Project

General

Profile

Activity

From 09/18/2011 to 10/17/2011

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> Sage Weil
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> Tommi Virtanen
10:35 PM Revision 3c90c0d4 (ceph): add singleton lost-unfound
Sage Weil
10:32 PM Revision 4ec37b23 (ceph): add lost_unfound task
Also some misc useful bits to ceph_manager. Sage Weil
10:21 PM Revision edcd4d97 (ceph): rgw: some more swift fixes
Yehuda Sadeh
09:45 PM Revision 83cf3fef (ceph): Expect 'wrongly marked me down' messages during thrashing
Josh Durgin
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
Josh Durgin
09:13 PM Revision 0bad37e3 (ceph): streamtest: do mkfs
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
09:12 PM Revision 525a610f (ceph): streamtest: print to stdout
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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>
Sage Weil
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.
Josh Durgin
04:56 PM Bug #1623 (Can't reproduce): ceph-osd fails to bind socket
... Yehuda Sadeh
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>
Sage Weil
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...
Sage Weil
03:49 PM Revision 195a484b (ceph): ceph.spec: capitalize first letter to make rpmlint happy
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
03:35 PM Revision a6f3bbb7 (ceph): v0.37
Sage Weil
03:27 PM Bug #1473 (Resolved): osd assert failure: FAILED assert(0 == "oi disagrees with stat, or error c...
Samuel Just
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). Samuel Just
03:25 PM Bug #1486 (Resolved): osd: 0-length meta/pginfo_* files
Sage Weil
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...
Sage Weil
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. Samuel Just
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. Josh Durgin
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. Sage Weil
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...
Sage Weil
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...
Sage Weil

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> Sage Weil
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...
Sage Weil
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...
Sage Weil
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> Sage Weil
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...
Sage Weil
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...
Sage Weil
04:02 AM Revision c3fa0783 (ceph): messages/MOSDPG*: clean up output a bit
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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-...
Sage Weil
04:02 AM Revision 22684f25 (ceph): osd: pass version explicitly to pull
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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 <...
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...
Sage Weil
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...
Sage Weil
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@...
Sage Weil
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...
Sage Weil
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...
Sage Weil
03:43 AM Revision beaca74d (ceph): msg: entity_name_t::parse()
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
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...
Sage Weil
03:43 AM Revision 7f687fca (ceph): osd: handle (and reply to) direct MCommands
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
03:43 AM Revision f868e382 (ceph): osd: remove some pg stats debug cruft
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
03:43 AM Revision b35d96d5 (ceph): mon: feed MPGStats tids back through the MPGStatsAck
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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...
Sage Weil
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 ...
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: ...
Sage Weil
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...
Samuel Just

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 ...
Sage Weil
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.
...
Sage Weil
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.
...
Sage Weil
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...
Sage Weil
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...
Sage Weil
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>
Sage Weil
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: ...
Sage Weil
08:20 PM Revision dd3282c1 (ceph): rgw: multiple swift fixes and cleanups
Yehuda Sadeh
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...
Samuel Just
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...
Samuel Just
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...
Samuel Just
01:35 PM Feature #1604 (Resolved): kclient: handle osdmap discontinuity
Sage Weil
01:00 PM Bug #1449 (Resolved): osd: FAILED assert(0 == "we got a bad state machine event")
b3c68a514135318e0dfda9f929f15f26340cd664 Samuel Just
12:42 PM Bug #1620 (Resolved): rgw suicide due to heartbeat timeout
Happens around a hour after osd went down:... Yehuda Sadeh
10:14 AM Bug #1607 (Resolved): osd: failed assert(missing.is_missing(oe.soid))
a50fbe2b982e5d19040f4ae5795455dde3a9a02e Samuel Just
10:13 AM Bug #1599 (Resolved): osd assert fail (new_tail >= ondisklog.tail)
fccd28df371dceffaf6ff7a50422b6a5b1ee126c should take care of it. Samuel Just
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...
Jojy George Varghese
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...
Jojy George Varghese
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...
Jojy George Varghese

10/13/2011

11:02 PM Revision 87f8389e (ceph): rgw: more swift fixes and adjustments
Yehuda Sadeh
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...
Sage Weil
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...
Sage Weil
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 ...
Greg Farnum
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...
Greg Farnum
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> Greg Farnum
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> Greg Farnum
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> Greg Farnum
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...
Greg Farnum
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 ...
Greg Farnum
04:29 PM Feature #1619 (Resolved): libvirt: test with selinux/apparmour enabled
There are probably checks that assume the image is a file. Josh Durgin
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...
Greg Farnum
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. Josh Durgin
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. Josh Durgin
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:... Josh Durgin
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...
Sage Weil
12:52 PM Bug #1616: crash in is_supported_auth
This happened again in run 493. Josh Durgin
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... Josh Durgin
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 ... Yehuda Sadeh
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. ... Greg Farnum
10:35 AM Linux kernel client Bug #1615 (Can't reproduce): null pointer dereference in ceph_msg_new
This happened during a blogbench run:... Josh Durgin
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... Josh Durgin
09:58 AM rgw Bug #1570 (Resolved): rgw: use tmap for bucket index objects
Pushed to master in commit:45ebaf705d1e37f6b0af84f27767c141496c2f1e
Passes S3 tests.
Greg Farnum
09:58 AM Feature #1569 (Resolved): osd: create a tmap class api
Pushed to master in commit:583e16d9591391c834cd17154571926bffc05abc Greg Farnum

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...
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> Josh Durgin
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.
...
Samuel Just
10:37 PM Revision 493596a7 (ceph): radosgw-admin: test swift keys creation/removal
Yehuda Sadeh
09:46 PM Revision 42bbea89 (ceph): rgw: swift key removal
Yehuda Sadeh
06:14 PM Revision 05dae94f (ceph): Revert "config: base default libdir, sysconfdir off autoconf values"
This reverts commit 7e5dee907a8218647a88d1c7d3316cc277e1c44b. Sage Weil
06:09 PM Revision 1216eb2d (ceph): rgw: some swift api fixes
Yehuda Sadeh
04:34 PM Revision 7e5dee90 (ceph): config: base default libdir, sysconfdir off autoconf values
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
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...
Josh Durgin
12:54 PM Bug #1613 (Resolved): mon crash
Greg Farnum
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...
Hong Cho
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...
Greg Farnum
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 ... Hong Cho
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... Greg Farnum
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. Josh Durgin
09:36 AM Bug #1614 (Resolved): default rados class location needs to be depend on autoconf libdir
Sage Weil
09:20 AM Bug #1614 (Duplicate): default rados class location needs to be depend on autoconf libdir
it's /usr/lib64/... on many platforms. Sage Weil
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...
Sage Weil
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 ...
Greg Farnum
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...
Sage Weil
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...
Alexandre Oliva

