Activity
From 09/21/2011 to 10/20/2011
10/20/2011
- 11:28 PM Revision 409c5717 (ceph): coverage: don't remove ceph tarball
- We want to keep it for examining core files, and we're already
fetching it here, once per suite run. - 10:56 PM Revision 49b6c118 (ceph): osd: PG::PriorSet: make debug_pg arg const
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:51 PM Revision fa66e65c (ceph): osd: PgPriorSet -> PriorSet
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:50 PM Revision 7bc855a8 (ceph): osd: PgPriorSet: rename prior_set_affected -> affected_by_map
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:47 PM Revision 78236e4e (ceph): osd: PgPriorSet: remove obsolete comment
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:46 PM Revision 2a870c14 (ceph): osd: PgPriorSet: move prior_set_affected into PgPriorSet
- This is really where it belongs.
Signed-off-by: Sage Weil <sage@newdream.net> - 10:46 PM Revision c2e66fbd (ceph): osd: PgPriorSet: kill whoami; make PG arg strictly optional
- It is only used for the debug output prefix. Make it so we can leave it
out entirely (e.g. for unit tests).
We don'... - 09:12 PM Revision 47e938c0 (ceph): Merge branch 'stable'
- 09:12 PM Revision 2b3bdea9 (ceph): osd: fix requeue_ops
- The ls argument passed to requeue_ops() is a reference, and one of the
methods we call (say, _handle_op) might want t... - 08:59 PM Revision 3b76f9fc (ceph): perfcounters: remove dout
- We can't use this because we're part of libglobal and there is no
g_ceph_context. And i'm too lazy to use cct.
Sign... - 08:58 PM Revision 863e5b04 (ceph): perfcounters: fix unit test
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 08:48 PM Revision 1d002a1e (ceph): Merge remote branch 'gh/wip-unfound'
- 08:16 PM Revision 28df1e91 (ceph): filestore: measure commit interval, latency, journal full count
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 07:45 PM Revision d2dbae97 (ceph): osd: clean up perfcounter names
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 07:43 PM Revision d31e78f6 (ceph): filestore: simplify perfcounter lifecycle
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 07:43 PM Revision b000e4d4 (ceph): filestore: simplify, clean up perfcounters
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 06:34 PM Revision d26488bc (ceph): perfcounters: fix addition/removal
- We are not responsible for deleting removed perfcounters.
Add debugging.
Signed-off-by: Sage Weil <sage.weil@dreamh... - 06:33 PM Revision 7207b819 (ceph): filestore: fix perfcounter definition
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:59 PM Revision 53ad579e (ceph): filestore: fix logger start
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:54 PM Revision d3366ccc (ceph): Merge remote-tracking branch 'github/master' into wip-swift-fix
- 05:52 PM Feature #1420 (Resolved): build release rpms
- this is done the extent that i am willing to spend time on it. hopefully suse will show up at some point and improve...
- 05:45 PM Bug #1636 (Resolved): reweight-by-utilization does not choose good weights
- The existing reweight-by-utilization code didn't make sense - commit:f94a44e688883f2db0971435a5333a8b60c77dec fixes t...
- 04:11 AM Bug #1636 (Resolved): reweight-by-utilization does not choose good weights
- there's a problem distributing the data evenly over all devices.
i'm using v0.36 and have a test setup with two host... - 05:22 PM CephFS Bug #1640 (Resolved): mds: failed assert(trim_to > trimming_pos)
- This happened with bonnie++ on cfuse in teuthology:~teuthworker/archive/nightly_coverage_2011-10-20/729/remote/ubuntu...
- 05:09 PM RADOS Feature #1639 (New): osd: guard against bad objects in cls map functions
- Got this when I accidentally set a bad locator:...
- 04:21 PM Revision 288ccc88 (ceph): perfcounters: clean up interface a bit
- No logger_ prefix necessary.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 04:21 PM Revision daea03ef (ceph): perfcounters: use simple names
- We don't need to uniquely identify ourselves in the global namespace with
the PerfCounter name.. only in the current ... - 02:15 PM Bug #1624: osd crash in HearbeatMap::_check
- commit:2b3bdea9f7bcf9e9f8d4328f62d82ff43e996b3a fixes at least some of these....
- 01:45 PM Bug #1624: osd crash in HearbeatMap::_check
- running this in a loop with logs to try ot catch it
- 12:02 PM Bug #1624: osd crash in HearbeatMap::_check
- And teuthology:~teuthworker/archive/nightly_coverage_2011-10-20/730/remote/ubuntu@sepia50.ceph.dreamhost.com/log/osd....
- 12:00 PM Bug #1624: osd crash in HearbeatMap::_check
- And teuthology:~teuthworker/archive/nightly_coverage_2011-10-20/727/remote/ubuntu@sepia27.ceph.dreamhost.com/log/osd....
- 11:57 AM Bug #1624: osd crash in HearbeatMap::_check
- Happened again in teuthology:~teuthworker/archive/nightly_coverage_2011-10-20/726/remote/ubuntu@sepia41.ceph.dreamhos...
- 02:01 PM Feature #1630 (Resolved): Monitor journal fullness (bytes used, size) via perfcounters
- 01:45 PM Bug #1635 (Duplicate): osd hit suicide timeout in heartbeat_map thread
- 01:28 PM Bug #1588: blogbench on kclient possibly made machine die
- Happened again today - just more transactions timing out in the logs.
- 01:23 PM Bug #1633: osd crash in CryptoKey::decrypt
- Happened again while thrashing in teuthology:~teuthworker/archive/nightly_coverage_2011-10-20/732/remote/ubuntu@sepia...
- 11:52 AM Bug #1530: osd crash during build_inc_scrub_map
- This happened again during cfuse on ffsb (teuthology:~teuthworker/archive/nightly_coverage_2011-10-20/694).
- 09:27 AM Bug #1638 (Won't Fix): Can't create object with large xattrs in a single operation (on extN)
- A single compound operation that does:
- create
- setxattr (small enough to fit but large enough to fill in the e... - 04:45 AM Revision f25879ac (ceph): encoding: add optional features
- Update encode macros to allow a feature bitmask to be passed through
to a classes encode() method.
Signed-off-by: Sa... - 04:22 AM Feature #1637 (Duplicate): OSDs running full take down other OSDs
- this issue has a relation to #1636.
in my test setup of v0.36 when one OSD runs full it gets taken down.
this start... - 04:14 AM Revision 0aa40ea0 (ceph): assert: no 0x before thread id
- There's no 0x prefix in the log lines either. This makes it easier to
copy/paste word and search.
Signed-off-by: Sa... - 03:48 AM Revision 0f0c5947 (ceph): osdmap: uninline big stuff
- Signed-off-by: Sage Weil <sage@newdream.net>
- 12:46 AM Revision a71455c8 (ceph): rgw: properly handle cleaning up of listings
- If a listing you get back from the OSD consists only of
non-existent entries, you still need to handle it and resume ... - 12:46 AM Revision 470742d8 (ceph): cls_rgw: move stat update code after error checks in complete_op
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 12:46 AM Revision 6dc0da4c (ceph): cls_rgw: implement a dir_suggest_changes function.
- This takes a bufferlist of suggested changes to the directory, trims
out any sufficiently old tags, and then applies ... - 12:46 AM Revision 952ebbae (ceph): cls_rgw: add constructors to data structs; don't leak tags on races
- We were leaking tags on races before, since we cut out of the function
before clearing the tag. We don't do that any ... - 12:45 AM Revision 9496732d (ceph): rgw: write and use the check_disk_state function
- This is used to check the actual on-disk state, and encode
suggested updates for the index.
Then cls_bucket_list send...
10/19/2011
- 11:47 PM Revision a5ada568 (ceph): rgw: fix bad snprintf
- 10:35 PM Revision 5de847f3 (ceph): .gitignore: add test_filestore_idempotent
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 10:35 PM Revision b57e8967 (ceph): test_filestore_idempotent: initialize var
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 09:58 PM Revision 7f5f1ec1 (ceph): rgw: implement swift metadata POST
- 04:14 PM Revision cf333152 (ceph): Merge branch 'stable'
- Conflicts:
src/mon/OSDMonitor.cc
src/osd/OSD.cc - 03:15 PM Bug #1526: log bound mismatch after thrashing with bonnie
- another occurance, running on swab. This may have led to pg version reset....
- 03:02 PM Bug #1635 (Duplicate): osd hit suicide timeout in heartbeat_map thread
- This was while thrashing with radosbench, during peering, with osds 3 and 6 marked out.
From teuthology:~teuthworker... - 02:46 PM Bug #1634 (Can't reproduce): osd: crash decoding non-existent object_info_t
- From teuthology:~teuthworker/archive/nightly_coverage_2011-10-19/680/remote/ubuntu@sepia28.ceph.dreamhost.com/log/osd...
- 12:05 PM Bug #1633 (Resolved): osd crash in CryptoKey::decrypt
- From teuthology:~teuthworker/archive/nightly_coverage_2011-10-19/682/remote/ubuntu@sepia72.ceph.dreamhost.com/log/osd...
- 11:59 AM Bug #1632 (Can't reproduce): osd: crash in dequeue_op
- During ffsb:...
- 11:26 AM Bug #1631 (Can't reproduce): osd: failed assert(repop_queue.front() == repop)
- This happened on two osds during a multiple_rsync workunit (teuthology:~teuthworker/archive/nightly_coverage_2011-10-...
- 10:51 AM Feature #1630 (Resolved): Monitor journal fullness (bytes used, size) via perfcounters
- 05:33 AM Revision b297d1ed (ceph): osdmap: make encoding based on features
- Instead of relying on the caller to decide whether encode_old_client()
is appropriate, pass in the feature set and en... - 05:26 AM Revision 6e2018ce (ceph): osd: normalize encoding of pg_pool_t
- Instead of using a cumbersom C struct, move members into pg_pool_t and
use normal encode/decode methods.
Signed-off-... - 05:26 AM Revision cee1b27f (ceph): crush: clean up encoder/decoder
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:25 AM Revision 954d3f9b (ceph): use WRITE_CLASS_ENCOER macro when possible
- 05:25 AM Revision 9d93bfce (ceph): encoding: WRITE_CLASS_ENCODER_MEMBER -> WRITE_CLASS_MEMBER_ENCODER
- Signed-off-by: Sage Weil <sage@newdream.net>
10/18/2011
- 11:52 PM Revision 83914d22 (ceph): test_filestore_idempotent: simple tool to generate a worklaod of non-id...
- Generate a workload of operations that are non-idempotent. These are:
transaction {
clone A -> A.($n-1)
writ... - 11:52 PM Revision 3e92aace (ceph): filestore: tolerate EEXIST on mkcoll when not-btrfs
- For non-btrfs file systems we should tolerate EEXIST because we may
replay the event more than once.
Signed-off-by: ... - 11:41 PM Revision ba165fec (ceph): rgw: some swift obj metadata related fixes
- 11:18 PM Revision 13b0bbb3 (ceph): mds: handle xattrs on inode creation
- Allow mknod, mkdir, symlink, create to provide xattrs for the new
inode. This will be used by the kclient to set ACL... - 11:04 PM Revision 7ea07832 (ceph): radosgw-admin: fix conflict with KeyType in libnss
- rgw/rgw_admin.cc:459:6: error: using typedef-name 'KeyType' after 'enum'
/usr/include/nss3/keythi.h:69:3: error: 'Key... - 08:28 PM Revision ed5e4341 (ceph): rgw: add content-type to index dirent
- 06:42 PM Revision da6cdfdd (ceph): osd: PgPriorSet: cur -> probe
- Rename cur to probe, the set of OSDs we need to probe in order to
successfully peer.
Signed-off-by: Sage Weil <sage@... - 06:40 PM Revision 4e5242e0 (ceph): osd: PgPriorSet: restructure lost checks for prior set
- When we add down osds to the cur set, we block peering because there
are OSDs that may have data we need and they are... - 06:01 PM Revision 298dbbe6 (ceph): rgw: workqueue suicide timeout is infinity
- 04:49 PM Bug #1629 (Can't reproduce): pgs stuck degraded (only mapped to 1 osd)
- From teuthology:~teuthworker/archive/nightly_coverage_2011-10-18/636/teuthology.log:...
- 04:42 PM Bug #1624: osd crash in HearbeatMap::_check
- argh, the tarball is already gone:
# wget http://ceph.newdream.net/gitbuilder/output/sha1/e6dbd7141bd8b4403f3b931f... - 12:00 PM Bug #1624 (Resolved): osd crash in HearbeatMap::_check
- Logs with debugging are in vit:~joshd/thrash_stuck_active4. This happened on osds 0 and 4:...
- 03:35 PM Bug #1628: segfault attempting to map an rbd snapshot
- This is a bug in the rbd command line tool - it accepts snapname but doesn't use it for map/unmap. Additionally, it d...
- 03:18 PM Bug #1628 (Resolved): segfault attempting to map an rbd snapshot
- ...
- 03:08 PM Bug #1626: ceph-mon HA not working right; all must be up
- Sorry to dribble this in: it seems with one mon down and voted out, "ceph -s" takes <1sec 66% of the time, ~3sec 33% ...
- 03:07 PM Bug #1626: ceph-mon HA not working right; all must be up
- Oh sorry, what I see with vstart is a 10-second timeout until the mons vote mon.c out. This is *not* what Carl report...
- 03:05 PM Bug #1626: ceph-mon HA not working right; all must be up
- Carl saw it originally. Easy to repro with vstart:...
- 02:48 PM Bug #1626: ceph-mon HA not working right; all must be up
- where did you see this?
- 02:28 PM Bug #1626 (Can't reproduce): ceph-mon HA not working right; all must be up
- If mon.gamma is down, "ceph -s" hangs trying to connect to all three ceph-mon. The paxos majority rule system does no...
- 02:52 PM Bug #213: non-idempotent transactions (clone) under ext3 may not replay correct result
- FWIW even if we know what not to replay, we could still be screwed with ext4 (which does not commit everything in ord...
- 02:25 PM Bug #213: non-idempotent transactions (clone) under ext3 may not replay correct result
- Tommi Virtanen wrote:
> Isn't the idempotency in that case "clone foo_head -> foo_2 IFF foo_2 does not exist" ?
T... - 02:06 PM Bug #213: non-idempotent transactions (clone) under ext3 may not replay correct result
- Isn't the idempotency in that case "clone foo_head -> foo_2 IFF foo_2 does not exist" ?
- 02:37 PM Bug #1627 (Can't reproduce): ceph-mon memleak if ceph-osd cluster ip is not reachable, but public...
- ...
- 02:25 PM Feature #1625 (Rejected): changing ceph-mon ip address needs monmap change on every mon machine
- Moving mon.{alpha,beta,gamma} to new IP addresses was a fairly convoluted process. This would be nice if it was simpl...
- 02:15 PM Feature #641: allow logs to be piped to an external program
- This is feature creep. If you want to process the logs asap in another process, just have it get ceph stdout as stdin...
- 11:19 AM Bug #1620 (Resolved): rgw suicide due to heartbeat timeout
- Fixed, commit:298dbbe64f8b0738ec58db43782813d0686717c7. Basically a 0 value for the rgw suicide timeout should do the...
- 11:01 AM Bug #1588: blogbench on kclient possibly made machine die
- This happened again yesterday and today with different machines. Both times, the only unusual thing in kern.log was t...
