pg query results
- This will help us figure out *why* nodes are in the prior set.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-... - 06:21 PM Revision 36a39795 (ceph): OSD: _have_pg should return NULL if pg is not in map
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:21 PM Revision ff470104 (ceph): Merge remote-tracking branch 'gh/wip-assert2'
- "So be it"
Reviewed-by: Sam Just <sam.just@dreamhost.com> - 05:19 PM Revision fae1d47a (ceph): deliberately break encoding macros when wrong assert is present
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:18 PM Revision 3571f43c (ceph): misc assert #include cleanup, hackery
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:18 PM Revision a1ae8b6a (ceph): reinclude assert.h after json_spirit
- json_spirit clobbers it!
Signed-off-by: Sage Weil <sage@inktank.com> - 05:08 PM Revision e87a66b7 (ceph): doc: Incorporated Sam's comments.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 04:41 PM Revision 36658552 (ceph): Merge remote-tracking branch 'gh/wip-assert'
- Reviewed-by: Sam Just <sam.just@inktank.com>
- 04:25 PM rbd Documentation #2530 (Closed): Doc: rbd manpage doesn't mention watch; usage does, and it works
- 04:20 PM Tasks #2529 (Resolved): debian: Merge packaging changes from Ubuntu 12.04
- The package in ubuntu is split to ceph-fs-common (mount helpers), ceph-mds (not in main), etc. Merge what makes sense.
- 03:10 PM rbd Bug #2528 (Resolved): Mounted RBD image appears to go read-only after a snapshot is created
- I have been able to repeat this a number of times. Essentially, I create a small rbd device, using the map command in...
- 02:38 PM Revision 3939839b (ceph): doc: Typo fix.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:54 PM Bug #2526 (Resolved): ceph-mon $mon_data_dir/keyring is world readable
- gah... commit:7332e9c717fb627d51efcaa3f31473a2c129e876
- 01:25 PM Bug #2526 (Resolved): ceph-mon $mon_data_dir/keyring is world readable
- Keys to the kingdom, for anyone to grab. ceph-mon --mkfs creates this file, it should enforce the access mode.
ubu... - 01:52 PM rgw Bug #2527 (Resolved): RGW may return 409 Conflict when deleting a bucket
- If a bucket delete call occurs immediately after running a delete operation on the final remaining object in that buc...
- 12:53 PM Bug #2525 (Resolved): librados: some functions are not thread-safe
- Some functions are accessing the osdmap without any locks. There are probably other cases like this. Find and fix all...
- 03:29 AM Revision 44374bc4 (ceph): new variable lock hid lock() function
- 02:19 AM Revision 22863c30 (ceph): mon: set policy for client, mds before throttler
- Otherwise we fail the assert in Messenger::set_policy_throttler()!
Signed-off-by: Sage Weil <sage@inktank.com> - 02:10 AM Revision 71c2877c (ceph): DBObjectMap: fix some warnings
- os/DBObjectMap.cc:197: warning: suggest a space before ';' or explicit braces around empty body in 'for' statement
S... - 01:54 AM Revision 9313cdea (ceph): teuthology-lock: add --summary and --brief options
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Also available in: Atom