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 ...
Hong Cho
10:06 PM Revision e07b956b (ceph): rgw: implement some missing swift api, other swift fixes
Yehuda Sadeh
07:31 PM Revision f883e638 (ceph): rgw: multiple swift keys per user
Yehuda Sadeh
07:31 PM Revision 5790a363 (ceph): rgw: encoded swift key contains full user name
Yehuda Sadeh
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>
Samuel Just
06:16 PM Revision f7ec9f79 (ceph): thread: whitespace
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
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....
Sage Weil
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>
Sage Weil
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 ...
Sage Weil
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... Greg Farnum
05:30 PM Feature #1569 (In Progress): osd: create a tmap class api
Pushed an implementation to wip-tmap. Haven't tested it yet. Greg Farnum
02:01 PM rgw Feature #1591: rgw: instrument with perfcounter
see wip-rgw-perfcounter branch Sage Weil
11:25 AM rgw Feature #1591 (In Progress): rgw: instrument with perfcounter
Sage Weil
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. Sage Weil
01:41 PM Bug #1490 (Resolved): cfuse assert failure: assert(ob->last_commit_tid < tid)
Sage Weil
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. Yehuda Sadeh
12:40 PM Bug #1558 (Resolved): osd crash when deleting pg
Should be fixed in 9b18e55e86a18de6ff91a42984ba9ba35d3bdd4f Samuel Just
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):... Sage Weil
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:... Sage Weil
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> Sage Weil
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> Sage Weil
02:11 AM Revision 3f619ddb (ceph): ceph.spec.in: fix radosgw files
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
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>
Sage Weil

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> Sage Weil
06:51 PM Revision 93a88150 (ceph): radosgw-admin: push log listing into RGWRados
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
06:51 PM Revision 69e9f51d (ceph): rgw: chdir to dir in conf (default /)
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
06:51 PM Revision 930d57f8 (ceph): rgw: push intent log processing into RGWRados layer
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
06:51 PM Revision d7f7a213 (ceph): librbd: don't return >32bit value from copy().
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
06:04 PM Revision 9ec60b4d (ceph): librbd: fix overflow on large large image copy
Fixes: #1611
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil
06:03 PM Revision b6c46158 (ceph): librbd: slightly cleaner
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
05:55 PM Revision 42ac18cd (ceph): .gitignore: test_libhadoopcephfs build
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
05:55 PM Revision 968b0909 (ceph): Merge branch 'master' of github.com:NewDreamNetwork/ceph
Greg Farnum
05:04 PM Bug #1612 (Resolved): osd/PG.cc: 3839: FAILED assert(missing[oid].need <= v)
osd.11 on cephstore6357, full log is available! Sage Weil
04:50 PM Revision 7060efa9 (ceph): librbd: fix copy progress
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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)... Sage Weil
11:06 AM Bug #1611 (Resolved): rbd cp broken?
Sage Weil
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... Sage Weil
10:17 AM Bug #1580 (Resolved): watch expiration
Sage Weil

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> Greg Farnum
08:45 PM rgw Feature #1375 (Rejected): Actually find pool limits
Sage Weil
08:45 PM rgw Feature #1268 (Rejected): rgw: optimistically fetch acl and first chunk
Sage Weil
08:42 PM Bug #1032 (Can't reproduce): osd: Marked down and become zombies after killing
Sage Weil

10/08/2011

09:07 PM Feature #1565 (Resolved): crowbar demo
Sage Weil
11:15 AM CephFS Bug #1435 (Resolved): mds: loss of layout policies upon mds restart
Great news, thanks. We haven't tested it. Sage Weil
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. Alexandre Oliva
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... Alexandre Oliva

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...
Sage Weil
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...
Samuel Just
09:51 PM Revision 321381d7 (ceph): teuthology-worker: remove --keep-locked-on-error
Josh Durgin
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 ...
Josh Durgin
09:37 PM Revision 9d846d33 (ceph): move ceph_mount call
Greg Farnum
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....
Sage Weil
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...
Sage Weil
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>
Josh Durgin
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....
Sage Weil
08:03 PM Revision 2f877f82 (ceph): crushtool: fix --weight arg parsing
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
08:02 PM Revision 8ff1cbb5 (ceph): crushtool: add --force N
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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>
Sage Weil
06:10 PM Revision 5a236942 (ceph): ceph.spec.in: build on suse
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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... Josh Durgin
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>
Sage Weil
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... Sage Weil
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... Josh Durgin
04:32 PM Revision ff31d3cc (ceph): rgw: fix printf format warning
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
03:45 PM Bug #1607 (Resolved): osd: failed assert(missing.is_missing(oe.soid))
While thrashing with bonnie++, this ocurred:... Josh Durgin
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... Josh Durgin
10:56 AM Bug #1454 (Can't reproduce): cosd process dies and remains in defunct state
Sage Weil
10:54 AM CephFS Bug #1437 (Can't reproduce): cfuse can't change permissions of a file
Sage Weil
10:34 AM Bug #1581 (Resolved): teuthology: restarting osds sometimes allows daemon-helper to fail
Josh Durgin
10:20 AM Bug #1403 (Resolved): osd: FAILED assert(0 == "we got a bad state machine event")
Sage Weil
10:20 AM Bug #1449 (Resolved): osd: FAILED assert(0 == "we got a bad state machine event")
Sage Weil
09:38 AM Feature #1606 (Rejected): osd: bound missing set memory usage
Sage Weil
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! Sage Weil
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... Sage Weil
09:33 AM Bug #1602 (Duplicate): mon crash during startup
#1415
Sage Weil
09:05 AM rgw Bug #1592 (Resolved): rgw: remove preallocated pools
This got merged into master and passed s3tests. Greg Farnum
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...
Sage Weil
12:18 AM Revision c56ab974 (ceph): reconnect: ignore SSHExceptions before the timeout expires
Fixes: #1587 Josh Durgin

10/06/2011

11:17 PM Revision 4fe9cca5 (ceph): objecter: cope with missing osdmaps in history
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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 ...
Sage Weil
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:...
Sage Weil
11:17 PM Revision 3d2f89fa (ceph): mon: make other send_incremental variant handle map discontinuity
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
10:59 PM Revision 85bbc2f9 (ceph): .gitignore: add multi_stress_watch
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> Samuel Just
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...
Josh Durgin
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...
Josh Durgin
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> Samuel Just
09:51 PM Revision 6bfae03a (ceph): ReplicatedPG: assert *_FLUSHING unreachable for AccessMode
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> Samuel Just
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>
Samuel Just
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>
Sage Weil
08:39 PM Revision 646ef6aa (ceph): xlist: more assertive
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
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>
Sage Weil
08:24 PM Revision 960deb49 (ceph): Makefile: include ceph_extattr.h to dist tarball
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
08:24 PM Revision b1ea37fc (ceph): Merge remote branch 'stass/wip-freebsdport-rebased2' into wip-freebsd
Sage Weil
08:12 PM Revision 07c88609 (ceph): Revert "osd: simplify the session ref-counting branches"
This reverts commit f002144ef7d314e80d3d19a5cd2c4cef38851056. Sage Weil
07:58 PM Revision fce17617 (ceph): osd: boot with map of oldest-1
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
07:50 PM Revision 4e61e483 (ceph): rgw: keep radosgw in foreground
It defaults to a daemon now. Sage Weil
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> Sage Weil
07:35 PM Revision 77cfbfbb (ceph): radosgw-admin: for date filtering for 'log list'
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
07:35 PM Revision e8dd1f8b (ceph): utime: add gmtime() output function
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
05:32 PM Bug #1587 (Resolved): teuthology: handle SSHException when reconnecting
Implemented in c56ab97442bbf61ad84526580bf773b324a05066 of teuthology.git. Josh Durgin
05:30 PM Revision 6e0a3df8 (ceph): Merge branch 'wip-leaks'
Greg Farnum
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...
Greg Farnum
04:44 PM Revision 5d7e4bd5 (ceph): osd: put session ref in ms_handle_reset
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
04:44 PM Revision f002144e (ceph): osd: simplify the session ref-counting branches
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
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_... Sage Weil
04:33 PM Feature #1604 (Resolved): kclient: handle osdmap discontinuity
Sage Weil
04:20 PM Bug #1449: osd: FAILED assert(0 == "we got a bad state machine event")
This should be fixed with commit:b344d7979b8e0aac931c9f337f367e400a932e36 Josh Durgin
03:52 PM Revision ca3662c8 (ceph): rgw: fix rgw_switch_url_previx printf arg
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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>
Sage Weil
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:... Josh Durgin
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... Josh Durgin
10:11 AM Bug #1534 (Can't reproduce): ceph tool failed assert(mon_addr.count(n))
Sage Weil
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. Sage Weil
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:... Josh Durgin
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...
Sage Weil
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> Sage Weil
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> Sage Weil
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>
Sage Weil
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> Sage Weil