- 01:59 AM Revision 0a027599 (ceph): osd: PgPriorSet: simplify (and change) CRASHED logic
- Any single OSD from a given interval surviving is sufficient to ensure
that an ACKed write during that interval was c... - 01:57 AM Revision f7ef94d3 (ceph): osd: PgPriorSet: update comment terms a bit
- Signed-off-by: Sage Weil <sage@newdream.net>
- 12:51 AM Revision bbb06d34 (ceph): osd: do not short-cut up_thru update for new PGs
- Commit e731885d2550ee985bf875ab5bb5faf28f1693eb made it possible for
a new PG to go active without forcing the OSDs u... - 12:44 AM Revision 57e0ab74 (ceph): osd: PgPriorSet: clean up per-interval var names
- We don't actually use any_lost_now, but it makes the logic easier
to understand to have it there.
Signed-off-by: Sag... - 12:44 AM Revision 53381364 (ceph): osd: PgPriorSet: clean up comments a bit
- Signed-off-by: Sage Weil <sage@newdream.net>
- 12:44 AM Revision 33b33f7e (ceph): osd: PgPriorSet: remove unused PG member
- Signed-off-by: Sage Weil <sage@newdream.net>
- 12:44 AM Revision 113b7833 (ceph): osd: PgPriorSet: revert start_since_joining check
- Commit 5b78f5db8c200edcc949033e1badae70fecd2e08 added a check to
prevent some sort of badness when osds were marked l... - 12:44 AM Revision 3dda4465 (ceph): osd: PgPriorSet: remove up_thru crap
- This was added way back in 1cf9bebc8e5063f5f311d33e7735bcc9286e98ce,
but as far as I can tell it didn't make any sens... - 12:44 AM Revision f89f4d9b (ceph): osd: PgPriorSet: do not include UP osds in prior.cur
- The up osds are not (directly) relevant since they are not necessarily
members of the PG. We only care about acting ... - 12:09 AM Revision 9dfa1105 (ceph): rgw: fix swift account and containers listing limits
10/17/2011
- 11:48 PM Revision c5638b70 (ceph): osd: PgPriorSet: any_survived -> any_is_alive_now
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:13 PM Revision e6dbd714 (ceph): doc: Change diagram to have radosgw closer to direct rados access.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:35 PM Revision 3c90c0d4 (ceph): add singleton lost-unfound
- 10:32 PM Revision 4ec37b23 (ceph): add lost_unfound task
- Also some misc useful bits to ceph_manager.
- 10:21 PM Revision edcd4d97 (ceph): rgw: some more swift fixes
- 09:45 PM Revision 83cf3fef (ceph): Expect 'wrongly marked me down' messages during thrashing
- 09:42 PM Revision bcded7f1 (ceph): ceph: add whitelist for cluster log errors
- Some messages are expected when thrashing osds or creating unfound
objects.
Fixes: #1622 - 09:13 PM Revision 0bad37e3 (ceph): streamtest: do mkfs
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:12 PM Revision 525a610f (ceph): streamtest: print to stdout
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:49 PM Revision 9c956049 (ceph): mkcephfs: copy ceph.conf to /etc/ceph/ceph.conf (when -a)
- You can disable this with --no-copy-conf.
Signed-off-by: Sage Weil <sage@newdream.net> - 05:40 PM Revision fba220ec (ceph): nuke: reset syslog configuration after rebooting
- Previously we removed a file and rebooted without syncing, so the file
was never deleted. - 04:56 PM Bug #1623 (Can't reproduce): ceph-osd fails to bind socket
- ...
- 03:51 PM Revision 9baf5ef4 (ceph): ceph.spec: don't chkconfig
- This was fighting with suse insserv. Still needs some cleanup.
Signed-off-by: Sage Weil <sage@newdream.net> - 03:50 PM Revision 21d941e8 (ceph): ceph.spec: work around build.opensuse.org
- The redhat-rpm-config isn't installed on build.opensuse.org, which means
the processor is set to i386 instead of some... - 03:49 PM Revision 195a484b (ceph): ceph.spec: capitalize first letter to make rpmlint happy
- Signed-off-by: Sage Weil <sage@newdream.net>
- 03:35 PM Revision a6f3bbb7 (ceph): v0.37
- 03:27 PM Bug #1473 (Resolved): osd assert failure: FAILED assert(0 == "oi disagrees with stat, or error c...
- 03:26 PM Bug #1473: osd assert failure: FAILED assert(0 == "oi disagrees with stat, or error code on stat")
- At least the recent instances of this were probably caused by the btrfs xattr bug (#1612).
- 03:25 PM Bug #1486 (Resolved): osd: 0-length meta/pginfo_* files
- 10:10 AM Bug #1486: osd: 0-length meta/pginfo_* files
- I saw this on alexandria, and it was caused by:
1- EMFILE (too many open files)
2- filestore wasn't assering on... - 03:20 PM Bug #1612 (Resolved): osd/PG.cc: 3839: FAILED assert(missing[oid].need <= v)
- This was caused by a btrfs xattr bug. I got a patch back from josef and pushed it to the dho kernel.
- 03:05 PM Feature #1622 (Resolved): teuthology: whitelist ceph.log entries
- Implemented in teuthology and whitelisted 'wrongly marked me down' messages for thrashing jobs in the suite.
- 10:08 AM Feature #1622 (Resolved): teuthology: whitelist ceph.log entries
- Need to be able to do this to make certain tests pass. notably thrashing and the new lost_unfound.
- 03:37 AM Revision ca8f6036 (ceph): osd: fix assemble_backlog
- This was written assuming that le->prior_version wouldn't be the version
that we have locally on disk. Not always tr... - 03:37 AM Revision 2fdec7b8 (ceph): osd: fix add_next_event Missing::item::have
- The missing set should be accurate up to the current point in the log. The
log_tail has no bearing on that, nor does...
10/15/2011
- 05:56 AM Revision c1cabf56 (ceph): ceph: don't crash when sending message to !up osd
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:03 AM Revision 615689a9 (ceph): osd: implement lost_revert
- Roll back to the last available version of an object. If there is no
available version, delete it.
Leave the door o... - 04:03 AM Revision 3a046774 (ceph): osd: pull old version to revert to
- If we are the primary, and are doing a LOST_REVERT, pull the old version
of the object and update the version when we... - 04:02 AM Revision 03cd1088 (ceph): osd: adjust LOST log entry types; simplify log entry type strings
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:02 AM Revision ad39d814 (ceph): osd: all_unfound_are_queried_or_lost
- The check to make isn't whether all locations are lost, but whether all
locations are either lost or have been querie... - 04:02 AM Revision 81f36c2d (ceph): osd: remove superfluous write_info calls
- - merge_log() will write_info (and log) as needed
- Activate() will do the same
Signed-off-by: Sage Weil <sage@newdr... - 04:02 AM Revision c3fa0783 (ceph): messages/MOSDPG*: clean up output a bit
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:02 AM Revision a3be6651 (ceph): osd: fix share_pg_log()
- We need to handle a log message in the ReplicaActive state. And set the
epoch properly when we send it.
Signed-off-... - 04:02 AM Revision 22684f25 (ceph): osd: pass version explicitly to pull
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:02 AM Revision efe5abfc (ceph): osd: make C_OSD_CommittedPushedObject::op optional
- This lets us reuse this helper for commiting recovery ops that aren't a
result of a push.
Signed-off-by: Sage Weil <... - 04:02 AM Revision 51158820 (ceph): osd: factor out recover_primary_got() helper
- This handles the missing set and lsat_complete adjustment when we recover
an object on the primary.
Signed-off-by: S... - 04:02 AM Revision 43bd49d8 (ceph): osd: fix up PG::Missing methods a bit
- Pass in iterators when possible. Stack methods instead of duplicating
functionality.
Signed-off-by: Sage Weil <sage... - 04:02 AM Revision 7c05c1fe (ceph): osd: simplify share_pg_log
- Use Log::copy_after(). Drop the useless argument. Strip out the broken
LOST logic.
Signed-off-by: Sage Weil <sage@... - 04:02 AM Revision a8760e50 (ceph): osd: fix up mark_all_unfound_lost so that it actually works
- Well, it works given our weak definition of LOST.
- use ObjectContexts properly
- move into ReplicatedPG
- no need f... - 03:43 AM Revision 35dab57f (ceph): msg: add MCommand, MCommandReply message types
- These are similar to MMonCommand[Ack], but aren't PaxosServiceMessage
children, don't include the command in the repl... - 03:43 AM Revision beaca74d (ceph): msg: entity_name_t::parse()
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 03:43 AM Revision a37d6d03 (ceph): cephtool: ability to send commands directly to osds
- This makes commands beginning with 'tell <target>' magic in that they go
to the given target instead of to the monito... - 03:43 AM Revision 7f687fca (ceph): osd: handle (and reply to) direct MCommands
- Signed-off-by: Sage Weil <sage@newdream.net>
- 03:43 AM Revision f868e382 (ceph): osd: remove some pg stats debug cruft
- Signed-off-by: Sage Weil <sage@newdream.net>
- 03:43 AM Revision b35d96d5 (ceph): mon: feed MPGStats tids back through the MPGStatsAck
- Signed-off-by: Sage Weil <sage@newdream.net>
- 03:43 AM Revision 1cbcc953 (ceph): osd: process commands in a workqueue
- This lets us do commands that can potentially block. For example:
- flush pg stats to osd
- request (and wait for... - 03:43 AM Revision 84a6f6e7 (ceph): osd: implement 'flush_pg_stats' command
- This flushes the current pg stats to the monitor, and blocks until the
monitor commits it.
Signed-off-by: Sage Weil ... - 03:21 AM Revision 502fbba5 (ceph): paxos: trim extra state dirs
- OSDMonitor, for instance, stores both an "osdmap" and "osdmap_full" for
each state. Trim them both.
Signed-off-by: ... - 03:20 AM Revision 6d123067 (ceph): PG: call set_last_peering_reset in Started contructor
- Calling it here should cover all possible replica and primary peering
resets.
Signed-off-by: Samuel Just <samuel.jus...
10/14/2011
- 11:49 PM Revision b5c60623 (ceph): filestore: assert on any unexpected error
- Right now, the only errors we expect out of the underlying filesystem are
-ENOENT, -ENODATA, or (as a workaround for ... - 08:31 PM Revision ba41e6c7 (ceph): osd: send full map if we don't have sufficiently old incremental
- If the peer has a really old map, send a full map instead of crashing
because we are missing the needed incremental.
... - 08:30 PM Revision 607043ed (ceph): osd: send full map if we don't have sufficiently old incremental
- If the peer has a really old map, send a full map instead of crashing
because we are missing the needed incremental.
... - 08:30 PM Revision 0cc7da2f (ceph): osd: share oldest_map info with peers
- This helps OSDs trim their old maps even when they don't get MOSDMap
messages directly from the monitor.
It also fee... - 08:30 PM Revision 818cf8c8 (ceph): mon: make number of old paxos states configurable
- Currently settable on osdmaps, pgmaps, and log. Still need MDSMap and
authmap trimming.
Signed-off-by: Sage Weil <s... - 08:30 PM Revision 474e368d (ceph): osd: remove old osdmaps
- When the monitor removes old maps, we should too.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 08:30 PM Revision 3acb9197 (ceph): paxos: trim extra state dirs
- OSDMonitor, for instance, stores both an "osdmap" and "osdmap_full" for
each state. Trim them both.
Signed-off-by: ... - 08:20 PM Revision dd3282c1 (ceph): rgw: multiple swift fixes and cleanups
- 08:03 PM Revision b3c68a51 (ceph): PG: call set_last_peering_reset in Started contructor
- Calling it here should cover all possible replica and primary peering
resets.
Signed-off-by: Samuel Just <samuel.jus... - 07:57 PM Revision ef30e69c (ceph): PG: Fix log.empty confusion
- Previously, log.empty meant that the log.head was everion_t(). However,
it was in a few places used to mean that log... - 05:17 PM Revision fccd28df (ceph): PG: Fix log.empty confusion
- Previously, log.empty meant that the log.head was everion_t(). However,
it was in a few places used to mean that log... - 01:35 PM Feature #1604 (Resolved): kclient: handle osdmap discontinuity
- 01:00 PM Bug #1449 (Resolved): osd: FAILED assert(0 == "we got a bad state machine event")
- b3c68a514135318e0dfda9f929f15f26340cd664
- 12:42 PM Bug #1620 (Resolved): rgw suicide due to heartbeat timeout
- Happens around a hour after osd went down:...
- 10:14 AM Bug #1607 (Resolved): osd: failed assert(missing.is_missing(oe.soid))
- a50fbe2b982e5d19040f4ae5795455dde3a9a02e
- 10:13 AM Bug #1599 (Resolved): osd assert fail (new_tail >= ondisklog.tail)
- fccd28df371dceffaf6ff7a50422b6a5b1ee126c should take care of it.
- 03:03 AM Revision f658cb4a (ceph): makefile changes for interval tree
- Added unit test case for interval tree to the makefile template.
Signed-off-by: Jojy George Varghese <jvarghese@scal... - 03:02 AM Revision d516f9b5 (ceph): mds: Unit tests for interval tree
- Provides usage scenarios and test cases for interval tree
implementation.
Tests include:
- testing addInterval inte... - 03:02 AM Revision 72d50fa5 (ceph): mds: Interval tree implementation
- Interval tree is an optimized data structure for representing and
querying intervals. Elementary intervals are repres...
10/13/2011
- 11:02 PM Revision 87f8389e (ceph): rgw: more swift fixes and adjustments
- 08:28 PM Revision b6d9ed94 (ceph): auth: remove global instance of auth_supported
- Wrap it in a class.
Instantiate locally, or keep a copy around if we'll need it often.
Factor out the protocol sele... - 04:53 PM Revision 1f3b12e0 (ceph): osd: bound generate_past_intervals() by oldest map
- The oldest osdmap we maintain is a lower bound on last_epoch_clean for the
entire system (assuming the monitor is doi... - 04:35 PM Revision 0167e824 (ceph): cls_rgw: rewrite rgw_bucket_complete_op to use update.
- Unfortunately we can't do multiple writes via the interface -- the
second one will clobber the first one. So use the ... - 04:35 PM Revision 45ebaf70 (ceph): cls_rgw: remove the write_bucket_dir function.
- It's no longer called anywhere. Hurray, we don't do our own
read-modify-write cycle any more (and can exploit the pow... - 04:33 PM Revision 75f7e546 (ceph): cls_rgw: refactor rgw_bucket_complete_op in terms of TMAP
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 04:33 PM Revision 2592e41a (ceph): cls_rgw: refactor rgw_bucket_prepare_op in terms of tmap
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 04:33 PM Revision 83504c42 (ceph): cls_rgw: refactor rgw_bucket_init_index in terms of tmap
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 04:33 PM Revision 15a3df84 (ceph): cls_rgw: refactor read_bucket_dir in terms of tmap.
- This function won't be called often once refactoring is done, but
its functionality will be needed for listing, if no... - 04:32 PM Revision 583e16d9 (ceph): objclass: add map interfaces.
- Right now, they implement the TMAP functions, plus a few obvious
extras to read/write select keys and the header. In ... - 04:29 PM Feature #1619 (Resolved): libvirt: test with selinux/apparmour enabled
- There are probably checks that assume the image is a file.
- 04:29 PM Revision c98e1c57 (ceph): ReplicatedPG: remove unused tmap implementation.
- If it's surrounded by an if(0), it shouldn't still be in the code.
Signed-off-by: Greg Farnum <gregory.farnum@dreamh... - 04:28 PM Feature #1618 (Resolved): libvirt: make sure migration works
- I think there's a small patch needed since it assumes the image is a file.
- 04:18 PM Bug #1617: pgs stuck down and peering with only one osd down and out
- Happened in run 494 as well. These were both rados bench with thrashing.
- 03:42 PM Bug #1617 (Won't Fix): pgs stuck down and peering with only one osd down and out
- From teuthology:~teuthworker/archive/nightly_coverage_2011-10-13/491/teuthology.log:...
- 01:35 PM Bug #1616: crash in is_supported_auth
- hopefully this is resolved by commit:b6d9ed9412cb046747bb0d0713c286613757bfcf
i confess i don't see why exactly th... - 12:52 PM Bug #1616: crash in is_supported_auth
- This happened again in run 493.
- 11:54 AM Bug #1616 (Resolved): crash in is_supported_auth
- From teuthology:~teuthworker/archive/nightly_coverage_2011-10-13/490/remote/ubuntu@sepia29.ceph.dreamhost.com/log/osd...
- 12:41 PM rgw Bug #1584 (Resolved): rgw: swift key management is busted
- We can now hold multiple swift keys, and multiple S3 keys. There's one swift key per subuser, and we can specify key ...
- 11:15 AM rgw Bug #1568 (Rejected): rgw: add object_locator to bucket index
- The only locator we use is on shadow and temporary objects, and these are located by their associated actual object. ...
- 10:35 AM Linux kernel client Bug #1615 (Can't reproduce): null pointer dereference in ceph_msg_new
- This happened during a blogbench run:...
- 10:02 AM Bug #1599: osd assert fail (new_tail >= ondisklog.tail)
- Finally reproduced this with debugging - logs and pg and osd dump will be in vit:~joshd/thrash_stuck_active3 in a bit...
- 09:58 AM rgw Bug #1570 (Resolved): rgw: use tmap for bucket index objects
- Pushed to master in commit:45ebaf705d1e37f6b0af84f27767c141496c2f1e
Passes S3 tests. - 09:58 AM Feature #1569 (Resolved): osd: create a tmap class api
- Pushed to master in commit:583e16d9591391c834cd17154571926bffc05abc
10/12/2011
- 11:26 PM Revision 42c8ae77 (ceph): test_librbd: expect copy to succeed
- 0 is the success return code. These were accidentally changed in the
conversion to gtest.
Signed-off-by: Josh Durgin... - 11:26 PM Revision d0d265bf (ceph): librbd: return errors when read_iterate fails during copy
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 10:44 PM Revision a50fbe2b (ceph): PG: merge_old_entry: merged delete might not be in missing
- If the new log does not contain an entry for that oid, it might not yet
be in missing, and we would need to add it.
... - 10:37 PM Revision 493596a7 (ceph): radosgw-admin: test swift keys creation/removal
- 09:46 PM Revision 42bbea89 (ceph): rgw: swift key removal
- 06:14 PM Revision 05dae94f (ceph): Revert "config: base default libdir, sysconfdir off autoconf values"
- This reverts commit 7e5dee907a8218647a88d1c7d3316cc277e1c44b.
- 06:09 PM Revision 1216eb2d (ceph): rgw: some swift api fixes
- 04:34 PM Revision 7e5dee90 (ceph): config: base default libdir, sysconfdir off autoconf values
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 03:42 PM Bug #1449 (In Progress): osd: FAILED assert(0 == "we got a bad state machine event")
- This happened again, with a log being received in GetInfo. This was during radosbench and fast thrashing.
From teuth... - 12:54 PM Bug #1613 (Resolved): mon crash
- 11:44 AM Bug #1613: mon crash
- Excellent. I got it running again using second monitor's data on first monitor.
Yes I am running kernel client on... - 11:11 AM Bug #1613: mon crash
- The mon data dir is specified in your ceph.conf.
This backtrace though makes it look like you're running the kerne... - 11:02 AM Bug #1613: mon crash
- Unfortunately I didn't get a chance to record the OOPS. I'll try to get them next time. In the syslog I found this ...
- 09:25 AM Bug #1613: mon crash
- Did you record the OOPS somewhere? It looks as though the monitor is pulling bad data off disk. You should be able to...
- 11:24 AM Bug #1594 (Resolved): pgs stuck degraded or active after 3 hours
- The bug in the second reproduced case was fixed by commit:af6a9f30696c900a2a8bd7ae24e8ed15fb4964bb.
- 09:36 AM Bug #1614 (Resolved): default rados class location needs to be depend on autoconf libdir
- 09:20 AM Bug #1614 (Duplicate): default rados class location needs to be depend on autoconf libdir
- it's /usr/lib64/... on many platforms.
- 09:14 AM CephFS Bug #1435: mds: loss of layout policies upon mds restart
- Greg Farnum wrote:
> I would assume this is just the IFILE lock state thing you talked about earlier?
>
> There w... - 09:09 AM CephFS Bug #1435: mds: loss of layout policies upon mds restart
- I would assume this is just the IFILE lock state thing you talked about earlier?
There were a few other bugs that ... - 09:05 AM CephFS Bug #1435 (In Progress): mds: loss of layout policies upon mds restart
- Can you do a bit of legwork and help us get a process to reproduce this? Once we have that it's easy to fix.
Prob... - 07:54 AM CephFS Bug #1435: mds: loss of layout policies upon mds restart
- I lied :-(
I had been running with a single mds for a while, and even though it restarted a number of times, it di...
10/11/2011
- 11:43 PM Bug #1613 (Resolved): mon crash
- Hi,
I am currently running ceph 0.36 w/ kernel 3.0.0 on two machines each with 4 2tb HDDs. All of those HDDs are ... - 10:06 PM Revision e07b956b (ceph): rgw: implement some missing swift api, other swift fixes
- 07:31 PM Revision f883e638 (ceph): rgw: multiple swift keys per user
- 07:31 PM Revision 5790a363 (ceph): rgw: encoded swift key contains full user name
- 06:39 PM Revision 9b18e55e (ceph): PG,OSD: clean up xlist::items on pg removal
- Should take care of #1599.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> - 06:16 PM Revision f7ec9f79 (ceph): thread: whitespace
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 06:16 PM Revision b43b8645 (ceph): osd: fix race between op requeueing and _dispatch
- If a message is working it's way through _dispatch, and another thread
requeues waiting messages under pg->lock (e.g.... - 06:08 PM Revision fc3aac6b (ceph): filestore: clean up error output
- No color codes in the logs!
Signed-off-by: Sage Weil <sage@newdream.net> - 06:08 PM Revision cd2dedd7 (ceph): filestore: tolerate missing current/
- We remove it anyway. If it's missing entirely, just continue and roll
back to the latest snap_ when the user passes ... - 05:31 PM rgw Bug #1570 (In Progress): rgw: use tmap for bucket index objects
- Pushed a first attempt to wip-tmap. Haven't tested it yet, but it does compile (and shouldn't change any behavior, wh...
- 05:30 PM Feature #1569 (In Progress): osd: create a tmap class api
- Pushed an implementation to wip-tmap. Haven't tested it yet.
- 02:01 PM rgw Feature #1591: rgw: instrument with perfcounter
- see wip-rgw-perfcounter branch
- 11:25 AM rgw Feature #1591 (In Progress): rgw: instrument with perfcounter
- 01:41 PM Bug #1608 (Resolved): osd crash in get_authorize_handler
- I'm going to cross my fingers and call this resolved, unless/until it comes up again.
- 01:41 PM Bug #1490 (Resolved): cfuse assert failure: assert(ob->last_commit_tid < tid)
- 01:12 PM Bug #1547: client log doesn't go to stderr unless 'log file' specified
- The interface is just confusing. We'll use two flags (--log-to-stderr, --err-to-stderr) instead.
- 12:40 PM Bug #1558 (Resolved): osd crash when deleting pg
- Should be fixed in 9b18e55e86a18de6ff91a42984ba9ba35d3bdd4f
- 11:32 AM Bug #1473: osd assert failure: FAILED assert(0 == "oi disagrees with stat, or error code on stat")
- Just saw this on osd.11 on alexandria (see #1612):...
- 08:41 AM Bug #1612: osd/PG.cc: 3839: FAILED assert(missing[oid].need <= v)
- Oh.. when i marked that node out, this came up:...
- 02:11 AM Revision 032dd84c (ceph): ceph.spec.in: more updates to make build.opensuse.org happy
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 02:11 AM Revision 468c7dce (ceph): rgw: find fcgi headers in /usr/include or /usr/include/fastcgi
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 02:11 AM Revision 3f619ddb (ceph): ceph.spec.in: fix radosgw files
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 02:11 AM Revision 465f1bf1 (ceph): ceph.spec.in: add init-radosgw back
- Accidentally took this out a few patches back.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
10/10/2011
- 06:51 PM Revision 52bad62d (ceph): rgw: push log list|show|rm into RGWStore
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 06:51 PM Revision 93a88150 (ceph): radosgw-admin: push log listing into RGWRados
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 06:51 PM Revision 69e9f51d (ceph): rgw: chdir to dir in conf (default /)
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 06:51 PM Revision 930d57f8 (ceph): rgw: push intent log processing into RGWRados layer
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 06:51 PM Revision d7f7a213 (ceph): librbd: don't return >32bit value from copy().
- Signed-off-by: Sage Weil <sage@newdream.net>
- 06:04 PM Revision 9ec60b4d (ceph): librbd: fix overflow on large large image copy
- Fixes: #1611
Signed-off-by: Sage Weil <sage@newdream.net> - 06:03 PM Revision b6c46158 (ceph): librbd: slightly cleaner
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:55 PM Revision 42ac18cd (ceph): .gitignore: test_libhadoopcephfs build
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 05:55 PM Revision 968b0909 (ceph): Merge branch 'master' of github.com:NewDreamNetwork/ceph
- 05:04 PM Bug #1612 (Resolved): osd/PG.cc: 3839: FAILED assert(missing[oid].need <= v)
- osd.11 on cephstore6357, full log is available!
- 04:50 PM Revision 7060efa9 (ceph): librbd: fix copy progress
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:44 PM Bug #1490: cfuse assert failure: assert(ob->last_commit_tid < tid)
- Reproduced. This time ordering is violated by a race between scrub completion doing take_waiters(waiting_for_active)...
- 11:06 AM Bug #1611 (Resolved): rbd cp broken?
- 09:36 AM Bug #1611 (Resolved): rbd cp broken?
- (09:34:39 AM) psomas: btw, i haven't searched if this is a known issue, but i tried "rbd cp image1 image2", and i get...
- 10:17 AM Bug #1580 (Resolved): watch expiration
10/09/2011
- 11:28 PM Revision 61855170 (ceph): hadoop: get the right class member, and ask for it properly.
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 08:45 PM rgw Feature #1375 (Rejected): Actually find pool limits
- 08:45 PM rgw Feature #1268 (Rejected): rgw: optimistically fetch acl and first chunk
- 08:42 PM Bug #1032 (Can't reproduce): osd: Marked down and become zombies after killing
10/08/2011
- 09:07 PM Feature #1565 (Resolved): crowbar demo
- 11:15 AM CephFS Bug #1435 (Resolved): mds: loss of layout policies upon mds restart
- Great news, thanks. We haven't tested it.
- 01:14 AM CephFS Bug #1435: mds: loss of layout policies upon mds restart
- Wasn't this fixed in 0.35? I haven't lost directory layout information any more.
- 01:08 AM Bug #1590: occasionally excessive mon memory footprint
- I've just run into this while only two out of the 3 mons were up: mon.0 was taking several minutes to complete a sync...
10/07/2011
- 11:47 PM Revision dc40b374 (ceph): auth: move AuthAuthorizeHandler registry into class
- Static classes with constructors and destructors are dangerous. Explicitly
manage these as part of the server compon... - 11:07 PM Revision 11a1d601 (ceph): OSD,ReplicatedPG: expire and cleanup unconnected watchers
- During handle_notify_timeout or ms_handle_reset, watchers are now marked
unconnected via pg->register_unconnected_wat... - 09:51 PM Revision 321381d7 (ceph): teuthology-worker: remove --keep-locked-on-error
- 09:49 PM Revision 3d3eb0ef (ceph): Remove --keep-locked-on-error, and behave as if it were specified
- This will help prevent machines with cephtest dirs still present from
being used. It's easy to unlock machines - the ... - 09:37 PM Revision 9d846d33 (ceph): move ceph_mount call
- 09:29 PM Revision 039035b3 (ceph): osd: discard requests that from disconnected clients
- If we can't reply, throw out the request; they'll need to resend it anyway.
Signed-off-by: Sage Weil <sage@newdream.... - 09:29 PM Revision 88de6ab5 (ceph): ceph.spec.in: handle docdir properly
- Pass correct path to configure (fixes SuSE builds).
Use %doc command to install sample.ceph.conf and sample.fetch_co... - 09:13 PM Revision 0121bcd2 (ceph): clitests: add test case for crush exhaustive search
- This detects the bug that caused #1594.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> - 08:13 PM Revision e5db7b24 (ceph): Makefile: only reset docdir if it's not already defined
- This is only for old versions of automake, and won't work for ancient
SuSe.
Signed-off-by: Sage Weil <sage@newdream.... - 08:03 PM Revision 2f877f82 (ceph): crushtool: fix --weight arg parsing
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:02 PM Revision 8ff1cbb5 (ceph): crushtool: add --force N
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:54 PM Revision af6a9f30 (ceph): crush: try _all_ bucket items when doing exhaustive search
- N-1 isn't exhaustive.
Fixes: #1594
Signed-off-by: Sage Weil <sage@newdream.net> - 06:10 PM Revision 5a236942 (ceph): ceph.spec.in: build on suse
- Signed-off-by: Sage Weil <sage@newdream.net>
- 06:05 PM Bug #1609 (Resolved): osd: failed assert(info.last_complete == info.last_update)
- From teuthology:~teuthworker/archive/nightly_coverage_2011-10-07/246/remote/ubuntu@sepia67.ceph.dreamhost.com/log/osd...
- 04:53 PM Revision 6e29c282 (ceph): mon: tolerate 50ms (instead of 10ms) of clock drift
- NTP on sepia can't manage 10ms, it seems. Sigh.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 04:49 PM Bug #1608: osd crash in get_authorize_handler
- if this was caused by global static class lameness, it should be fixed by commit:dc40b37403298a60cb5823c030fa94518b0c...
- 04:22 PM Bug #1608 (Resolved): osd crash in get_authorize_handler
- Possibly a use-after-free. From teuthology:~teuthworker/archive/nightly_coverage_2011-10-07/251/remote/ubuntu@sepia86...
- 04:32 PM Revision ff31d3cc (ceph): rgw: fix printf format warning
- Signed-off-by: Sage Weil <sage@newdream.net>
- 03:45 PM Bug #1607 (Resolved): osd: failed assert(missing.is_missing(oe.soid))
- While thrashing with bonnie++, this ocurred:...
- 11:29 AM Bug #1594: pgs stuck degraded or active after 3 hours
- Reproduced with 2.1p3 stuck in active since the up and acting sets were different. In this case 3 osds were marked ou...
- 10:56 AM Bug #1454 (Can't reproduce): cosd process dies and remains in defunct state
- 10:54 AM CephFS Bug #1437 (Can't reproduce): cfuse can't change permissions of a file
- 10:34 AM Bug #1581 (Resolved): teuthology: restarting osds sometimes allows daemon-helper to fail
- 10:20 AM Bug #1403 (Resolved): osd: FAILED assert(0 == "we got a bad state machine event")
- 10:20 AM Bug #1449 (Resolved): osd: FAILED assert(0 == "we got a bad state machine event")
- 09:38 AM Feature #1606 (Rejected): osd: bound missing set memory usage
- 09:38 AM Feature #1583: osd: bound pg log memory usage
- I don't think this is a new problem, but it is a problem!