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> Sage Weil
10:16 PM Revision 9d53b3d3 (ceph): osd: fix pg stats encoding for unfound
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
08:48 PM Revision ed878715 (ceph): rgw: fix initscript default user
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
08:37 PM Revision 4ab2a852 (ceph): rgw: daemonize by default
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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...
Sage Weil
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...
Sage Weil
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...
Greg Farnum
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>
Sage Weil
06:13 PM Revision e4a69004 (ceph): osd: fix map epoch check in handle_osd_map
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
05:47 PM Bug #1599: osd assert fail (new_tail >= ondisklog.tail)
Happened in 151 as well. Josh Durgin
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). Josh Durgin
01:42 PM Bug #1599: osd assert fail (new_tail >= ondisklog.tail)
can we reproduce with osd logs on? Sage Weil
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... Josh Durgin
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... Josh Durgin
05:45 PM Revision a76f8d42 (ceph): rgw: fix mis-merge issues.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
04:54 PM Revision 20e0d36a (ceph): Merge branch 'wip-rgw-pools'
Conflicts:
src/rgw/rgw_bucket.cc
src/rgw/rgw_main.cc
Greg Farnum
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...
Greg Farnum
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...
Greg Farnum
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...
Greg Farnum
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...
Greg Farnum
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>
Greg Farnum
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>
Greg Farnum
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...
Greg Farnum
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... Josh Durgin
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:...
Josh Durgin
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/ Josh Durgin
03:36 AM Revision 3bb6ad9d (ceph): Merge branch 'stable'
Sage Weil
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...
Sage Weil
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...
Sage Weil
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>
Stanislav Sedov
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>
Stanislav Sedov
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...
Stanislav Sedov
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...
Stanislav Sedov
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...
Stanislav Sedov
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...
Stanislav Sedov
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>
Stanislav Sedov
12:34 AM Revision 3efa1603 (ceph): Fix endianess detection on FreeBSD.
Signed-off-by: Stanislav Sedov <stas@FreeBSD.org> Stanislav Sedov
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>
Stanislav Sedov
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>
Stanislav Sedov
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...
Stanislav Sedov
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>
Stanislav Sedov
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...
Stanislav Sedov
12:34 AM Revision 0cd3e562 (ceph): Use /bin/sh, which is more portable.
Signed-off-by: Stanislav Sedov <stas@FreeBSD.org> Stanislav Sedov
12:21 AM Revision 107db6a9 (ceph): Retry listing machines if the lock server goes down.
Josh Durgin

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>
Sage Weil
11:08 PM Revision 7cbb68d8 (ceph): Merge branch 'wip-rgw-log'
Sage Weil
11:07 PM Revision 64d2b97d (ceph): osd: remove some dead code
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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> Sage Weil
11:02 PM Revision 3b645fb9 (ceph): common: CINIT_FLAG_NO_BANNER
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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>
Sage Weil
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...
Sage Weil
10:36 PM Revision 37c88295 (ceph): rgw: remove useless RGWConf::log_level
Not used for anything.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil
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...
Sage Weil
09:59 PM Revision 27cf8547 (ceph): rgw: RGW_LOG -> dout
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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...
Sage Weil
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...
Sage Weil
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...
Josh Durgin
09:08 PM Revision f24216a4 (ceph): mon: make MPoolOp*::print() readable
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
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...
Sage Weil
08:46 PM Revision b8f5a35a (ceph): Merge branch 'wip-oldmaps'
Sage Weil
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...
Henry Chang
08:46 PM Revision b2361dc7 (ceph): radosgw: run as 'user' field in ceph.conf
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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...
Sage Weil
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>
Sage Weil
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...
Sage Weil
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...
Sage Weil
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>
Sage Weil
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...
Sage Weil
08:44 PM Revision 6ff57932 (ceph): osdmap: include addrs in json dump
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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...
Sage Weil
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...
Sage Weil
08:44 PM Revision 906e1dad (ceph): osd: add last_epoch_clean to pg_stat_t
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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>
Sage Weil
08:44 PM Revision 2a9330fb (ceph): osd: do not request osdmap when loner if not booted
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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> Sage Weil
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 <...
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@...
Sage Weil
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>
Sage Weil
08:44 PM Revision b8aca4e2 (ceph): radosgw: run as 'user' field in ceph.conf
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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> Sage Weil
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. Josh Durgin
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.
Josh Durgin
05:35 PM Feature #1559 (Resolved): teuthology: continue waiting if the lock server fails
Done in 107db6a913e58201ed51b097881979539723a139. Josh Durgin
04:08 PM rgw Feature #1593 (Resolved): rgw: normalize logging
Sage Weil
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. Sage Weil
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:... Josh Durgin
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...
Sage Weil
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:... Josh Durgin
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...
Sage Weil
01:48 PM Bug #1562 (Resolved): osd: fix osd replacement
Sage Weil
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... Josh Durgin
12:06 PM Bug #1581: teuthology: restarting osds sometimes allows daemon-helper to fail
Looking into this since it's happened again today. Josh Durgin
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... Josh Durgin
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... Greg Farnum
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>
Sage Weil
12:49 AM Revision d305d61b (ceph): ceph_manager: remove unused raw_pg_status method
Josh Durgin
12:49 AM Revision 8e031730 (ceph): ceph_manager: run ceph -s as a normal program
This allows failures from it to be detected better. Josh Durgin
12:11 AM Revision bad609e6 (ceph): teuthology-results: include passed tests in email
Josh Durgin
12:08 AM Revision 8bcd2a74 (ceph): teuthology-results: include reasons for failure in email
Josh Durgin
12:07 AM Revision 817b9504 (ceph): radosbench: get coverage and cores
Josh Durgin
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...
Josh Durgin
12:07 AM Revision 030161ed (ceph): teuthology-ls: show reasons for failures with -v
Josh Durgin