- 09:36 AM RADOS Feature #1605 (New): osd: rewrite missing object if op is replayed
- If an MOSDOp is received with a reqid that matches a missing object, and we have the prior version (or no prior versi...
- 09:33 AM Bug #1602 (Duplicate): mon crash during startup
- #1415
- 09:05 AM rgw Bug #1592 (Resolved): rgw: remove preallocated pools
- This got merged into master and passed s3tests.
- 12:39 AM Revision 8be9450b (ceph): rgw: make log object naming configurable
- Use date(1) codes for object name, plus %i and %n for bucket id/name, and
make UTC vs localtime configurable.
Signed... - 12:18 AM Revision c56ab974 (ceph): reconnect: ignore SSHExceptions before the timeout expires
- Fixes: #1587
10/06/2011
- 11:17 PM Revision 4fe9cca5 (ceph): objecter: cope with missing osdmaps in history
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:17 PM Revision 6e04f60e (ceph): mon: fix osdmap trimming unsigned overflow
- This was trimming way to aggressively for early epochs due to the unsigned
version overflowing.
Signed-off-by: Sage ... - 11:17 PM Revision 64935d4c (ceph): auth: fix authorizer leak fix
- We were never reusing the authorizer, so make it local. This fixes a crash
(double-free) on reset().
Signed-off-by:... - 11:17 PM Revision 3d2f89fa (ceph): mon: make other send_incremental variant handle map discontinuity
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:59 PM Revision 85bbc2f9 (ceph): .gitignore: add multi_stress_watch
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 10:45 PM Revision ad48ada8 (ceph): pg: rename warm_restart and last_warm_restart
- These names make more sense, since last_warm_restart was updated
outside of the warm_restart function.
Signed-off-by... - 10:45 PM Revision b344d797 (ceph): osd, pg: ignore responses to obsolete queries
- This adds a query_epoch to notify and log messages, which are
sent in response to queries from the primary during pee... - 09:51 PM Revision 5840ae46 (ceph): test/multi_stress_watch.cc: add watch notify tester for teuthology
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 09:51 PM Revision 6bfae03a (ceph): ReplicatedPG: assert *_FLUSHING unreachable for AccessMode
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 09:34 PM Revision 4722d468 (ceph): task/watch_notify_stress: watch_notify_stress now thrashes clients
- This should exercise the watch notify timeout code.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> - 08:56 PM Revision 088d0dfa (ceph): qa: rados-api: try harder to make these pool names unique
- Still getting -17 sometimes on sepia... :/
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 08:39 PM Revision 646ef6aa (ceph): xlist: more assertive
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 08:24 PM Revision d78b8c76 (ceph): xattr: use sys/types.h instead of linux/types.h
- This way it compiles.
Signed-off-by: Sage Weil <sage@newdream.net> - 08:24 PM Revision 960deb49 (ceph): Makefile: include ceph_extattr.h to dist tarball
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 08:24 PM Revision b1ea37fc (ceph): Merge remote branch 'stass/wip-freebsdport-rebased2' into wip-freebsd
- 08:12 PM Revision 07c88609 (ceph): Revert "osd: simplify the session ref-counting branches"
- This reverts commit f002144ef7d314e80d3d19a5cd2c4cef38851056.
- 07:58 PM Revision fce17617 (ceph): osd: boot with map of oldest-1
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:50 PM Revision 4e61e483 (ceph): rgw: keep radosgw in foreground
- It defaults to a daemon now.
- 07:35 PM Revision d2721464 (ceph): radosgw-admin: UTC for time in 'log show', local time in separate field
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:35 PM Revision 77cfbfbb (ceph): radosgw-admin: for date filtering for 'log list'
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:35 PM Revision e8dd1f8b (ceph): utime: add gmtime() output function
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:32 PM Bug #1587 (Resolved): teuthology: handle SSHException when reconnecting
- Implemented in c56ab97442bbf61ad84526580bf773b324a05066 of teuthology.git.
- 05:30 PM Revision 6e0a3df8 (ceph): Merge branch 'wip-leaks'
- 04:58 PM Revision d9262014 (ceph): cephx: don't leak Authorizers on each request
- It's not clear to me why this is a class member -- it's only
written to or read from in this function, which allocate... - 04:44 PM Revision 5d7e4bd5 (ceph): osd: put session ref in ms_handle_reset
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 04:44 PM Revision f002144e (ceph): osd: simplify the session ref-counting branches
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 04:40 PM Revision d78286e1 (ceph): rgw: fix chdir result warning
- warning: rgw/rgw_main.cc:265: ignoring return value of ‘int chdir(const char*)’, declared with attribute warn_unused_...
- 04:33 PM Feature #1604 (Resolved): kclient: handle osdmap discontinuity
- 04:20 PM Bug #1449: osd: FAILED assert(0 == "we got a bad state machine event")
- This should be fixed with commit:b344d7979b8e0aac931c9f337f367e400a932e36
- 03:52 PM Revision ca3662c8 (ceph): rgw: fix rgw_switch_url_previx printf arg
- Signed-off-by: Sage Weil <sage@newdream.net>
- 03:50 PM Revision 02be9938 (ceph): osd: same_acting_since -> same_interval_since
- Interval is (currently) defined as same acting and up sets.
Signed-off-by: Sage Weil <sage@newdream.net> - 01:26 PM CephFS Bug #1603 (Can't reproduce): ceph-fuse crash during unmount
- From teuthology:~teuthworker/archive/nightly_coverage_2011-10-06/165/teuthology.log:...
- 01:24 PM Bug #1602 (Duplicate): mon crash during startup
- From teuthology:~teuthworker/archive/nightly_coverage_2011-10-06/164/remote/ubuntu@sepia51.ceph.dreamhost.com/log/mon...
- 10:11 AM Bug #1534 (Can't reproduce): ceph tool failed assert(mon_addr.count(n))
- 10:10 AM CephFS Bug #1601: mds crash during snaps workunit
- this looks like heap corruption to me. we should run that teuthology task with valgrind on the mds.
- 10:08 AM CephFS Bug #1601 (Can't reproduce): mds crash during snaps workunit
- From teuthology:~teuthworker/archive/nightly_coverage_2011-10-06/163/teuthology.log:...
- 04:41 AM Revision 5ab7f8fa (ceph): osd: fix same_acting_since update
- same_acting_since actually means "same acting AND up set since". This is
what the other same_acting_since update doe... - 04:30 AM Revision 5235b970 (ceph): rgw: add conf rgw_remote_addr_param instead of using fcgi environment
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:30 AM Revision 24e05e32 (ceph): rgw: use conf for rgw_dns_name instead of fcgi environment
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:30 AM Revision 85cf0a8d (ceph): rgw: use conf for rgw_print_continue instead of fcgi environment
- Also remove unused expect100cont bool.
Signed-off-by: Sage Weil <sage@newdream.net> - 04:30 AM Revision 8f62c3bb (ceph): rgw: use conf for rgw_swift_url[_prefix] instead of fcgi env
- Signed-off-by: Sage Weil <sage@newdream.net>
10/05/2011
- 10:16 PM Revision 1e151664 (ceph): vstart: use normal name for .asok files
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 10:16 PM Revision 9d53b3d3 (ceph): osd: fix pg stats encoding for unfound
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 08:48 PM Revision ed878715 (ceph): rgw: fix initscript default user
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:37 PM Revision 4ab2a852 (ceph): rgw: daemonize by default
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:07 PM Revision 5af012a8 (ceph): rgw: set locator key before calling get_obj_state()
- get_obj_state assumes the io_ctx is ready to go. Set the locator key
earlier rather than later.
Signed-off-by: Sage... - 08:05 PM Revision c4b51e30 (ceph): objecter: normalize oloc.key
- If oloc.key == oid, clear it. Users can set it to the oid or leave it
blank; they are equivalent.
Signed-off-by: Sa... - 07:02 PM Revision a3316f44 (ceph): cli: fix test contents again.
- I don't know why this didn't come across properly from my wip branch...
Signed-off-by: Greg Farnum <gregory.farnum@d... - 06:13 PM Revision b38cba2d (ceph): paxos: update first_committed
- Otherwise this stays at 0, which isn't accurate.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 06:13 PM Revision e4a69004 (ceph): osd: fix map epoch check in handle_osd_map
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:47 PM Bug #1599: osd assert fail (new_tail >= ondisklog.tail)
- Happened in 151 as well.
- 01:51 PM Bug #1599: osd assert fail (new_tail >= ondisklog.tail)
- I'm thrashing with osd debugging. This should turn up (as well as other bugs we've seen while thrashing).
- 01:42 PM Bug #1599: osd assert fail (new_tail >= ondisklog.tail)
- can we reproduce with osd logs on?
- 01:38 PM Bug #1599: osd assert fail (new_tail >= ondisklog.tail)
- This happened again in teuthology:~teuthworker/archive/nightly_coverage_2011-10-05/150/remote/ubuntu@sepia5.ceph.drea...
- 11:13 AM Bug #1599 (Resolved): osd assert fail (new_tail >= ondisklog.tail)
- From teuthology:~teuthworker/archive/nightly_coverage_2011-10-04/102/remote/ubuntu@sepia75.ceph.dreamhost.com/log/osd...
- 05:45 PM Revision a76f8d42 (ceph): rgw: fix mis-merge issues.
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 04:54 PM Revision 20e0d36a (ceph): Merge branch 'wip-rgw-pools'
- Conflicts:
src/rgw/rgw_bucket.cc
src/rgw/rgw_main.cc - 04:50 PM Revision b5c27aec (ceph): monclient: add an initialized bool to guard shutdown.
- The addition of a Finisher in 9c56070bc20878e87fcb4715b0a3559dd1aaf9ff
broke shutdown in the case where MonClient::in... - 04:25 PM Revision 13d48030 (ceph): rgw: remove rgw_create_bucket.
- Push all its extra functionality down into RGWRados::create_bucket. Convert
callers to the different interface (there... - 04:25 PM Revision 5f960f82 (ceph): rgw: remove select_bucket_placement from RGWAccess interface.
- RGWRados::create_bucket is the only user now, so make it private
and make the interface a little tighter.
(We are go... - 04:25 PM Revision 12472785 (ceph): rgw: move rgw_store_bucket_info into RGWRados.
- create_bucket is the only user, so just make it a simple helper.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhos... - 04:25 PM Revision f723f0a5 (ceph): rgw: remove the rgw_get_bucket_info functions
- Push them down into the RGWAccess layers.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 04:25 PM Revision 1c2ff9d6 (ceph): rgw: remove the rgw_buckets files
- We don't need them any more. Hurrah!
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 04:25 PM Revision 98f15e64 (ceph): rgw: new command to add pools to the list of available places for storage.
- Do this by adding an add_bucket_placement function to RGWAccess. Hurray
leaky abstractions! :(
Signed-off-by: Greg F... - 02:26 PM Bug #1449: osd: FAILED assert(0 == "we got a bad state machine event")
- Replicated this with osd debugging enabled by thrashing with teuthology. Logs are in vit:~joshd/thrash_bad_state_mach...
- 12:47 PM Linux kernel client Bug #1600 (Can't reproduce): general protection fault during blogbench
- Logs in teuthology:~teuthworker/archive/nightly_coverage_2011-10-05/129
From kern.log on sepia29:... - 10:09 AM Bug #1530: osd crash during build_inc_scrub_map
- A third recurrence, this time with ffsb on rbd. Logs in teuthology:~teuthworker/archive/nightly_coverage_2011-10-05/142/
- 03:36 AM Revision 3bb6ad9d (ceph): Merge branch 'stable'
- 03:35 AM Revision a788bfdb (ceph): osd: fix PG::up calculation on startup
- We weren't filling in pg->up, which meant we booked an incorrect past
interval in PG::warm_restart(), leading to unkn... - 03:30 AM Revision 36aaa774 (ceph): mon: fix maps sent after osd boot
- This was a bad hunk that crept in while I was rebasing wip-oldmaps. :(
Signed-off-by: Sage Weil <sage.weil@dreamhos... - 02:03 AM Revision d4340bac (ceph): On FreeBSD, libedit should be linked in explicitly, because this library
- is present in the system, but it is not in the pkg-config database.
Signed-off-by: Stanislav Sedov <stas@FreeBSD.org> - 12:34 AM Revision 9fde4d94 (ceph): First cut of FreeBSD support. This patch allowes ceph to compile succe...
- under FreeBSD.
Signed-off-by: Stanislav Sedov <stas@FreeBSD.org> - 12:34 AM Revision 2b9ba0bd (ceph): Use system-independent definitions for Ceph's setxattr flags
- parameter. Ceph passes Linux setxattr flags on the wire without
converting them, so use the same values for these de... - 12:34 AM Revision 8ffbaffb (ceph): osd: Minimize amount of #ifdefs in src/os/FileStore.cc by allowing
- btrfs_ioctl.h to compile and relying on the btrfs runtime checks
wherever possible.
Signed-off-by: Stanislav Se... - 12:34 AM Revision c4f4ea96 (ceph): osd: use numeric values for OSD errnos, as ERESTART and ESHUTDOWN values
- are system-dependent. In future, we'll probably want to use system
independent values as Ceph result codes, not... - 12:34 AM Revision 8140bdb0 (ceph): Abstract out extended attribute calls in ceph_extattr.c so all
- the system-dependent extattr code can be moved into a single
place. Implement FreeBSD and Darwin support.
Signed-of... - 12:34 AM Revision 71cc72f9 (ceph): osd: prevent a potential huge memory allocation in case a error
- code is returned from getxattr.
Signed-off-by: Stanislav Sedov <stas@FreeBSD.org> - 12:34 AM Revision 3efa1603 (ceph): Fix endianess detection on FreeBSD.
- Signed-off-by: Stanislav Sedov <stas@FreeBSD.org>
- 12:34 AM Revision 5d75d69d (ceph): Change extattr wrapper for FreeBSD to return ERANGE error code in case
- the buffer provided was too small similar to what Linux does.
Signed-off-by: Stanislav Sedov <stas@FreeBSD.org> - 12:34 AM Revision 8f19bb0e (ceph): SimpleMessenger: getnameinfo needs the correct address size to be passe...
- not just a size of the whole sockaddr_storage placeholder.
Signed-off-by: Stanislav Sedov <stas@FreeBSD.org> - 12:34 AM Revision 07b9bc03 (ceph): SimpleMessenger: add new method addr_size() to return the correct size ...
- address object. Also, do not assume ss_family is 2 bytes
on all platforms.
Signed-off-by: Stanisla... - 12:34 AM Revision 3e0122c9 (ceph): Change PAGE_MASK/PAGE_SIZE definitions to CEPH_PAGE_MASK/CEPH_PAGE_SIZE
- so they won't interfere with system definitions.
Signed-off-by: Stanislav Sedov <stas@FreeBSD.org> - 12:34 AM Revision cb45fbcb (ceph): SimpleMessenger: pass correct address sizes to bind(2) and connect(2),
- otherwise they fail on FreeBSD (and possibly on other
platforms).
Signed-off-by: Stanislav Sedov <s... - 12:34 AM Revision 0cd3e562 (ceph): Use /bin/sh, which is more portable.
- Signed-off-by: Stanislav Sedov <stas@FreeBSD.org>
- 12:21 AM Revision 107db6a9 (ceph): Retry listing machines if the lock server goes down.
10/04/2011
- 11:09 PM Revision 39a1e760 (ceph): rgw: use normal logging mechanism
- Keep capturing stdout/err, even though it should end up empty.
Signed-off-by: Sage Weil <sage@newdream.net> - 11:08 PM Revision 7cbb68d8 (ceph): Merge branch 'wip-rgw-log'
- 11:07 PM Revision 64d2b97d (ceph): osd: remove some dead code
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:05 PM Revision 167c091e (ceph): rgw: write debug acl output to the debug output (not cout)
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:02 PM Revision 3b645fb9 (ceph): common: CINIT_FLAG_NO_BANNER
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:02 PM Revision 4e9969e7 (ceph): rgw: more sane defaults
- Notably, this gives us log_to_stderr = 1.
Signed-off-by: Sage Weil <sage@newdream.net> - 10:40 PM Revision 09b23b42 (ceph): rgw: rgw_log -> debug_rgw
- Normalize with the rest of the code base.
Also, 'rgw log' might be confused with 'log file'.
Signed-off-by: Sage We... - 10:36 PM Revision 37c88295 (ceph): rgw: remove useless RGWConf::log_level
- Not used for anything.
Signed-off-by: Sage Weil <sage@newdream.net> - 10:36 PM Revision 14338615 (ceph): rgw: set dout condvar to rgw_log
- We would normally set DOUT_SUBSYS and get debug_$foo, but the setting in
this case is rgw_log.
Signed-off-by: Sage W... - 09:59 PM Revision 27cf8547 (ceph): rgw: RGW_LOG -> dout
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:43 PM Bug #1598 (Resolved): osd: fix lost objects
- - track them properly
- consider rolling back to prior version vs strict EIO
- if a lost object had no prior_versio... - 09:40 PM Bug #1594: pgs stuck degraded or active after 3 hours
- Found one unrelated but, commit:a788bfdb93548751cec7184b65d42702cc207508.
I see one other possible badness:
- op... - 04:39 PM Bug #1594: pgs stuck degraded or active after 3 hours
- I reproduced this with debugging enabled. Logs are in vit:~joshd/thrash_stuck_active.
In this case there was 1 stuck... - 09:08 PM Revision f24216a4 (ceph): mon: make MPoolOp*::print() readable
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 09:08 PM Revision a7abb068 (ceph): rados-api/test: don't srand(time())
- This will give duplicate results if called more than once per second, which
leads to things like -EEXIST (#1558).
Si... - 08:46 PM Revision b8f5a35a (ceph): Merge branch 'wip-oldmaps'
- 08:46 PM Revision 80842721 (ceph): rgw: set xmlns on ListBucketResult element
- Certain S3 clients (e.g., s3fs) require the xmlns to parse the
results correctly.
Signed-off-by: Henry C Chang <henr... - 08:46 PM Revision b2361dc7 (ceph): radosgw: run as 'user' field in ceph.conf
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:44 PM Revision 71792e83 (ceph): objecter: fix locking on is_latest_map checks
- We need to take the lock protecting these structures in the completion
context.
Signed-off-by: Sage Weil <sage@newdr... - 08:44 PM Revision e661bf86 (ceph): osd: use pointers for handle_advance_map
- So that lastmap can be optional.
Signed-off-by: Sage Weil <sage@newdream.net> - 08:44 PM Revision b8ada495 (ceph): osdmap: include oldest, newest known epoch in message
- If non-zero, these are filled in with the oldest and newest map epochs
available. This helps the client decide wheth... - 08:44 PM Revision a47aedd4 (ceph): mon: limit maps send on onetime osdmap subscribe
- This throttles the load put on the monitor by making the client request
osdmaps in discrete chunks. Use a feature bi... - 08:44 PM Revision cd93f18f (ceph): osdmap: show old addrs for down osds
- This is useful for admins to find which ip/node to connect to.
Signed-off-by: Sage Weil <sage@newdream.net> - 08:44 PM Revision ddbb2ca4 (ceph): osdmap: show weight for out osds
- This info is reduncant (weight is 0 for out osds), but makes the output
cleaner.
Signed-off-by: Sage Weil <sage@newd... - 08:44 PM Revision 6ff57932 (ceph): osdmap: include addrs in json dump
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:44 PM Revision 4f591b55 (ceph): osd: get latest osdmaps before booting
- - get the latest osdmaps before adding/marking ourselves up
- behave if there is a discontinuity in the osdmap histor... - 08:44 PM Revision ea087e39 (ceph): mon: implicitly mark lost_at when a fresh osd rejoins the cluster
- If an osd is wiped an rejoins the cluster, record that by implicitly
setting lost_at.
Signed-off-by: Sage Weil <sage... - 08:44 PM Revision 906e1dad (ceph): osd: add last_epoch_clean to pg_stat_t
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:44 PM Revision 799323b1 (ceph): mon: trim old osdmaps
- Trakc the oldest clean pg, and trim osdmaps that are older than that.
Signed-off-by: Sage Weil <sage@newdream.net> - 08:44 PM Revision 2a9330fb (ceph): osd: do not request osdmap when loner if not booted
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:44 PM Revision 51fc234c (ceph): osd: is_active() instead of !is_booting() for map sharing checks
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:44 PM Revision 54ce5442 (ceph): monclient: implement get_version() to get newest _and_ oldest map versions
- Reimplement is_latest_map() in terms of more general helper. Add field
to reply message.
Signed-off-by: Sage Weil <... - 08:44 PM Revision 04b90cc7 (ceph): monclient: clean up old version_requests on session reset
- This throws out the old contexts. We assume that the caller will not wait
for them.
Signed-off-by: Sage Weil <sage@... - 08:44 PM Revision 9c56070b (ceph): monclient: use an async finisher
- Otherwise we can deadlock if any completions call back into MonClient.
Signed-off-by: Sage Weil <sage@newdream.net> - 08:44 PM Revision b8aca4e2 (ceph): radosgw: run as 'user' field in ceph.conf
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:55 PM Revision 8e37140f (ceph): radosgw-admin: make 'log list' behave when .log pool dne
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 07:32 PM Revision 7b7ff6e8 (ceph): teuthology-worker: clean up last_in_suite jobs
- There's no reason not to delete them once they start.
- 07:17 PM Revision 3d3ba1eb (ceph): daemon-helper: detect the signal actually sent
- I thought I fixed this when I implemented coverage collection, but I
guess it got lost in a rebase or something. - 05:35 PM Feature #1559 (Resolved): teuthology: continue waiting if the lock server fails
- Done in 107db6a913e58201ed51b097881979539723a139.
- 04:08 PM rgw Feature #1593 (Resolved): rgw: normalize logging
- 02:49 PM CephFS Bug #1596: mds crash during ffsb on kernel client in CInode::is_frozen
- nothing obvious in the code. needs logs on this one.
- 10:35 AM CephFS Bug #1596 (Can't reproduce): mds crash during ffsb on kernel client in CInode::is_frozen
- Logs in teuthology:~teuthworker/archive/nightly_coverage_2011-10-04/82:...
- 02:46 PM Linux kernel client Bug #1597: general protection fault during mount
- not sure if this is ceph related at all. google turned up
http://forum.ubuntu-it.org/index.php?topic=422944.msg33... - 11:28 AM Linux kernel client Bug #1597 (Can't reproduce): general protection fault during mount
- Teuthology log in teuthology:teuthworker/archive/nightly_coverage_2011-10-04/84 shows:...
- 02:40 PM Bug #1563 (Closed): OSD isn't prioritizing data with waiting ops during transfer
2011-09-26 12:36:16.150430 7f66b08b4700 -- 64.188.54.43:6800/4514 <== mds0 64.188.54.36:6800/10043 6 ==== osd_op(m...- 01:48 PM Bug #1562 (Resolved): osd: fix osd replacement
- 12:32 PM Bug #1581: teuthology: restarting osds sometimes allows daemon-helper to fail
- Probably fixed with 3d3ba1ebb1c9f145300e972829b73a7eeaf00faa. I'll close the issue if it doesn't recur in the next co...
- 12:06 PM Bug #1581: teuthology: restarting osds sometimes allows daemon-helper to fail
- Looking into this since it's happened again today.
- 09:57 AM Bug #1581: teuthology: restarting osds sometimes allows daemon-helper to fail
- This happened again in teuthology:~teuthworker/archive/nightly_coverage_2011-10-03/41...
- 09:39 AM rgw Bug #1592: rgw: remove preallocated pools
- Done in branch wip-rgw-pools as of commit:f458d7aac4597e7ad735853cfdfe405c80a2dacb. I'm going to try and finish clean...
- 03:03 AM Revision 81c5f6ad (ceph): debian: don't recommend gceph
- Not until it's worth installing.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 12:49 AM Revision d305d61b (ceph): ceph_manager: remove unused raw_pg_status method
- 12:49 AM Revision 8e031730 (ceph): ceph_manager: run ceph -s as a normal program
- This allows failures from it to be detected better.
- 12:11 AM Revision bad609e6 (ceph): teuthology-results: include passed tests in email
- 12:08 AM Revision 8bcd2a74 (ceph): teuthology-results: include reasons for failure in email
- 12:07 AM Revision 817b9504 (ceph): radosbench: get coverage and cores
- 12:07 AM Revision 1cad309d (ceph): Add failure_reason to summary for the first failure detected.
- For now, this is the exception raised during a task, the error found
in the central log, or coredumps found. More spe... - 12:07 AM Revision 030161ed (ceph): teuthology-ls: show reasons for failures with -v
10/03/2011
- 10:40 PM Revision 9f71bb0c (ceph): rgw: don't specify create_pool and set_marker in create_bucket.
- It's wildly inappropriate for that kind of implementation detail to
leak out of the interface. For the moment, leave ... - 10:23 PM Revision 3503b34a (ceph): Merge branch 'stable'
- 10:23 PM Revision 4ae8f1c9 (ceph): radosgw: make stop succeed when not running
- This fixes apt-get errors like
No /usr/bin/radosgw found running; none killed.
invoke-rc.d: initscript radosgw, acti... - 10:14 PM Revision 36f650b4 (ceph): rgw: move rgw_bucket_select_host_pool behind RGWAccess as select_bucket...
- This doesn't really belong in front of the interface. Maybe later we
can hide it completely, but for now we can put i... - 10:02 PM Revision c49c19c1 (ceph): radosgw: fix init-radosgw provides
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:32 PM Revision bbc644e0 (ceph): rgw: remove withdraw_pool function.
- I think its use was broken anyway?
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 09:32 PM Revision 1018673c (ceph): rgw: remove preallocation of pools
- Rename rgw_bucket_allocate_pool to rgw_bucket_select_host_pool, since
that better describes functionality we might ac... - 09:31 PM Revision df9c6602 (ceph): rgw: remove preallocating pools maintenance tick
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 09:26 PM Revision fe1a271d (ceph): watch_notify_stress.py: add ceph flags option
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 09:26 PM Revision 28d60172 (ceph): ceph.py: add btrfs option
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 08:43 PM CephFS Bug #1472 (Can't reproduce): cfuse hangs with v0.34
- 08:42 PM rgw Feature #1542 (Resolved): rgw: combine multiple buckets in a pool
- 08:23 PM Revision 04f825ed (ceph): rgw: set xmlns on ListBucketResult element
- Certain S3 clients (e.g., s3fs) require the xmlns to parse the
results correctly.
Signed-off-by: Henry C Chang <henr... - 08:19 PM Revision 848a1f95 (ceph): debian: add non-stripped exception for libcls_rgw rados class
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:18 PM Revision 5d54398c (ceph): mds: fix possible deadlock in multi-mds setup
- This should fix the file_excl case on a file_max update when there
is more than one mds.
If we dont issue caps here ... - 08:18 PM Revision 2a078f89 (ceph): Makefile: more radosgw_admin -> radosgw-admin
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:22 PM Revision a192ee1b (ceph): basic: add rbd cli tests
- 07:20 PM Revision b968ff3a (ceph): workunit: clean up temporary files
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 06:25 PM Revision 6103ee9e (ceph): more radosgw_admin -> radosgw-admin
- Signed-off-by: Sage Weil <sage@newdream.net>
- 06:20 PM Bug #1594 (Resolved): pgs stuck degraded or active after 3 hours
- From teuthology:~teuthworker/archive/nightly_coverage_2011-10-03/42/teuthology.log...
- 06:19 PM Revision c5b0e3ee (ceph): osd: trim ondisk log using Log::Entry::offset
- The block_map is a waste of memory. It is simpler just to keep track of
what offset a Log::Entry was read/written/ap... - 06:13 PM Revision 12ce321b (ceph): ReplicatedPG: reset return code after find_object_context
- This way the object is actually deleted when it has no snapshots,
since the transaction is not aborted. This makes
te... - 05:59 PM Revision f85dfa74 (ceph): osd: combine log_op into append_log
- They're both short, and log_op only ends up hiding information that
append_log will soon need (the raw Log::Entry's).... - 05:30 PM Feature #1557 (Resolved): teuthology: summary string
- This does exceptions, the first most severe error in the central log (in order of SEC, ERR, WRN), and core dumps. Thi...
- 04:56 PM Revision ae196028 (ceph): nuke: keep up with renaming cfuse -> ceph-fuse
- 04:55 PM Revision f4e61db8 (ceph): mdcache: tolerate no subtrees in create_subtree_map()
- We don't really need mydir here. It is normally opened up in the
subsequent call to open_root(). That will be ident... - 04:55 PM Revision 8111b619 (ceph): mds: make jouranl writeable in MDLog::append()
- When restarting a stopped MDS, we need to mark the Journaler read/write
before we use it. Do this in MDLog::append()... - 04:45 PM Revision a827f040 (ceph): Merge remote branch 'gh/stable'
- 04:45 PM Revision b93a0077 (ceph): tasks/radosgw-admin: test radosgw-admin tool
- Not yet complete...
- 04:45 PM Revision 2b601a32 (ceph): radosgw-admin: test additional keys, log list/show/rm
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:44 PM Revision afc2dc08 (ceph): nuke: killall apache2 and radosgw too
- 03:15 PM rgw Feature #1593 (Resolved): rgw: normalize logging
- Instead of logging to stdout/err, use the normal log mechanism to write to wherever log_file points to. Then fix the...
- 02:22 PM Feature #1377 (Resolved): teuthology: use btrfs to back osds
- 11:50 AM Bug #1554 (Resolved): rbd rollback does not work with a snapshot of an empty image
- Fixed by commit:12ce321b3217b1f3134a7586c1f7d1e6cc384b02
- 11:47 AM CephFS Bug #1538 (Resolved): mds: all clients can and up becoming unresponsive, mds locker waiting for u...
- I applied your patch, slightly modified.. I still pass need_issue and call issue_caps explicitly. Same end result, b...
- 10:18 AM Feature #1483 (Resolved): glance: rbd backend
- 10:12 AM Feature #1583: osd: bound pg log memory usage
- Just started looking at this, but alldown-to-cleanboth points to the Ondisklog::block_map, which is a stupid piece of...
- 10:04 AM rgw Bug #1592 (Resolved): rgw: remove preallocated pools
- We don't want this since we're putting many buckets into a single pool now. Keeping it around breaks many interface l...
- 10:01 AM rgw Feature #1544 (Resolved): rgw: explicit bucket index
- We have a bucket index. Other tickets exist for doing the cleanup, etc.
- 09:55 AM CephFS Bug #1589 (Resolved): MDS assert failure
10/02/2011
- 10:30 PM Revision 4922757e (ceph): ceph.spec.in still packages libceph.so in 0.36
- Package libcephfs.so instead of libceph.so.