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 ...
Greg Farnum
10:23 PM Revision 3503b34a (ceph): Merge branch 'stable'
Sage Weil
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...
Sage Weil
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...
Greg Farnum
10:02 PM Revision c49c19c1 (ceph): radosgw: fix init-radosgw provides
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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>
Greg Farnum
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...
Greg Farnum
09:31 PM Revision df9c6602 (ceph): rgw: remove preallocating pools maintenance tick
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
09:26 PM Revision fe1a271d (ceph): watch_notify_stress.py: add ceph flags option
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> Samuel Just
09:26 PM Revision 28d60172 (ceph): ceph.py: add btrfs option
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> Samuel Just
08:43 PM CephFS Bug #1472 (Can't reproduce): cfuse hangs with v0.34
Sage Weil
08:42 PM rgw Feature #1542 (Resolved): rgw: combine multiple buckets in a pool
Sage Weil
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...
Henry Chang
08:19 PM Revision 848a1f95 (ceph): debian: add non-stripped exception for libcls_rgw rados class
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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 ...
Brandon Seibel
08:18 PM Revision 2a078f89 (ceph): Makefile: more radosgw_admin -> radosgw-admin
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
07:22 PM Revision a192ee1b (ceph): basic: add rbd cli tests
Josh Durgin
07:20 PM Revision b968ff3a (ceph): workunit: clean up temporary files
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Josh Durgin
06:25 PM Revision 6103ee9e (ceph): more radosgw_admin -> radosgw-admin
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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... Josh Durgin
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...
Sage Weil
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...
Josh Durgin
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)....
Sage Weil
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... Josh Durgin
04:56 PM Revision ae196028 (ceph): nuke: keep up with renaming cfuse -> ceph-fuse
Josh Durgin
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...
Sage Weil
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()...
Sage Weil
04:45 PM Revision a827f040 (ceph): Merge remote branch 'gh/stable'
Sage Weil
04:45 PM Revision b93a0077 (ceph): tasks/radosgw-admin: test radosgw-admin tool
Not yet complete... Sage Weil
04:45 PM Revision 2b601a32 (ceph): radosgw-admin: test additional keys, log list/show/rm
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
04:44 PM Revision afc2dc08 (ceph): nuke: killall apache2 and radosgw too
Sage Weil
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... Sage Weil
02:22 PM Feature #1377 (Resolved): teuthology: use btrfs to back osds
Samuel Just
11:50 AM Bug #1554 (Resolved): rbd rollback does not work with a snapshot of an empty image
Fixed by commit:12ce321b3217b1f3134a7586c1f7d1e6cc384b02 Josh Durgin
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... Sage Weil
10:18 AM Feature #1483 (Resolved): glance: rbd backend
Sage Weil
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... Sage Weil
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... Greg Farnum
10:01 AM rgw Feature #1544 (Resolved): rgw: explicit bucket index
We have a bucket index. Other tickets exist for doing the cleanup, etc. Greg Farnum
09:55 AM CephFS Bug #1589 (Resolved): MDS assert failure
Sage Weil

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>
Alexandre Oliva
03:17 PM rgw Feature #1591 (Resolved): rgw: instrument with perfcounter
things like op counts, bytes, latency from receiving request to sending first byte Sage Weil

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... Alexandre Oliva

09/30/2011

10:48 PM Revision 877cacbb (ceph): v0.36
Sage Weil
09:42 PM Revision f5feda05 (ceph): Merge branch 'wip-pool-sharing'
Sage Weil
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>
Josh Durgin
06:37 PM Revision faeecd81 (ceph): rbd.py: allow setting an image to no snapshot
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Josh Durgin
06:37 PM Revision 1c1785da (ceph): rbd.py: use a dict to translate error codes
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Josh Durgin
06:37 PM Revision 683f4dca (ceph): rbd.py: add class and method documentation
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Josh Durgin
06:37 PM Revision c00e06f6 (ceph): doc: add documentation for librbd python bindings
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Josh Durgin
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...
Greg Farnum
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,...
Greg Farnum
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>
Sage Weil
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 ...
Sage Weil
04:26 PM Revision 9b44469e (ceph): s3-tests: use radosgw-admin instead of radosgw_admin
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
04:26 PM Revision cb425c15 (ceph): s3-tests: use radosgw-admin instead of radosgw_admin
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
04:11 PM Revision b269d3cd (ceph): radosgw-admin: rename clitest dir
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
04:11 PM Revision cb2d3660 (ceph): radosgw-admin: fix acl vs content-length check
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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...
Sage Weil
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: ... Adam Jacob Muller
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:... Josh Durgin
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. Josh Durgin
10:23 AM rgw Feature #1561 (Resolved): rgw: admin command to get stats for a single bucket
Sage Weil
10:23 AM Bug #1523 (Resolved): Erroneous prior_version in log for notify/head
Sage Weil
10:10 AM Bug #1587 (Resolved): teuthology: handle SSHException when reconnecting
It should keep retrying until the timeout expires. Josh Durgin
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... Josh Durgin
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... Josh Durgin
09:26 AM Bug #1524 (Resolved): osd got misdirected messages
Sage Weil
09:25 AM rgw Feature #1582 (Resolved): radosgw-admin: log [list|show|rm]
Sage Weil

09/29/2011

11:48 PM Revision 44d311af (ceph): radosgw-admin: fix help clitest
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
11:47 PM Revision f9792506 (ceph): Merge branch 'wip-pool-sharing' of github.com:NewDreamNetwork/ceph into...
Conflicts:
src/rgw/rgw_bucket.h
Greg Farnum
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...
Sage Weil
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
...
Sage Weil
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 ...
Sage Weil
11:32 PM Revision 560f90c5 (ceph): rgw: fix RGWBucketInfo encoding of owner
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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 <...
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 ...
Greg Farnum
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> Greg Farnum
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...
Samuel Just
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>
Samuel Just
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>
Samuel Just
06:50 PM Revision 2269dc25 (ceph): test_async_snap: loop a finite number of times.
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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>
Sage Weil
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...
Sage Weil
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... Sage Weil
04:18 PM Revision 120736ab (ceph): radosgw-admin: dump ints, not strings
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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>
Sage Weil
04:09 PM Revision 52427589 (ceph): ceph_manager: parse osd numbers with dots
This is necessary since wip-dot-names was merged. Josh Durgin
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...
Greg Farnum
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>
Greg Farnum
03:37 PM Revision e701177b (ceph): radosgw-admin: fix 'bucket stats --uid='
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
03:09 PM Revision 569e7863 (ceph): Forgot to add ceph task to a couple thrashers.
Josh Durgin
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:
...
Alexandre Oliva
12:16 PM Bug #1579 (Resolved): watch notify
Probably fixed in 1eb1ce4d36f369da82b100507fd8f781ac661a2e Samuel Just
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. Brandon Seibel
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:
...
Josh Durgin
04:38 AM Revision 81478414 (ceph): radosgw-admin: include 'suspended' in user info output
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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>
Sage Weil
04:26 AM Revision 0870764c (ceph): radosgw-admin: use formatter for 'bucket list'
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil

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>
Sage Weil
11:09 PM Revision 17603ee8 (ceph): radosgw-admin: use formatter for 'bucket list'
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
11:09 PM Revision 2f78faf1 (ceph): rgw_admin: default to json output
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
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
Sage Weil
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.
...
Sage Weil
11:09 PM Revision 0c75ec05 (ceph): radosgw-admin: clean up 'bucket list' output
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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>
Sage Weil
09:18 PM Revision 1392bbb8 (ceph): rgw: remove now-unused struct RGWPoolInfo
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
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... Alexandre Oliva
08:57 PM Revision 2f1fc5ab (ceph): ceph: make -o - the default
Finally.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil
08:54 PM Revision 7eb15ce2 (ceph): ceph: make --concise hide 'N byte written' message
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
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...
Greg Farnum
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...
Sage Weil
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>
Josh Durgin
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>
Josh Durgin
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> Greg Farnum
04:17 PM rgw Feature #1543 (Resolved): rgw: usage accounting for multiple buckets in a pool
Sage Weil
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=...
Sage Weil
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...
Hannes Reinecke
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... Josh Durgin
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? :) Greg Farnum
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...
Sage Weil
08:47 AM RADOS Feature #1576: Deduplication support in RADOS
Not aware of anything like that, sorry! Greg Farnum
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...
Wilfrid Allembrand
04:47 AM Revision aa20f0d6 (ceph): Merge branch 'wip-dotnames'
Sage Weil
04:46 AM Revision a1521ae8 (ceph): clientN -> client.N
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
04:43 AM Revision 214e7b19 (ceph): monN -> mon.N
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
04:42 AM Revision f5fd7f19 (ceph): mdsN -> mds.N
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
04:34 AM Revision 4b09c1ad (ceph): osdN -> osd.N
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
04:29 AM Revision 594180ad (ceph): msgr: print entity_name_t with a .
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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...
Sage Weil
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>
Sage Weil
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...
Sage Weil
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...
Sage Weil
04:03 AM Revision 532c594c (ceph): osd: some PgPriorSet comments, trivial cleanups, new FIXME
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil

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>
Samuel Just
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> Greg Farnum
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.
...
Samuel Just
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>
Sage Weil
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...
Sage Weil
08:09 PM Revision e63b86d7 (ceph): ceph-authtool: fix -C
Fixes: #1578
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil
08:08 PM Revision 607634f6 (ceph): ceph.spec.in: radosgw init script
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
08:06 PM Revision 3a73606b (ceph): mon: fix error return codes for 'auth ...'
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
08:06 PM Revision b690475c (ceph): mon: auth: implement 'auth print-key <name>'
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
07:41 PM Revision 25ff9fdf (ceph): debian: move ceph and ceph-authtool into ceph-common
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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> Sage Weil
07:34 PM Revision edb2587a (ceph): ceph.spec.in: add rbd python bindings
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Josh Durgin
07:34 PM Revision 951ce29e (ceph): debian: make python-ceph depend on librbd
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Josh Durgin
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>
Josh Durgin
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> Sage Weil
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 ...
Sage Weil
04:37 PM Bug #1580 (Resolved): watch expiration
expiring watches need to be detected and handled Samuel Just
04:36 PM Bug #1579 (Resolved): watch notify
Running test_stress_watch while thrashing osds seems to eventually cause a lost notify Samuel Just
04:15 PM Revision 9e2edce2 (ceph): osdmap: remove dead code
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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
Greg Farnum
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! Greg Farnum
01:41 PM rgw Feature #1532 (Resolved): add radosgw init.d script to radosgw deb
Sage Weil
01:41 PM rgw Feature #1531 (Resolved): radosgw init.d script stop/restart
Sage Weil
01:06 PM Bug #1578 (Resolved): ceph-authtool: -C option does not work
Sage Weil
01:01 PM Bug #1578 (Resolved): ceph-authtool: -C option does not work
Usage says:... Josh Durgin
01:00 PM rgw Bug #1566 (Resolved): rgw: use a global bucket id
Simple enough. commit:c780494d8d5f0f0f3ad372a07227b631879cf2a9 Greg Farnum
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. Josh Durgin
09:50 AM rgw Feature #1560 (Resolved): rgw: admin command to list buckets
Sage Weil
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... Greg Farnum
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...
Wilfrid Allembrand
04:49 AM Revision 9045b3f5 (ceph): Merge branch 'stable'
Sage Weil
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...
Sage Weil
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...
Sage Weil
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...
Josh Durgin
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> Josh Durgin
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>
Josh Durgin
01:10 AM Revision a28eea85 (ceph): rbd.py: remove useless version object
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Josh Durgin
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>
Josh Durgin
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>
Josh Durgin
01:10 AM Revision d71bf04f (ceph): test_rbd.py: Add large read and write tests
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Josh Durgin
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>
Josh Durgin
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> Josh Durgin
01:10 AM Revision 74f07fbd (ceph): librbd: use pre-existing helper methods for tmap operations
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Josh Durgin
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> Josh Durgin
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> Josh Durgin
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> Josh Durgin
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....
Josh Durgin
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...
Josh Durgin
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...
Josh Durgin
01:10 AM Revision c34e87d0 (ceph): rados.py: make Rados and Ioctx objects context managers
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Josh Durgin
01:10 AM Revision c60abe1b (ceph): rbd.py: make Image a context manager
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Josh Durgin
01:10 AM Revision c53d05af (ceph): rados.py: allow configuring rados through constructor options
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Josh Durgin
01:10 AM Revision 69a5e795 (ceph): rados.py: make exceptions inherit from a base class
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Josh Durgin
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>
Josh Durgin

09/26/2011

11:36 PM Revision 56ce7c20 (ceph): mon: fix it again
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
11:25 PM Revision e1eea2b5 (ceph): mon: fix dup pool creation race
Fixes: #1574
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil
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...
Greg Farnum
09:51 PM rgw Bug #1575 (Resolved): rgw: failing s3tests.functional.test_headers:test_object_create_bad_content...
commit:d340e8e742d119658206928ca50238841b147be5 Sage Weil
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... Sage Weil
09:51 PM rgw Bug #1574 (Resolved): rgw: creating multiple metadata pools?
commit:e47c11cf5d7ba15a37768468b7d369568fd41293 Sage Weil
03:18 PM rgw Bug #1574: rgw: creating multiple metadata pools?
ie:... Greg Farnum
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... Greg Farnum
09:25 PM Revision d27d9d89 (ceph): init-ceph: more c* -> ceph-* cleanup
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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>
Sage Weil
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>
Sage Weil
08:30 PM Revision 3b10fd78 (ceph): Makefile: include init-radosgw in tarball
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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 ...
Sage Weil
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> Greg Farnum
08:23 PM Revision 38c6fa5d (ceph): osd: fix warning more
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
08:18 PM Revision bd1625b1 (ceph): Merge remote branch 'origin/master' into wip-pool-sharing
Greg Farnum
08:10 PM Revision b582e7cd (ceph): osd: fix warning
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
06:04 PM Revision 8563b96f (ceph): debian: include radosgw init script in package
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
06:03 PM Revision b19a2006 (ceph): radosgw: init script
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
05:11 PM Revision 10e90abf (ceph): Add some thrashing tasks.
This includes only in-out toggling (default), as well as restarting daemons. Josh Durgin
02:49 PM CephFS Bug #1573 (Duplicate): mds crash during multiple_rsync workunit
... Josh Durgin
01:24 PM rgw Bug #1572 (Resolved): radosgw: don't crash when rgw socket path not specified
Sage Weil
11:41 AM rgw Bug #1572 (Resolved): radosgw: don't crash when rgw socket path not specified
Error out gracefully instead of spewing... Sage Weil
11:31 AM rgw Feature #1544: rgw: explicit bucket index
I've attached our current design doc, such as it is. Greg Farnum
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.) Greg Farnum
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. Greg Farnum
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... Greg Farnum
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... Greg Farnum
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...
Greg Farnum
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 Greg Farnum
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...
Adam Jacob Muller
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... Greg Farnum
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... Greg Farnum
10:31 AM Feature #1498 (Resolved): qa: add osd thrashing tasks
Added in 10e90abf770b61fee4d69c384d0ba47aaf259f2e of ceph-qa-suite.git. Josh Durgin
09:59 AM Feature #1565 (Resolved): crowbar demo
Sage Weil
09:57 AM rgw Bug #1550 (Closed): radosgw fails test_object_create_bad_expect_empty with a 500 response
Sage Weil
09:48 AM Feature #1517 (Resolved): qa: automate node setup after reinstall
Sage Weil
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... Greg Farnum