Signed-off-by: Alexandre Oliva <oliva@lsd.ic.unicamp.br> - 03:17 PM rgw Feature #1591 (Resolved): rgw: instrument with perfcounter
- things like op counts, bytes, latency from receiving request to sending first byte
10/01/2011
- 01:23 PM Bug #1590 (Duplicate): occasionally excessive mon memory footprint
- I have 3 mons that share disks with osds. Sometimes, when btrfs gets into a mode in which syncs are delayed, the mon...
09/30/2011
- 10:48 PM Revision 877cacbb (ceph): v0.36
- 09:42 PM Revision f5feda05 (ceph): Merge branch 'wip-pool-sharing'
- 06:37 PM Revision da61e1e7 (ceph): rbd.py: turn EROFS into an exception
- This is returned when trying to write to a snapshot.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> - 06:37 PM Revision faeecd81 (ceph): rbd.py: allow setting an image to no snapshot
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 06:37 PM Revision 1c1785da (ceph): rbd.py: use a dict to translate error codes
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 06:37 PM Revision 683f4dca (ceph): rbd.py: add class and method documentation
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 06:37 PM Revision c00e06f6 (ceph): doc: add documentation for librbd python bindings
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 05:36 PM Revision 19228d4a (ceph): rgw: revert part of commit:30b814e2677659ddda4109a1421f33a47d83a05b
- It's more consistent for RGWRados to delete the bucket object, rather
than the rgw_user functions.
And commenting fun... - 05:36 PM Revision b1bed355 (ceph): rgw: don't remove on-disk bucket object in rgw_user::rgw_remove_bucket
- This is the same object that rgw_rados removes from the root pool now.
And since nobody calls rgw_remove_bucket_info,... - 05:15 PM Revision 30b814e2 (ceph): rgw: don't remove bucket object twice
- Or else the second attempt will faile with -ENOENT.
Signed-off-by: Sage Weil <sage@newdream.net> - 05:13 PM Revision b441ecf5 (ceph): rgw: fix bucket-id assignment
- Get the version from the same io_ctx that you write with.
Also, use a private one, so that we don't race with other ... - 04:26 PM Revision 9b44469e (ceph): s3-tests: use radosgw-admin instead of radosgw_admin
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 04:26 PM Revision cb425c15 (ceph): s3-tests: use radosgw-admin instead of radosgw_admin
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 04:11 PM Revision b269d3cd (ceph): radosgw-admin: rename clitest dir
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:11 PM Revision cb2d3660 (ceph): radosgw-admin: fix acl vs content-length check
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:11 PM Revision 48558bb6 (ceph): rgw: separate bucket vs object owner tracking
- - track bucket_owner in session
- separte bucket and object owner fields in log entries
Signed-off-by: Sage Weil <sa... - 03:16 PM CephFS Bug #1589 (Resolved): MDS assert failure
- 2011-09-30 17:03:43.524357 7fc876c37720 ceph version 0.34.commit: 2f039eeeb745622b866d80feda7afa055e15f6d6. process: ...
- 02:43 PM Bug #1526 (In Progress): log bound mismatch after thrashing with bonnie
- This happened again today. From teuthology:~teuthworker/archive/nightly_coverage_2011-09-30/903/ceph.log:...
- 10:31 AM Bug #1588 (Can't reproduce): blogbench on kclient possibly made machine die
- This was sepia29. Nothing useful on the console, I had to powerc it, and nothing I could see in the logs.
- 10:23 AM rgw Feature #1561 (Resolved): rgw: admin command to get stats for a single bucket
- 10:23 AM Bug #1523 (Resolved): Erroneous prior_version in log for notify/head
- 10:10 AM Bug #1587 (Resolved): teuthology: handle SSHException when reconnecting
- It should keep retrying until the timeout expires.
- 09:59 AM CephFS Bug #1586 (Can't reproduce): failed pjd chmod test 00 on kclient
- Logs are in teuthology:~teuthworker/archive/nightly_coverage_2011-09-30/889...
- 09:53 AM CephFS Bug #1585 (Can't reproduce): mds crash during shutdown
- This crash looks like an invalid address was used. From teuthology:~teuthworker/archive/nightly_coverage_2011-09-30/8...
- 09:26 AM Bug #1524 (Resolved): osd got misdirected messages
- 09:25 AM rgw Feature #1582 (Resolved): radosgw-admin: log [list|show|rm]
09/29/2011
- 11:48 PM Revision 44d311af (ceph): radosgw-admin: fix help clitest
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:47 PM Revision f9792506 (ceph): Merge branch 'wip-pool-sharing' of github.com:NewDreamNetwork/ceph into...
- Conflicts:
src/rgw/rgw_bucket.h - 11:36 PM Revision a47d7ada (ceph): rgw: set log entry owner to user if s->acl is not set
- This is probably wrong, but it fixes the immediate problem of the first
entry in the log not having the owner field s... - 11:35 PM Revision a4e60491 (ceph): rgw: simplify bucket info storage
- Use a single method to store bucket metadata.
Store it in both locations, so it never diverges. (This can still be
... - 11:33 PM Revision aa7c5c5f (ceph): radosgw-admin: pull 'log show' owner+bucket from first entry
- Don't rely on the bucketinfo object for this, as it may be deleted. Having
it there most of the time but not always ... - 11:32 PM Revision 560f90c5 (ceph): rgw: fix RGWBucketInfo encoding of owner
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:09 PM Revision 4b8d72b3 (ceph): radosgw: fix log retry after bucket creation
- We were clobbering the object name for some reason.. probably cruft from
some old change.
Signed-off-by: Sage Weil <... - 08:46 PM Revision 80ba05e8 (ceph): radosgw_admin: we do want to set markers on these buckets
- Commit 25499b644b1c5a7b6f4c8876261334dda10fbec3 introduced the initial
work for pool sharing and markers, but didn't ... - 08:46 PM Revision 444ca656 (ceph): rgw: store bucket information in the .rgw pool instead of .buckets
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 07:04 PM Revision 79fddd20 (ceph): Cond.h: adjust nlock during waits
- Previously, is_locked could erroneously return true if there were any
threads waiting on a cond on that lock. In par... - 07:04 PM Revision 1eb1ce4d (ceph): librados: Make notify a linger op
- Notifies must be refreshed when the mapping changes.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> - 07:04 PM Revision d38b9a53 (ceph): ReplicatedPG: dump_watchers in do_osd_op_effects
- dump_watchers requires the osd watch_lock.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> - 06:50 PM Revision 2269dc25 (ceph): test_async_snap: loop a finite number of times.
- Signed-off-by: Sage Weil <sage@newdream.net>
- 06:48 PM Revision 697e664c (ceph): qa: btrfs: test_async_snap
- Hammer on the btrfs async sync/snap create/remove ioctls.
Signed-off-by: Sage Weil <sage@newdream.net> - 06:23 PM Revision 4be33097 (ceph): radosgw-admin: 'log list' and 'log rm'
- The normal object listing API seemed like a real poor match here so I
hacked in something that just lists the raw rad... - 04:39 PM rgw Bug #1584 (Resolved): rgw: swift key management is busted
- from wodrich: "just to make sure, I created a key on matwod-dev2 and it didn't have any anomalies displaying the swif...
- 04:18 PM Revision 120736ab (ceph): radosgw-admin: dump ints, not strings
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:16 PM Revision a1942e61 (ceph): radosgw-admin: fix bucket stats
- - 'usage' object instead of 'categories' array.
- dump ints, not strings.
Signed-off-by: Sage Weil <sage@newdream.net> - 04:09 PM Revision 52427589 (ceph): ceph_manager: parse osd numbers with dots
- This is necessary since wip-dot-names was merged.
- 03:39 PM Revision fc8588ff (ceph): rgw: protect the id-based accesses from namespace collisions
- Users can create buckets named "8", but they can't name them ".8". So
prepend the actual on-disk objects with a perio... - 03:38 PM Revision 47e5958f (ceph): rgw: remove get_bucket_info and convert users.
- This just lives in struct rgw_bucket now.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 03:37 PM Revision e701177b (ceph): radosgw-admin: fix 'bucket stats --uid='
- Signed-off-by: Sage Weil <sage@newdream.net>
- 03:09 PM Revision 569e7863 (ceph): Forgot to add ceph task to a couple thrashers.
- 01:56 PM Feature #1583: osd: bound pg log memory usage
- For comparison, here are some graphs of memory use in 0.34, with the 3210-PG cluster, given the following events:
... - 12:16 PM Bug #1579 (Resolved): watch notify
- Probably fixed in 1eb1ce4d36f369da82b100507fd8f781ac661a2e
- 11:15 AM CephFS Bug #1538: mds: all clients can and up becoming unresponsive, mds locker waiting for unfreeze
- I think I have a fix for this, let me know if it makes sense.
- 07:40 AM Bug #1490 (In Progress): cfuse assert failure: assert(ob->last_commit_tid < tid)
- Happened again with tiobench. From teutholoyg:~teuthworker/archive/nightly_coverage_2011-09-29/814/teuthology.log:
... - 04:38 AM Revision 81478414 (ceph): radosgw-admin: include 'suspended' in user info output
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:38 AM Revision 68917619 (ceph): radosgw-admin: clean up some cout usage
- Errors to stderr. Avoid cout for commands with structured output.
Signed-off-by: Sage Weil <sage@newdream.net> - 04:26 AM Revision 0870764c (ceph): radosgw-admin: use formatter for 'bucket list'
- Signed-off-by: Sage Weil <sage@newdream.net>
09/28/2011
- 11:09 PM Revision b69da176 (ceph): rdosgw_admin -> radosgw-admin
- Be consistent with other binary tool naming.
Signed-off-by: Sage Weil <sage@newdream.net> - 11:09 PM Revision 17603ee8 (ceph): radosgw-admin: use formatter for 'bucket list'
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:09 PM Revision 2f78faf1 (ceph): rgw_admin: default to json output
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 11:09 PM Revision 600126f3 (ceph): rgw_admin: fix --pretty-format and --purge-data flag parsing
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Conflicts:
src/rgw/rgw_admin.cc - 11:09 PM Revision 83c59cfb (ceph): rgw_admin: rip out format.empty() special cases
- If we want a plain output, we should implement a PlainFormatter of some
sort. For now, pretty json is good enough.
... - 11:09 PM Revision 0c75ec05 (ceph): radosgw-admin: clean up 'bucket list' output
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:09 PM Revision ab25a4bd (ceph): radosgw-admin: 'bucket stats --uid'
- List stats for all buckets on for the given user.
Signed-off-by: Sage Weil <sage@newdream.net> - 09:18 PM Revision 1392bbb8 (ceph): rgw: remove now-unused struct RGWPoolInfo
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 09:04 PM Feature #1583 (Resolved): osd: bound pg log memory usage
- Back in 0.34, my cluster with 3210 PGs 3-plicated across 3 OSD required some 4GB of RAM for the OSDs, i.e., with 3 OS...
- 08:57 PM Revision 2f1fc5ab (ceph): ceph: make -o - the default
- Finally.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 08:54 PM Revision 7eb15ce2 (ceph): ceph: make --concise hide 'N byte written' message
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 08:51 PM Revision 0eb433d4 (ceph): rgw: remove rgw_[retrieve|store]_pool_info and ".pool" pool
- Convert these to rgw_[get|store]_bucket_info, add the owner field
to bucket info, and store both lookup formats in th... - 07:19 PM Revision 4884f06f (ceph): osd: fix leak of src_obc references
- We never moved the src_obc map from the local var into the RepGather
member!
Signed-off-by: Sage Weil <sage.weil@dre... - 07:18 PM Revision a883c83d (ceph): librbd: fix end_block calculation for read_iterate
- All end block calculations match now.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> - 07:18 PM Revision 1e4fdf51 (ceph): librbd: don't zero negative lengths
- They are past the end of the buffer (and wrap around).
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> - 05:50 PM Revision c2fbde4d (ceph): rgw: remove references to pool_id and replace with new bucket_id.
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 04:17 PM rgw Feature #1543 (Resolved): rgw: usage accounting for multiple buckets in a pool
- 04:14 PM rgw Feature #1582 (Resolved): radosgw-admin: log [list|show|rm]
- Don't make the user peek at rados directly. Add
log list -- list log objects
and maybe
log rm --object=... - 03:49 PM Revision bd914440 (ceph): Use LIBEDIT_LIBS in Makefile.am
- The editline library might require some additional libs, so
instead of hardcoding '-ledit' we should be using LIBEDIT... - 11:50 AM Bug #1581 (Resolved): teuthology: restarting osds sometimes allows daemon-helper to fail
- This causes the test to be marked failed. From teuthology:~teuthworker/archive/nightly_coverage_2011-09-26/652/teutho...
- 08:52 AM Bug #1150 (Duplicate): kclient: ERESTARTSYS from flock/fcntl locks
- I forgot about this bug! It's almost certainly the same as #1475 -- EINTR and ERESTARTSYS are synonyms, right? :)
- 08:48 AM Bug #1150: kclient: ERESTARTSYS from flock/fcntl locks
- > the ping_pong code is here:
> http://junkcode.samba.org/ftp/unpacked/junkcode/ping_pong.c
>
> l start by running... - 08:47 AM RADOS Feature #1576: Deduplication support in RADOS
- Not aware of anything like that, sorry!
- 03:18 AM RADOS Feature #1576: Deduplication support in RADOS
- Thanks Greg. Yep, for sure I'm aware you have other priorities first.
In the meantime it is implemented, are you a... - 04:47 AM Revision aa20f0d6 (ceph): Merge branch 'wip-dotnames'
- 04:46 AM Revision a1521ae8 (ceph): clientN -> client.N
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 04:43 AM Revision 214e7b19 (ceph): monN -> mon.N
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 04:42 AM Revision f5fd7f19 (ceph): mdsN -> mds.N
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 04:34 AM Revision 4b09c1ad (ceph): osdN -> osd.N
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 04:29 AM Revision 594180ad (ceph): msgr: print entity_name_t with a .
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:28 AM Revision fa2fdd9c (ceph): osd: fix leak of src_obc references
- We never moved the src_obc map from the local var into the RepGather
member!
Signed-off-by: Sage Weil <sage.weil@dre... - 04:19 AM Revision fc2df623 (ceph): test-rados-api: test tmap rm
- Make sure we get ENOENT if the entry doesn't exist.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 04:16 AM Revision 21aa6d58 (ceph): osd: error out current op only on tmap ENOENT
- If an individual op in do_osd_ops() fails, set result, and continue to the
end of the loop. Normally we'll return th... - 04:03 AM Revision ce086ff3 (ceph): osd: skip replay phase if osd_replay_window=0
- The replay phase is only useful if there are clients waiting for ACK (but
not COMMIT) and expect ordering to be prese... - 04:03 AM Revision 532c594c (ceph): osd: some PgPriorSet comments, trivial cleanups, new FIXME
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
09/27/2011
- 10:50 PM Revision 390b7905 (ceph): ReplicatedPG: remove assert in remove_watcher
- notif is not in notif->session->notifs.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> - 10:19 PM Revision 57ea6b67 (ceph): rgw: don't encode the bucket name twice in RGWPoolInfo!
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 09:10 PM Revision a28047b4 (ceph): ReplicatedPG: clean up watched objects on role change
- Also removes inconsistent watch handling in handle_notify_timeout.
We will need to handle watch timeouts elsewhere.
... - 09:07 PM Revision e3eb2f25 (ceph): rgw: put bucketid allocator object in root (.rgw) pool
- This keeps the .rgw.control pool disposable.