09/25/2011

08:54 PM Revision 9da0fdf4 (ceph): Merge branch 'stable'
Sage Weil
08:54 PM Revision 30d81fe1 (ceph): filejournal: improve debug error messge
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
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 ...
Sage Weil

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> Sage Weil
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...
Sage Weil
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_...
Sage Weil
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...
Sage Weil
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> Greg Farnum
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...
Sage Weil
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...
Sage Weil
08:49 PM Revision ad38abcf (ceph): - Fix atomic set.
Stanislav Sedov
06:13 AM Revision 67094554 (ceph): rgw: user async exec for index completion op
Yehuda Sadeh
06:13 AM Revision c8bd67b4 (ceph): librados: add async exec
Yehuda Sadeh
05:36 AM Revision 53695134 (ceph): rgw: tmp objects can be removed async
Yehuda Sadeh
04:32 AM Revision 6b9817af (ceph): rgw: fix bucket stats
Yehuda Sadeh
04:21 AM Revision 24176176 (ceph): rgw: fix header encoding
Yehuda Sadeh
12:26 AM Revision 230ec89e (ceph): rgw: fix compilation warning
Yehuda Sadeh
12:22 AM Revision 37f5da43 (ceph): rgw: fix compilation
Yehuda Sadeh
12:19 AM Revision b7ec4d5d (ceph): cls_rgw: substract obj stats only if obj exists
Yehuda Sadeh
12:11 AM Revision ca77ba77 (ceph): rgw: integrate index categories
Yehuda Sadeh

09/23/2011

11:00 PM Revision 623c6916 (ceph): Merge remote branch 'gh/stable'
Sage Weil
10:55 PM Revision cdecf718 (ceph): man: c* -> ceph-* rename: Regenerate manpages.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
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> Tommi Virtanen
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> Tommi Virtanen
10:55 PM Revision c4166492 (ceph): doc: Add index into the sidebar.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
10:55 PM Revision 1ce18d3a (ceph): doc: v0.35 is out, remove rpm build workaround.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
10:55 PM Revision 98b55b30 (ceph): Makefile: c* -> ceph-* rename: missed crun.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
10:55 PM Revision dea14f7e (ceph): rpm: c* -> ceph-* rename: missed crbdnamer, cdebugpack.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
10:55 PM Revision 3fd3c6be (ceph): debian: c* -> ceph-* rename: missed csyn, crbdnamer.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
10:55 PM Revision da8fa783 (ceph): udev: c* -> ceph-* rename: missed crbdnamer.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
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> Tommi Virtanen
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> Tommi Virtanen
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....
Tommi Virtanen
10:55 PM Revision d32592e4 (ceph): .gitignore: distcheck temporary directory.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
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>
Tommi Virtanen
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]: *** [...
Tommi Virtanen
10:55 PM Revision 7f301510 (ceph): doc: Fix reStructuredText formatting warnings.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
10:55 PM Revision 65d2c499 (ceph): doc: Leftovers of the c* -> ceph-* rename.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
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> Tommi Virtanen
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 ...
Greg Farnum
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> Greg Farnum
10:49 PM Revision 29bbcee9 (ceph): rgw: update index when doing put_obj_meta
this fixes multipart upload listing Yehuda Sadeh
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> Greg Farnum
09:42 PM Revision 2ffb04ba (ceph): rgw: fix a few regressions
Yehuda Sadeh
09:38 PM Revision 3b5cb69d (ceph): cls_rgw: list entries return upper_bound of marker
Yehuda Sadeh
09:24 PM Feature #1501 (Resolved): librbd: python bindings
Sage Weil
09:24 PM Feature #1212 (Resolved): teuthology: ability to restart daemons while other tasks are running
Sage Weil
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...
Sage Weil
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...
Henry C Chang
05:04 PM Revision 0fdc8638 (ceph): rename source files c* -> ceph-*
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
05:04 PM Revision dd8d4ecd (ceph): Makefile: drop useless all_sources thing
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
04:42 PM Revision 5369c776 (ceph): misc: use strncpy to prevent buffer overflow
Henry C Chang
04:40 PM Revision 4b8cf145 (ceph): ceph-elaster: add parentheses around macros
Henry C Chang
04:40 PM Revision 17071816 (ceph): test_store: parse args, don't link librados
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
03:57 PM Revision a92fef77 (ceph): rename c* -> ceph-*
Leave cfuse task name unchanged for now... Sage Weil
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 Sage Weil
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. Sage Weil
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 ... Yehuda Sadeh
10:37 AM rgw Feature #1561 (Resolved): rgw: admin command to get stats for a single bucket
Sage Weil
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... Yehuda Sadeh
10:37 AM rgw Feature #1560 (Resolved): rgw: admin command to list buckets
Sage Weil
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... Josh Durgin
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
...
Josh Durgin
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 ...
Sage Weil
06:14 AM Revision 5ede4c87 (ceph): Merge branch 'wip-pool-sharing' of ssh://github.com/NewDreamNetwork/cep...
Yehuda Sadeh
06:14 AM Revision 5f951728 (ceph): rgw: fix clone in case state is NULL
Yehuda Sadeh
05:33 AM Revision e2414330 (ceph): rgw: send correct object id to class op
Yehuda Sadeh
05:30 AM Revision abdb3272 (ceph): rgw: encode correct timestamp
Yehuda Sadeh
04:29 AM Revision 10c5ceef (ceph): rgw: fix rgw_admin arg parsing
Yehuda Sadeh
04:22 AM Revision 00e03327 (ceph): rgw: generate tag if doesn't exist
Yehuda Sadeh
04:11 AM Revision 9441c419 (ceph): crushtool: add unit test for adding items to map
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
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>
Sage Weil
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>
Sage Weil
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...
Sage Weil
01:23 AM Revision c7ff5fc3 (ceph): queue: results_timeout needs to be converted to a string
Josh Durgin
01:08 AM Revision b22fab3c (ceph): Last run of iozone uses 10240M, so increase image size.
Josh Durgin
12:16 AM Revision b873ec8d (ceph): rgw: two phase commit for index updating
Just compiles, not tested, probably wouldn't work. Yehuda Sadeh