Signed-off-by: Sage Weil <sage@newdream.net> - 08:56 PM Revision 8953c4d3 (ceph): rgw: use same prefix for locator key as for oid
- If the bucket has a prefix for oids, prepend the same prefix to the
locator key.
Signed-off-by: Sage Weil <sage@newd... - 08:09 PM Revision e63b86d7 (ceph): ceph-authtool: fix -C
- Fixes: #1578
Signed-off-by: Sage Weil <sage@newdream.net> - 08:08 PM Revision 607634f6 (ceph): ceph.spec.in: radosgw init script
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:06 PM Revision 3a73606b (ceph): mon: fix error return codes for 'auth ...'
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:06 PM Revision b690475c (ceph): mon: auth: implement 'auth print-key <name>'
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:41 PM Revision 25ff9fdf (ceph): debian: move ceph and ceph-authtool into ceph-common
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:41 PM Revision 9be9f916 (ceph): mon: auth: generate random key on 'auth add ...' if no keyring is provided
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:34 PM Revision edb2587a (ceph): ceph.spec.in: add rbd python bindings
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 07:34 PM Revision 951ce29e (ceph): debian: make python-ceph depend on librbd
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 07:31 PM Revision 58003d23 (ceph): pybind: fix errors found by pyflakes
- Unused imports, typos, and unused variables.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> - 05:02 PM Revision 1a14a23d (ceph): debian: ceph-client-tools -> ceph-common, now required, w/ ceph-conf etc.
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:47 PM Revision 68839a68 (ceph): rgw: list buckets using bucket objects
- Don't assume the pools == buckets. List the bucket objects in the .rgw
pool.
Fixes: #1560
Signed-off-by: Sage Weil ... - 04:37 PM Bug #1580 (Resolved): watch expiration
- expiring watches need to be detected and handled
- 04:36 PM Bug #1579 (Resolved): watch notify
- Running test_stress_watch while thrashing osds seems to eventually cause a lost notify
- 04:15 PM Revision 9e2edce2 (ceph): osdmap: remove dead code
- Signed-off-by: Sage Weil <sage@newdream.net>
- 03:28 PM Revision d3646281 (ceph): Merge remote branch 'origin/master' into wip-pool-sharing
- Conflicts:
src/osd/OSD.cc
src/rgw/rgw_rados.cc - 03:26 PM rgw Feature #1561: rgw: admin command to get stats for a single bucket
- Well, I was going to do this now but we need to deal with the marker/bucket_id situation first. Gah!
- 01:41 PM rgw Feature #1532 (Resolved): add radosgw init.d script to radosgw deb
- 01:41 PM rgw Feature #1531 (Resolved): radosgw init.d script stop/restart
- 01:06 PM Bug #1578 (Resolved): ceph-authtool: -C option does not work
- 01:01 PM Bug #1578 (Resolved): ceph-authtool: -C option does not work
- Usage says:...
- 01:00 PM rgw Bug #1566 (Resolved): rgw: use a global bucket id
- Simple enough. commit:c780494d8d5f0f0f3ad372a07227b631879cf2a9
- 10:55 AM Bug #1577 (Resolved): rados.py: Snap.get_timestamp does not work
- It was partially completed in commit:1065bef0eb777117a2950fa7fefeff8233b4e29e when updating the librados api.
- 09:50 AM rgw Feature #1560 (Resolved): rgw: admin command to list buckets
- 08:42 AM RADOS Feature #1576: Deduplication support in RADOS
- This is a blue-sky feature. It's been discussed in the past and will probably happen someday, but isn't an easy featu...
- 03:19 AM RADOS Feature #1576 (New): Deduplication support in RADOS
- Hi,
Ceph and RADOS are wonderfull and allow us to scale the storage. But one great feature would be to have a dedu... - 04:49 AM Revision 9045b3f5 (ceph): Merge branch 'stable'
- 04:48 AM Revision d340e8e7 (ceph): radosgw: fix content-length checks
- Ignore content-length check if the REQUEST_URI has a trailing ?acl.
(The object_str.find() check was wrong because o... - 04:47 AM Revision e47c11cf (ceph): radosgw: tolerate race creating .rgw* metadata pools
- There may be multiple people trying to create these pools. That's just
fine.
Signed-off-by: Sage Weil <sage@newdrea... - 01:10 AM Revision e8d476da (ceph): rbd.py: pass 0 for the default order, not NULL
- librbd expects the order pointer to be valid - if it points to 0, the
default order is used.
Signed-off-by: Josh Dur... - 01:10 AM Revision 5cd6fad4 (ceph): rbd.py: explicitly cast strings to c_char_p for type clarity
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 01:10 AM Revision 10157d2e (ceph): rbd.py: be paranoid about strings
- This prevents bad conversions (i.e. from int to char *).
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> - 01:10 AM Revision a28eea85 (ceph): rbd.py: remove useless version object
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 01:10 AM Revision 4bb553b9 (ceph): rados.py: be paranoid about strings
- This prevents bad conversions (i.e. from int to char *).
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> - 01:10 AM Revision 8ca79a96 (ceph): librbd: don't zero negative lengths
- They are past the end of the buffer (and wrap around).
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> - 01:10 AM Revision d71bf04f (ceph): test_rbd.py: Add large read and write tests
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 01:10 AM Revision 916e49d7 (ceph): librbd: fix end_block calculation for read_iterate
- All end block calculations match now.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> - 01:10 AM Revision afa30640 (ceph): librbd: add debugging for failing to remove a header object
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 01:10 AM Revision 74f07fbd (ceph): librbd: use pre-existing helper methods for tmap operations
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 01:10 AM Revision 0cea48a6 (ceph): ReplicatedPG, tmap: return -ENOENT if the key to remove does not exist
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 01:10 AM Revision 9983f076 (ceph): rbd: init counter to 0 so errors don't say '-1% done'
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 01:10 AM Revision fa691dfe (ceph): rados.py: raise specific error when write is too long
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 01:10 AM Revision 5f9be6fb (ceph): rbd.py: add partial bindings for librbd
- This is all the basic operations, but nothing with callbacks yet.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.... - 01:10 AM Revision bc16878c (ceph): Use cpp_strerror or strerror_r when appropriate.
- The only remaining uses of strerror are in single-threaded programs
that don't depend on libcommon.
Signed-off-by: J... - 01:10 AM Revision a381294e (ceph): rbd.py: make exceptions inherit from a base class
- This way you can catch them all.
Also remove the unused NoData exceptions
- this was just useful for xattrs in librad... - 01:10 AM Revision c34e87d0 (ceph): rados.py: make Rados and Ioctx objects context managers
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 01:10 AM Revision c60abe1b (ceph): rbd.py: make Image a context manager
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 01:10 AM Revision c53d05af (ceph): rados.py: allow configuring rados through constructor options
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 01:10 AM Revision 69a5e795 (ceph): rados.py: make exceptions inherit from a base class
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 01:10 AM Revision 2d8f52f0 (ceph): rbd: improve error messages
- One of these was accidentally not negated.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
09/26/2011
- 11:36 PM Revision 56ce7c20 (ceph): mon: fix it again
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:25 PM Revision e1eea2b5 (ceph): mon: fix dup pool creation race
- Fixes: #1574
Signed-off-by: Sage Weil <sage@newdream.net> - 10:11 PM Revision c780494d (ceph): rgw: get bucket markers from the same object at all times
- We use an object in the control pool here, rather than an object
local to each pool. This gives us a single value whi... - 09:51 PM rgw Bug #1575 (Resolved): rgw: failing s3tests.functional.test_headers:test_object_create_bad_content...
- commit:d340e8e742d119658206928ca50238841b147be5
- 04:35 PM rgw Bug #1575 (Resolved): rgw: failing s3tests.functional.test_headers:test_object_create_bad_content...
- This passes as recently as commit:4c98418bb99a78a2821ddcbd5cb93ede6f1f8749...
- 09:51 PM rgw Bug #1574 (Resolved): rgw: creating multiple metadata pools?
- commit:e47c11cf5d7ba15a37768468b7d369568fd41293
- 03:18 PM rgw Bug #1574: rgw: creating multiple metadata pools?
- ie:...
- 03:10 PM rgw Bug #1574 (Resolved): rgw: creating multiple metadata pools?
- While testing on sepia, I'm noticing that I keep ending up with two of the ".rgw", ".rgw.control", etc pools. This ha...
- 09:25 PM Revision d27d9d89 (ceph): init-ceph: more c* -> ceph-* cleanup
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:08 PM Revision 9cb6c550 (ceph): osd: fix warning more
- Argh
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
Signed-off-by: Sage Weil <sage@newdream.net> - 09:03 PM Revision 7cd4c688 (ceph): radosgw_admin: 'bucket list' or 'buckets list'
- The plural looks weird to me.
Signed-off-by: Sage Weil <sage@newdream.net> - 08:30 PM Revision 3b10fd78 (ceph): Makefile: include init-radosgw in tarball
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:28 PM Revision 0dc45bea (ceph): radosgw: shut down threadpool
- Don't crash when run as a non-daemon without apache.. e.g. 'radosgw' with
no args.
Fixes: #1572
Signed-off-by: Sage ... - 08:24 PM Revision 774aa25b (ceph): rgw: pass POD c-string instead of string to formatter
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 08:23 PM Revision 38c6fa5d (ceph): osd: fix warning more
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 08:18 PM Revision bd1625b1 (ceph): Merge remote branch 'origin/master' into wip-pool-sharing
- 08:10 PM Revision b582e7cd (ceph): osd: fix warning
- Signed-off-by: Sage Weil <sage@newdream.net>
- 06:04 PM Revision 8563b96f (ceph): debian: include radosgw init script in package
- Signed-off-by: Sage Weil <sage@newdream.net>
- 06:03 PM Revision b19a2006 (ceph): radosgw: init script
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:11 PM Revision 10e90abf (ceph): Add some thrashing tasks.
- This includes only in-out toggling (default), as well as restarting daemons.
- 02:49 PM CephFS Bug #1573 (Duplicate): mds crash during multiple_rsync workunit
- ...
- 01:24 PM rgw Bug #1572 (Resolved): radosgw: don't crash when rgw socket path not specified
- 11:41 AM rgw Bug #1572 (Resolved): radosgw: don't crash when rgw socket path not specified
- Error out gracefully instead of spewing...
- 11:31 AM rgw Feature #1544: rgw: explicit bucket index
- I've attached our current design doc, such as it is.
- 11:29 AM Feature #1571 (Resolved): osd: non-trivial map object
- tmap is convenient but slow on large mappings. We should build a better one. (RGW in particular will appreciate it.)
- 11:28 AM rgw Bug #1570 (Resolved): rgw: use tmap for bucket index objects
- Using the tmap will make it a lot easier for us to leverage better options that get built.
- 11:28 AM Feature #1569 (Resolved): osd: create a tmap class api
- We want to be able to use tmap (and, eventually, a less stupid key-value store) for the rados gateway, and other purp...
- 11:26 AM rgw Bug #1568 (Rejected): rgw: add object_locator to bucket index
- We want to include the object locator in the index so we can find temporary and multi-part upload object without havi...
- 11:22 AM rgw Bug #1567 (Resolved): rgw [list|delete]_bucket should clean up
- We've discussed how to clean up properly if the bucket index has unfinished ops, and it needs to be implemented:
D... - 11:20 AM Bug #1563: OSD isn't prioritizing data with waiting ops during transfer
- Copied locally to kai:~gregf/logs/ajm_osd_not_prioritizing_reads.log
- 11:07 AM Bug #1563: OSD isn't prioritizing data with waiting ops during transfer
- log file from the affected OSD: http://adam.gs/osd.5.log.1317056213.bz2
md5(osd.5.log.1317056213.bz2) = c162d935... - 09:30 AM Bug #1563 (Closed): OSD isn't prioritizing data with waiting ops during transfer
- ajm reported on irc that his MDS was stuck in replay, and it turned out to be because it was waiting for a read respo...
- 11:14 AM rgw Bug #1566 (Resolved): rgw: use a global bucket id
- The new version of rgw currently uses bucket IDs that are unique within a single pool. Make them unique across all po...
- 10:31 AM Feature #1498 (Resolved): qa: add osd thrashing tasks
- Added in 10e90abf770b61fee4d69c384d0ba47aaf259f2e of ceph-qa-suite.git.
- 09:59 AM Feature #1565 (Resolved): crowbar demo
- 09:57 AM rgw Bug #1550 (Closed): radosgw fails test_object_create_bad_expect_empty with a 500 response
- 09:48 AM Feature #1517 (Resolved): qa: automate node setup after reinstall
- 09:30 AM Bug #1564 (Won't Fix): osd: osd should not be primary before data is replicated
- Right now an OSD is kicked out of the acting set only if it needs a backlog, and it's allowed back in to the acting s...
09/25/2011
- 08:54 PM Revision 9da0fdf4 (ceph): Merge branch 'stable'
- 08:54 PM Revision 30d81fe1 (ceph): filejournal: improve debug error messge
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 03:52 PM Bug #1562 (Resolved): osd: fix osd replacement
- Saw some weird and bad behavior when wiping+replacing an osd in an aged cluster.
- the new osd would walk through ...
09/24/2011
- 10:49 PM Revision 8aa15e8c (ceph): osd/mon: make max maps per MOSDMap message tunable
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 10:49 PM Revision 8711c32a (ceph): osd: limit size of osdmap messages
- Limit size of MOSDMap messages sent from OSDs. Send many smaller
messages instead of a single large one.
Signed-off... - 10:19 PM Revision 56071cc1 (ceph): osd: drop map_cache_keep_from
- The purpose here was to avoid trimming cached maps prior to what we have
on disk. However, now that we have the map_... - 10:16 PM Revision 59bcb0de (ceph): osd: limit size of OSDMap cache
- If we get way way behind on our maps, we may end up with a really large
OSDMap cache because we currently on trim old... - 09:53 PM Revision 720788c0 (ceph): rgw: only require content-length to be set on non-acl puts
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 09:47 PM Revision 4aa90a5e (ceph): osd: don't finish boot unless instance in map is really us
- We were going BOOTING->ACTIVE as soon as we showed up in the map with the
same client_addr. Also verify that we were... - 09:08 PM Revision 9fe49f5d (ceph): init-ceph: don't umount btrfs by default
- As an admin I find this very annoying, even though it isn't strictly
symmetrical with the mount behavior.
Signed-off... - 08:49 PM Revision ad38abcf (ceph): - Fix atomic set.
- 06:13 AM Revision 67094554 (ceph): rgw: user async exec for index completion op
- 06:13 AM Revision c8bd67b4 (ceph): librados: add async exec
- 05:36 AM Revision 53695134 (ceph): rgw: tmp objects can be removed async
- 04:32 AM Revision 6b9817af (ceph): rgw: fix bucket stats
- 04:21 AM Revision 24176176 (ceph): rgw: fix header encoding
- 12:26 AM Revision 230ec89e (ceph): rgw: fix compilation warning
- 12:22 AM Revision 37f5da43 (ceph): rgw: fix compilation
- 12:19 AM Revision b7ec4d5d (ceph): cls_rgw: substract obj stats only if obj exists
- 12:11 AM Revision ca77ba77 (ceph): rgw: integrate index categories
09/23/2011
- 11:00 PM Revision 623c6916 (ceph): Merge remote branch 'gh/stable'
- 10:55 PM Revision cdecf718 (ceph): man: c* -> ceph-* rename: Regenerate manpages.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:55 PM Revision 8ca4c5a1 (ceph): doc: Add a space after sudoers "NOPASSWD:", as that seems more common.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:55 PM Revision b2d46ef3 (ceph): doc: Search page is always in sidebar, no need to have it on page.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:55 PM Revision c4166492 (ceph): doc: Add index into the sidebar.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:55 PM Revision 1ce18d3a (ceph): doc: v0.35 is out, remove rpm build workaround.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:55 PM Revision 98b55b30 (ceph): Makefile: c* -> ceph-* rename: missed crun.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:55 PM Revision dea14f7e (ceph): rpm: c* -> ceph-* rename: missed crbdnamer, cdebugpack.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:55 PM Revision 3fd3c6be (ceph): debian: c* -> ceph-* rename: missed csyn, crbdnamer.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:55 PM Revision da8fa783 (ceph): udev: c* -> ceph-* rename: missed crbdnamer.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:55 PM Revision 0c2cfa18 (ceph): ceph-debugpack: c* -> ceph-* rename: use "ceph-debugpack" as temp dir n...
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:55 PM Revision a62108bf (ceph): ceph-run: c* -> ceph-* rename: Use ceph-run as stderr prefix.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:55 PM Revision e35d9de0 (ceph): Makefile: include run-cli-tests-maybe-unset-ccache in dist tarball.
- Apparently "make distcheck" has been broken for 3 months;
I find that hard to believe, but that's what it looks like.... - 10:55 PM Revision d32592e4 (ceph): .gitignore: distcheck temporary directory.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:55 PM Revision 8506c5b3 (ceph): Makefile: Add missing header test/unit.h
- Used to fail "make distcheck".
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> - 10:55 PM Revision 3fe96bec (ceph): Makefile: c* -> ceph-* rename: missed cdebugpack in CLEANFILES.
- make distcheck said:
ERROR: files left in build directory after distclean:
./src/ceph-debugpack
make[1]: *** [... - 10:55 PM Revision 7f301510 (ceph): doc: Fix reStructuredText formatting warnings.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:55 PM Revision 65d2c499 (ceph): doc: Leftovers of the c* -> ceph-* rename.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:55 PM Revision 76fbdfb3 (ceph): doc: Add index entries, remove glossary as it's practically replaced by...
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 10:49 PM Revision 00a7d3ca (ceph): Revert "rgw: tolerate missing content-length header on canned ACL puts"
- This reverts commit 05b06e807ef20c7fe1bd7c7abbeecd656d2280c0.
Don't be stupid when an empty content-length can only ... - 10:49 PM Revision 5a397241 (ceph): rgw: only require content-length to be set on non-acl puts
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 10:49 PM Revision 29bbcee9 (ceph): rgw: update index when doing put_obj_meta
- this fixes multipart upload listing
- 10:19 PM Revision 05b06e80 (ceph): rgw: tolerate missing content-length header on canned ACL puts
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 09:42 PM Revision 2ffb04ba (ceph): rgw: fix a few regressions
- 09:38 PM Revision 3b5cb69d (ceph): cls_rgw: list entries return upper_bound of marker
- 09:24 PM Feature #1501 (Resolved): librbd: python bindings
- 09:24 PM Feature #1212 (Resolved): teuthology: ability to restart daemons while other tasks are running
- 07:55 PM Revision 878fedbb (ceph): osd: fix race between handle_osd_ping and handle_osd_map
- If handle_osd_map is in progress and handle_osd_ping doesn't have the
map lock, we can't call osdmap->get_inst() in s... - 07:55 PM Revision e0be65cf (ceph): mon: remember source client address in routed requests
- when we resend_routed_requests, the source client address is lost.
This may cause problems. For example, if we resend... - 05:04 PM Revision 0fdc8638 (ceph): rename source files c* -> ceph-*
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:04 PM Revision dd8d4ecd (ceph): Makefile: drop useless all_sources thing
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 04:42 PM Revision 5369c776 (ceph): misc: use strncpy to prevent buffer overflow
- 04:40 PM Revision 4b8cf145 (ceph): ceph-elaster: add parentheses around macros
- 04:40 PM Revision 17071816 (ceph): test_store: parse args, don't link librados
- Signed-off-by: Sage Weil <sage@newdream.net>
- 03:57 PM Revision a92fef77 (ceph): rename c* -> ceph-*
- Leave cfuse task name unchanged for now...
- 03:18 PM rgw Bug #1550: radosgw fails test_object_create_bad_expect_empty with a 500 response
- this is because sepia has the wrong apache2 or libapache2-mod-fastcgi packages
- 03:12 PM rgw Bug #1551 (Won't Fix): radosgw returns 400 instead of 403 on unreadable authorization
- marking this as fails-on-rgw in s3-tests.
- 12:46 PM rgw Feature #1561: rgw: admin command to get stats for a single bucket
- We have such a command (radosgw_admin bucket stats). Currently it dumps wrong data, we need to make it gets the info ...
- 10:37 AM rgw Feature #1561 (Resolved): rgw: admin command to get stats for a single bucket
- 12:44 PM rgw Feature #1560: rgw: admin command to list buckets
- there's already 'radosgw_admin buckets list' command, and it works ok if we specify --uid. However, we need to make i...
- 10:37 AM rgw Feature #1560 (Resolved): rgw: admin command to list buckets
- 10:03 AM Feature #1559 (Resolved): teuthology: continue waiting if the lock server fails
- The lock server may temporarily be unavailable due to network or database issues. Right now this makes tasks fail, bu...
- 10:01 AM Bug #1558 (Resolved): osd crash when deleting pg
- This happened during rados_api_tests. Logs are in teuthology:~teuthworker/archive/nightly_coverage_2011-09-23/470
... - 09:16 AM Feature #1557 (Resolved): teuthology: summary string
- On error, it can be something like 'errors in ceph.log' or 'exception in ___'.
For s3-tests, it could be 'N tests ... - 06:14 AM Revision 5ede4c87 (ceph): Merge branch 'wip-pool-sharing' of ssh://github.com/NewDreamNetwork/cep...
- 06:14 AM Revision 5f951728 (ceph): rgw: fix clone in case state is NULL
- 05:33 AM Revision e2414330 (ceph): rgw: send correct object id to class op
- 05:30 AM Revision abdb3272 (ceph): rgw: encode correct timestamp
- 04:29 AM Revision 10c5ceef (ceph): rgw: fix rgw_admin arg parsing
- 04:22 AM Revision 00e03327 (ceph): rgw: generate tag if doesn't exist
- 04:11 AM Revision 9441c419 (ceph): crushtool: add unit test for adding items to map
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 04:02 AM Revision 6eb8862e (ceph): crushtool: fix argument parsing
- Reported by: Henry C Chang <henry.cy.chang@gmail.com>
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 04:02 AM Revision 33151a9d (ceph): crushtool: crush_finalize on any map modification
- This recalculates max_devices and the parent maps.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 04:02 AM Revision e6eeaacc (ceph): Revert "crush: refuse to add item >= max_devices"
- This reverts commit 58f98e7afc364d28a385adc7ef0fee2291d70c17.
max_devices only affects the size of the parent arrays... - 01:23 AM Revision c7ff5fc3 (ceph): queue: results_timeout needs to be converted to a string
- 01:08 AM Revision b22fab3c (ceph): Last run of iozone uses 10240M, so increase image size.
- 12:16 AM Revision b873ec8d (ceph): rgw: two phase commit for index updating
- Just compiles, not tested, probably wouldn't work.
09/22/2011
- 11:20 PM Revision c5523239 (ceph): Merge branch 'stable'
- 11:19 PM Revision f9c3cb10 (ceph): Merge branch 'wip-names'
- 11:18 PM Revision 3e9a9360 (ceph): doc: more c* -> ceph-* renames
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:18 PM Revision bfbda964 (ceph): man: rebuild manpages
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:40 PM Revision ba9271ca (ceph): rbd: set default pool when none is specified
- 096e3b6353e5035362cffdcbd2e4a4f5572aa2ba broke this by only using
set_pool_image_name for commands that accept the sn... - 10:08 PM Revision 6f8f1403 (ceph): c* -> ceph-*
- Hopefully I didn't miss too much...
Signed-off-by: Sage Weil <sage@newdream.net> - 10:08 PM Revision fba541e4 (ceph): libceph -> libcephfs
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:47 PM Revision 97aa1aab (ceph): mount.ceph: use ":/" instead of just ":" as ip/path delimiter
- This is tolerant of colons in the mount subdir.
Signed-off-by: Sage Weil <sage@newdream.net> - 09:47 PM Revision e124b15b (ceph): addr_parsing: null terminate safe_cat result
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:47 PM Revision 17b2451a (ceph): mount.ceph: fix use-after-free
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:25 PM Revision ef56a72b (ceph): task/watch_notify_stress.py: add simple watch_notify stress test
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 08:20 PM Revision ac1a40d1 (ceph): test/rados-api/test.cc: Add ability to set client id
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 08:18 PM Revision 4686b56d (ceph): test/test_stress_watch.cc: added simple watch stress test
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 04:57 PM Revision 5503d450 (ceph): PG: set log.backlog to false on corrupt log
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 04:56 PM Revision a01a947a (ceph): PG: set log.backlog to false on corrupt log
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 04:50 PM Revision 0fbf86c2 (ceph): rgw: fix rgw_bucket_dir_entry encoding
- 02:44 PM Bug #1556 (Resolved): mount -t ceph server:/ /mnt/point no longer works in 0.35
- fixed by commit:e124b15bc41aa0dd3f8ec02f780e61f1a65b7cc7 and commit:17b2451a645417213cf18fa3c83d856947b8588e
- 02:15 PM Bug #1556 (In Progress): mount -t ceph server:/ /mnt/point no longer works in 0.35
- i probably broke this when i changed the ipv6 addr parsing... will take a look
- 11:32 AM Bug #1556 (Resolved): mount -t ceph server:/ /mnt/point no longer works in 0.35
- In my home network, ceph is a name that resolves to the IPs of all ceph monitors, so I run:
[root@freie ~]# mount ... - 11:06 AM CephFS Bug #1553 (Duplicate): file locking test 2 fails
- Same issue as #1552.
- 10:59 AM CephFS Bug #1552: qa: file locking test fails
- This still doesn't work with the changes to the lockfile task. It looks to me like it needs some barriers instead of ...
- 06:12 AM Revision 6f519f9d (ceph): rgw: list objects (almost completely) works
- 12:27 AM Revision b36b01f1 (ceph): rgw: obj listing doesn't stat object
- 12:14 AM Revision 98d0361d (ceph): rgw: store more info for each indexed object
09/21/2011
- 11:27 PM Revision 82a19351 (ceph): rbd: fix progress redraw
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 11:27 PM Revision ca63faf5 (ceph): mds: fix traverse snap vs forward check
- This should compare against the forward attempt, not retry attempt.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 11:27 PM Revision 68fe748f (ceph): osd: fix PG::copy_after vs backlog
- If you call copy_after(..., 0) on a log with a backlog, you get all the
backlog entries, but no backlog flag. That's... - 11:27 PM Revision 8cb57462 (ceph): vstart: debug filestore = 20
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 11:19 PM Revision ebe6d08c (ceph): cls_rgw: store more info for each entry, stats categories
- 10:20 PM Revision 1c2cc8bc (ceph): rgw: account object removal
- 10:12 PM Revision 8403daf8 (ceph): rgw: account clone_range dest object
- 09:55 PM Revision f488908c (ceph): doc: Content for Getting Started with cephfs and rbd.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 09:17 PM Revision 028ba54f (ceph): rgw: class init_index
- 08:46 PM Revision 9888fc6d (ceph): doc: Split manage into multiple pages.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 08:46 PM Revision d292aee8 (ceph): doc: Move ops/grow under ops/manage.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 08:46 PM Revision 8648b7a5 (ceph): doc: Move recommendations under /rec.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 08:46 PM Revision bc9477af (ceph): doc: Reorganize ops/manage/
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 08:46 PM Revision 093f4f33 (ceph): doc: Split data placement into concrete operations and recommendations.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 08:46 PM Revision c01d36cf (ceph): doc: Move config reference to top-level.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 08:46 PM Revision 47dfe29f (ceph): doc: Separate key management from mounting.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 08:46 PM Revision c3fae7e7 (ceph): doc: Structure for Getting Started.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 08:46 PM Revision 69fabca6 (ceph): doc: Content for Getting Started with RADOS.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 08:46 PM Revision c448c4c0 (ceph): doc: Clean reStructuredText syntax.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 08:46 PM Revision 331510f3 (ceph): doc: Split install into multiple pages.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 08:37 PM Revision 2c842053 (ceph): Merge branch 'stable'
- 08:37 PM Revision aa666b13 (ceph): objclass: add stat operation
- 07:15 PM Revision 2ec5f158 (ceph): cls_rgw: list marker uses lower_bound
- 06:05 PM Revision c3c26265 (ceph): schedule: put results timeout in the job
- The default was always being used instead.
- 05:43 PM Revision 894a8b66 (ceph): client: tear down dir when setting I_COMPLETE on empty
- If the dir is supposed to be empty and we are setting I_COMPLETE, empty
it out and close it. This ensures we don't r... - 04:50 PM Revision b9e32fff (ceph): rados: accept '-b' as an argument.
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 04:47 PM Revision 2c28e1c7 (ceph): Makefile: include config_opts.h
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:47 PM Revision 0afda378 (ceph): v0.35
- 04:42 PM Revision fdd3d1da (ceph): Merge branch 'master' of github.com:NewDreamNetwork/ceph
- 04:35 PM Revision 6068fc83 (ceph): osd: set reply version for dup requests
- If we get a dup request, set the version in the reply. That means the
client knows the client was successful and com... - 04:35 PM Revision 0852ecfa (ceph): mon: remove unused MonitorStore::sync()
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:35 PM Revision b39f0808 (ceph): mon: make fsync vs sync threshold configurable
- If mon+osd+client are on the same machine, sync() can deadlock. Setting it
to 0 disables the big sync. And the cuto... - 04:35 PM Revision 43967f5e (ceph): auth: keyring: whitespace
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:34 PM Feature #1337 (Rejected): osd: support alphanumerically sorted list-objects
- 04:30 PM Bug #1526 (Resolved): log bound mismatch after thrashing with bonnie
- should be fixed by commit:68fe748fc2d703623050e8f2a448a0fd31ca8a0f
- 01:38 PM Bug #1555 (Resolved): radosgw_admin --gen-access-key=false and --gen-secret=false flags appear to...
- Running radosgw_admin user create with access/secret keys specified should render --gen-access-key and --gen-secret m...
- 11:28 AM CephFS Bug #1509 (In Progress): cfuse sometimes hangs after unmount
- 10:01 AM CephFS Bug #1509: cfuse sometimes hangs after unmount
- This occurred again on the snaps workunit in teuthology:~teuthworker/archive/nightly_coverage_2011-09-21/372. cfuse w...
- 08:01 AM Feature #1212: teuthology: ability to restart daemons while other tasks are running
- Isn't this done as of commit:a3c886af19f370c2bf1ccaa973758bb1c630f7bc in teuthology?
- 04:34 AM Revision b2fbbf0f (ceph): rgw: implement rgw_rados helpers for class calls
- 12:02 AM Revision 56413b8e (ceph): mkcephfs: create /var/run/ceph (or wherever pid_file and admin_socket l...
- Fixes: #1546
Signed-off-by: Sage Weil <sage@newdream.net> - 12:01 AM Revision f5c16321 (ceph): cconf: do not common_init_finish
- All that common_init_finish() does is indicate that we're done initializing
and we're allowed to start up extra threa...
Also available in: Atom