09/22/2011

11:20 PM Revision c5523239 (ceph): Merge branch 'stable'
Sage Weil
11:19 PM Revision f9c3cb10 (ceph): Merge branch 'wip-names'
Sage Weil
11:18 PM Revision 3e9a9360 (ceph): doc: more c* -> ceph-* renames
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
11:18 PM Revision bfbda964 (ceph): man: rebuild manpages
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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...
Josh Durgin
10:08 PM Revision 6f8f1403 (ceph): c* -> ceph-*
Hopefully I didn't miss too much...
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil
10:08 PM Revision fba541e4 (ceph): libceph -> libcephfs
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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>
Sage Weil
09:47 PM Revision e124b15b (ceph): addr_parsing: null terminate safe_cat result
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
09:47 PM Revision 17b2451a (ceph): mount.ceph: fix use-after-free
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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> Samuel Just
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> Samuel Just
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> Samuel Just
04:57 PM Revision 5503d450 (ceph): PG: set log.backlog to false on corrupt log
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> Samuel Just
04:56 PM Revision a01a947a (ceph): PG: set log.backlog to false on corrupt log
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> Samuel Just
04:50 PM Revision 0fbf86c2 (ceph): rgw: fix rgw_bucket_dir_entry encoding
Yehuda Sadeh
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 Sage Weil
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 Sage Weil
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 ...
Alexandre Oliva
11:06 AM CephFS Bug #1553 (Duplicate): file locking test 2 fails
Same issue as #1552. Josh Durgin
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 ... Josh Durgin
06:12 AM Revision 6f519f9d (ceph): rgw: list objects (almost completely) works
Yehuda Sadeh
12:27 AM Revision b36b01f1 (ceph): rgw: obj listing doesn't stat object
Yehuda Sadeh
12:14 AM Revision 98d0361d (ceph): rgw: store more info for each indexed object
Yehuda Sadeh

09/21/2011

11:27 PM Revision 82a19351 (ceph): rbd: fix progress redraw
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
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>
Sage Weil
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...
Sage Weil
11:27 PM Revision 8cb57462 (ceph): vstart: debug filestore = 20
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> Sage Weil
11:19 PM Revision ebe6d08c (ceph): cls_rgw: store more info for each entry, stats categories
Yehuda Sadeh
10:20 PM Revision 1c2cc8bc (ceph): rgw: account object removal
Yehuda Sadeh
10:12 PM Revision 8403daf8 (ceph): rgw: account clone_range dest object
Yehuda Sadeh
09:55 PM Revision f488908c (ceph): doc: Content for Getting Started with cephfs and rbd.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
09:17 PM Revision 028ba54f (ceph): rgw: class init_index
Yehuda Sadeh
08:46 PM Revision 9888fc6d (ceph): doc: Split manage into multiple pages.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
08:46 PM Revision d292aee8 (ceph): doc: Move ops/grow under ops/manage.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
08:46 PM Revision 8648b7a5 (ceph): doc: Move recommendations under /rec.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
08:46 PM Revision bc9477af (ceph): doc: Reorganize ops/manage/
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
08:46 PM Revision 093f4f33 (ceph): doc: Split data placement into concrete operations and recommendations.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
08:46 PM Revision c01d36cf (ceph): doc: Move config reference to top-level.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
08:46 PM Revision 47dfe29f (ceph): doc: Separate key management from mounting.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
08:46 PM Revision c3fae7e7 (ceph): doc: Structure for Getting Started.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
08:46 PM Revision 69fabca6 (ceph): doc: Content for Getting Started with RADOS.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
08:46 PM Revision c448c4c0 (ceph): doc: Clean reStructuredText syntax.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
08:46 PM Revision 331510f3 (ceph): doc: Split install into multiple pages.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> Tommi Virtanen
08:37 PM Revision 2c842053 (ceph): Merge branch 'stable'
Sage Weil
08:37 PM Revision aa666b13 (ceph): objclass: add stat operation
Yehuda Sadeh
07:15 PM Revision 2ec5f158 (ceph): cls_rgw: list marker uses lower_bound
Yehuda Sadeh
06:05 PM Revision c3c26265 (ceph): schedule: put results timeout in the job
The default was always being used instead. Josh Durgin
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...
Sage Weil
04:50 PM Revision b9e32fff (ceph): rados: accept '-b' as an argument.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
04:47 PM Revision 2c28e1c7 (ceph): Makefile: include config_opts.h
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
04:47 PM Revision 0afda378 (ceph): v0.35
Sage Weil
04:42 PM Revision fdd3d1da (ceph): Merge branch 'master' of github.com:NewDreamNetwork/ceph
Greg Farnum
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...
Sage Weil
04:35 PM Revision 0852ecfa (ceph): mon: remove unused MonitorStore::sync()
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
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...
Sage Weil
04:35 PM Revision 43967f5e (ceph): auth: keyring: whitespace
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
04:34 PM Feature #1337 (Rejected): osd: support alphanumerically sorted list-objects
Sage Weil
04:30 PM Bug #1526 (Resolved): log bound mismatch after thrashing with bonnie
should be fixed by commit:68fe748fc2d703623050e8f2a448a0fd31ca8a0f Sage Weil
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... Matthew Wodrich
11:28 AM CephFS Bug #1509 (In Progress): cfuse sometimes hangs after unmount
Sage Weil
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... Josh Durgin
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? Greg Farnum
04:34 AM Revision b2fbbf0f (ceph): rgw: implement rgw_rados helpers for class calls
Yehuda Sadeh
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>
Sage Weil
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...
Sage Weil

09/20/2011

11:24 PM Revision c329d00b (ceph): mon: 'osd set pool <foo> crush_ruleset <num>'
You can set the crush rule on pool creation. Let people change existing
pool rulesets too.
Signed-off-by: Sage Weil...
Sage Weil
11:24 PM Revision 096e3b63 (ceph): rbd: error out gracefully when snapname specified for command that does...
Fixes: #1545
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil
10:34 PM Revision 3a8568b3 (ceph): rgw: fix epoch check (greg)
Yehuda Sadeh
10:26 PM Revision f137a046 (ceph): rgw: reuse pools
Yehuda Sadeh
09:39 PM Revision f4d63b03 (ceph): rgw: fix bucket removal (old scheme)
Yehuda Sadeh
09:33 PM Revision b445c6f1 (ceph): rgw: fix object removal
Yehuda Sadeh
09:21 PM Revision fdd98eeb (ceph): rgw: fix bucket listing (still using old scheme)
Yehuda Sadeh
09:20 PM Revision 1c11b200 (ceph): rgw: rgw_admin -- add bucket marker to bucket stats
Yehuda Sadeh
08:43 PM Revision 0b0e8446 (ceph): OSD: return NULL when the OSD does not have the pg in lookup_lock_raw_pg
Previously, we returned NULL if the osd lacked the pool, but not if the
osd had the pool and lacked the pg. In that ...
Samuel Just
08:34 PM Revision 25499b64 (ceph): pool sharing, initial work
Yehuda Sadeh
08:12 PM Revision 4fc1e96d (ceph): rgw: define rgw class api
Yehuda Sadeh
07:52 PM Revision 726a5830 (ceph): rgw: Makefile changes, move around definitions
Yehuda Sadeh
06:56 PM Revision 73bc7713 (ceph): rgw: make cls_rgw compile
Yehuda Sadeh
06:46 PM Revision 0f7a4908 (ceph): ReplicatedPG: populate obc watchers on sub_op_push
Previously, obc->unconnected_watchers did not get filled in during
sub_op_push.
Signed-off-by: Samuel Just <samuel.j...
Samuel Just
05:58 PM Revision a711f293 (ceph): osd: remove throttle_op_queue()
There are subtle annoying problems with throttling and requeueing, and
throttling at this particular point in the sta...
Sage Weil
05:29 PM rgw Feature #1531: radosgw init.d script stop/restart
We need to make the init script somehow know whether radosgw is configured in daemon mode or not. It also needs to k... Sage Weil
05:28 PM Bug #1554 (Resolved): rbd rollback does not work with a snapshot of an empty image
Found this when testing python bindings for librbd. If you
1. create an rbd image
2. create a snapshot
3. write to...
Josh Durgin
05:04 PM Revision e4dfe3d4 (ceph): lockfile: increase interval to prevent incorrect locking orders
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
05:03 PM Revision 5ff88d19 (ceph): lockfile: don't fail cleanup if no lock procs exist
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
05:02 PM Bug #1545 (Resolved): rbd rm crashes when a snapshot is specified
commit:096e3b6353e5035362cffdcbd2e4a4f5572aa2ba Sage Weil
05:02 PM Bug #1546 (Resolved): /var/run/ceph is not present during mkpcehfs: AdminSocketConfigObs::init: f...
commit:56413b8e2e6cbe52972d61976be081d2f2e192d3 Sage Weil
04:31 PM Bug #1547: client log doesn't go to stderr unless 'log file' specified
This works for me with cfuse... need to do --log-to-stderr 2, though. 1 means only emergency stuff, 2 means everythi... Sage Weil
04:01 PM CephFS Bug #1553 (Duplicate): file locking test 2 fails
Logs are in teuthology:~teuthworker/archive/nightly_coverage_2011-09-20/366... Josh Durgin
04:00 PM CephFS Bug #1552 (Duplicate): qa: file locking test fails
Logs are in teuthology:~teuthworker/archive/nightly_coverage_2011-09-20/365... Josh Durgin
03:55 PM rgw Bug #1551 (Won't Fix): radosgw returns 400 instead of 403 on unreadable authorization
From teuthology:~teuthworker/archive/nightly_coverage_2011-09-20/364/teuthology.log:... Josh Durgin
03:46 PM rgw Bug #1550 (Closed): radosgw fails test_object_create_bad_expect_empty with a 500 response
Logs are in teuthology:~teuthworker/archive/nightly_coverage_2011-09-20/364... Josh Durgin
03:40 PM rgw Bug #1522 (Resolved): rgw couldn't read user info
Nope, that fixed it. Josh Durgin
02:40 PM CephFS Bug #1549: mds: zeroed root CDir* vtable in scatter_writebehind_finish
{CDentry,CInode,CDir}::auth_pin() pin the object too, so i'm not sure how we can have a use-after-free in the code th... Sage Weil
01:21 PM CephFS Bug #1549: mds: zeroed root CDir* vtable in scatter_writebehind_finish
Grr, I ran a loop on #1464 for days and wasn't able to hit this. Want to see the mds log to see how we got into this... Sage Weil
01:17 PM CephFS Bug #1549 (Resolved): mds: zeroed root CDir* vtable in scatter_writebehind_finish
Logs are in teuthology:~teuthworker/archive/nightly_coverage_2011-09-20/342/... Josh Durgin
01:43 PM CephFS Bug #1538: mds: all clients can and up becoming unresponsive, mds locker waiting for unfreeze
Narrowed it down to the following scenario:
* At some point earlier on we're imported with a loner
* A client re...
Brandon Seibel
11:07 AM Bug #1508: iozone stuck on kernel rbd mount
this doesn't include commit:935b639a049053d0ccbcf7422f2f9cd221642f58 (kernel), which i hope is responsible for all of... Sage Weil
11:03 AM Bug #1490 (Resolved): cfuse assert failure: assert(ob->last_commit_tid < tid)
should be fixed by commit:a711f2935c0637b1b8ee88e5c7ce8d6e05c29467, which removes throttle_op_queue entirely. Sage Weil
10:41 AM CephFS Bug #1548 (Resolved): metadata inconsistencies and mds crashes
Three issues are covered in this report: empty directories that can't be removed, files that cause the mds to crash w... Alexandre Oliva
05:44 AM Revision 741990cc (ceph): rgw: class for bucket directory
doesn't compile yet Yehuda Sadeh
01:23 AM Revision 46cfda7b (ceph): osd: preserve ordering when throttling races with missing/degraded requeue
When we delay an op because the op_queue is full, we can violate the op
order:
- op1 comes in, waits because object...
Sage Weil

09/19/2011

11:52 PM Revision 4fb3d34a (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...
Sage Weil
09:56 PM Revision 6cce379f (ceph): CInode: don't leak old default_layouts if they get overwritten
This was happening in decode_replica_inode, called by add_replica_inode.
Signed-off-by: Greg Farnum <gregory.farnum@...
Greg Farnum
09:09 PM Revision 0ac89855 (ceph): CDir: put delete with pop so we don't read free'd memory in output
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
09:05 PM Revision 8c8e1d82 (ceph): osd: clear need_up_thru in build_prior as appropriate
The only time need_up_thru is cleared is in the Peering state AdvMap
handler, but it doesn't get called if prior_set_...
Sage Weil
05:45 PM Revision 734e63a7 (ceph): locking: add another test.
I used this to test the correctness of more wait lock behavior. Unfortunately
it doesn't fail on the wrong behavior i...
Greg Farnum
05:44 PM Revision e498caaf (ceph): locking: fix the horribly-botched maxwait values
And generally clean up the timing Greg Farnum
05:40 PM Revision 9cd0b5d2 (ceph): Merge branch 'wip-flock'
Greg Farnum
04:48 PM Revision d440a674 (ceph): flock: clean up waiting records of a lock when adding it succeeds
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
04:47 PM Revision 39970c0f (ceph): flock: add a replay parameter to add_lock
Only insert locks into the waiting lost when NOT replaying
an already-attempted lock.
Signed-off-by: Greg Farnum <gr...
Greg Farnum
04:47 PM Revision d64237a6 (ceph): ceph_common.sh: Do not sudo to root unless needed
Using do_root_cmd() doesn't really need to sudo to root
if you're already root.
Commit 71dc75bdafe62a098c0493ad62f2d...
Tommi Virtanen
04:37 PM Revision ea6986a5 (ceph): flock: move operator<<() to flock header, remove extra line
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
04:20 PM Revision 3e3c0bae (ceph): flock: remove doubled debug output
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> Greg Farnum
03:39 PM Bug #1547 (Resolved): client log doesn't go to stderr unless 'log file' specified
Yehuda Sadeh
02:12 PM Bug #1490: cfuse assert failure: assert(ob->last_commit_tid < tid)
Reproduced with debugging for the osd and cfuse when thrashing with bonnie. Logs are at vit:~joshd/bug_1490 Josh Durgin
11:54 AM Bug #1526: log bound mismatch after thrashing with bonnie
Reproduced this with thrashing and rados bench - logs with full debugging are in vit:~joshd/thrash_bound_mismatch. Josh Durgin
11:03 AM CephFS Bug #1541 (Resolved): flock: a single request can get multiple locks set
Merged this and a couple other fixes to master in commit:9cd0b5d2269227bf96ef543984750b9a6addb929 Greg Farnum
10:51 AM Bug #1508: iozone stuck on kernel rbd mount
ffsb killed the rbd node in teuthology:~teuthworker/archive/nightly_coverage_2011-09-19/323 - probably the same bug. Josh Durgin
10:36 AM Bug #1530: osd crash during build_inc_scrub_map
This happened again, but with blogbench on cfuse. Logs in teuthology:~teuthworker/archive/nightly_coverage_2011-09-19... Josh Durgin
01:30 AM Revision 375b8f76 (ceph): fix .gitignore for test_addrs
Sage Weil
 

Also available in: Atom