Activity
From 04/10/2011 to 05/09/2011
05/09/2011
- 11:01 PM Revision 0ac419e0 (ceph): osd: drop bad warning
- The stats won't match reality if there are any missing or if there are any
snapped objects.
Signed-off-by: Sage Weil... - 11:01 PM Revision 8e1e45c0 (ceph): osd: reset last_complete on mark_all_unfound_as_lost if no more missing
- If we marked _all_ missing as lost, reset last_complete, since missing is
now empty!
Signed-off-by: Sage Weil <sage.... - 11:01 PM Revision 70d8c994 (ceph): osd: simplify build_might_have_unfound
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 11:01 PM Revision 8a781f11 (ceph): osd: fix osd$foo typos
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 11:01 PM Revision 7a6b9b97 (ceph): osd: fix pollution of peer_info
- The ++ postfix has no effect here! We really want +1.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 11:01 PM Revision 7ada5cd6 (ceph): osd: wait for up_thru updates
- Before the primary can go active we need to wait for the up_thru in the
osdmap to reflect that we were alive during t... - 11:01 PM Revision 6d70592d (ceph): osd: log debug output for Crashed state
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 11:01 PM Revision 8cb861c3 (ceph): osd: rename Pending -> WaitActingChange
- We only use the Pending state while waiting for the acting set to change.
Rename the state and log it appropriately s... - 10:18 PM Revision d9ea95f2 (ceph): rados tool: remove import/export
- rados_sync replaces rados import / rados export
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com> - 04:46 PM RADOS Feature #1075 (Resolved): crushtool: warn if uniform item weights vary
- uniform bucket weights are ignored (and presumed uniform, hence "uniform").
- 04:29 PM Bug #1073 (Resolved): osd: failed assert: info.last_complete == info.last_update
- fixed by commit:7ada5cd685fcf3cae4e1c5d2dd81ea1817cceee7
- 09:51 AM Bug #998 (In Progress): qemu/librbd race conditon
- Christian Brunner had a similar error, but in aio_write during a yum upgrade. We should do more testing on this.
- 09:05 AM Bug #1028: segfault in OSDMap::object_locator_to_pg
- This problem is that the locator stored in the object_info_t on disk is wrong. Can you say anything about when the o...
- 05:28 AM rgw Bug #1035 (Resolved): incorrect rgw log data
- This is already fixed, commit:a09eb0c33f6b05714bd4f780f79c70cb4529f840.
05/08/2011
- 11:30 PM Bug #1028: segfault in OSDMap::object_locator_to_pg
- Cherry-picked 85292b367b0e6e6d8963de32ad198482500c887f into the stable branch, here are the logs... I kept the core f...
05/07/2011
- 07:56 PM Revision 1cb611a0 (ceph): .gitignore: rados_sync
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 02:15 PM Bug #1073: osd: failed assert: info.last_complete == info.last_update
- we only wait for up_thru updates if some_down:
if (prior.some_down) {
need_up_thru = true;
for (vect... - 01:51 PM Bug #1073: osd: failed assert: info.last_complete == info.last_update
- this is wrong:
2011-05-06 17:33:48.284200 7f1466b56710 osd4 31 pg[0.12( v 21'17 (21'15,21'17] n=17 ec=2 les=11 31/... - 01:39 PM Bug #1073: osd: failed assert: info.last_complete == info.last_update
- something is definitely going wrong here.. i see
2011-05-06 17:34:24.391722 7fe3aae59710 osd9 43 pg[0.12( v 21'17... - 05:10 AM Revision ea0a1395 (ceph): osd: fix compilation for some g++ versions
- wasn't compiling on lenny, g++ ver 4.3.2. Might be that
it's also due to differebt boost version. - 04:59 AM Revision 25bfb987 (ceph): osd: reassert our assert definition after including boostchart
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 04:59 AM Revision f9ed9885 (ceph): assert: make our assert clobber any others too
- Two can play this game, /usr/include/assert.h!
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 04:42 AM Revision 7db49499 (ceph): rgw: opening bucket io ctx stats bucket info if failed
- this should trigger request of a new osdmap if we were racing
with bucket creation. - 04:42 AM Revision 588fe672 (ceph): rgw: minor cleanup
- 12:43 AM Revision 290668c0 (ceph): Merge branch 'wip-rados-sync'
- 12:42 AM Revision fbe0bd1b (ceph): test_rados_sync: check that second sync does nada
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 12:33 AM Revision 210c38d2 (ceph): rados_sync: more fixes
- * separate BackedUpObject::from_path and BackedUpObject::from_file.
* librados functions return negative values on e...
05/06/2011
- 11:50 PM Revision 85292b36 (ceph): osd: warn when obc locator doesn't match ops
- This will hopefully help us track down #1028.
Signed-off-by: Sage Weil <sage@newdream.net> - 11:41 PM Revision 5a726efc (ceph): rados_sync: fix memory leak, other misc fixes
- * Store BackedUpObject in auto_ptr to avoid memory leaks
* better comment for BackedUpObject::get_fs_path()
* xattr... - 11:26 PM Revision 5f7df9af (ceph): osdmap: refactor mapping; don't assert on missing pool
- We were asserting on a pg with a missing pool fed to pg_to_acting_osds
because raw_to_temp_osds called raw_pg_to_pg. ... - 11:13 PM Revision a61484e6 (ceph): test_rados_sync: test xattr preservation
- test xattr preservation across import/export
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com> - 11:03 PM Revision 6b870bbd (ceph): test_rados_sync: add import/export test
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 11:01 PM Revision b169379c (ceph): rados_sync: complain if import src is inaccessible
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 10:55 PM Revision 010ffced (ceph): rados_sync: fix --create for import
- Fix import's pool creation faculty.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com> - 10:55 PM Revision e3212711 (ceph): add test_rados_sync.sh
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 10:24 PM Revision e00a8244 (ceph): client: map file stripes to acting osds
- Old result was just wrong if any osds were down.
Signed-off-by: Sage Weil <sage@newdream.net> - 10:18 PM Revision f2c94459 (ceph): rados_sync: fix import a bit
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 10:11 PM Revision 8a56a74d (ceph): rados_sync: nicer error formatting
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 10:07 PM Bug #817 (Won't Fix): Implement custom propose logic for OSDMap/PGMap
- 10:07 PM Cleanup #755 (Resolved): Compartmentalize rados.cc
- 10:05 PM Bug #1028 (In Progress): segfault in OSDMap::object_locator_to_pg
- 04:48 PM Bug #1028: segfault in OSDMap::object_locator_to_pg
- added some debug checks in the code to track this one down, commit:85292b367b0e6e6d8963de32ad198482500c887f
- 09:57 PM Revision e9550b57 (ceph): common: be a little less scary in our startup warning
- - be less scary
- be helpful and tell them where to go
Signed-off-by: Sage Weil <sage@newdream.net> - 09:47 PM Revision f98475da (ceph): rados_sync: misc bugfixes
- Avoid using a temporary c_str pointer when it goes out of scope.
Complain if XATTR_FULLNAME is empty, as well as mis... - 09:37 PM Revision 6b6617ef (ceph): rados_sync: nicer printouts
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 09:31 PM Revision a4936a5e (ceph): man: mkcephfs: small fixes
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:28 PM Revision 73facc19 (ceph): rados_sync: do_export: fix diff'ing
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 09:22 PM Revision 6c9698b4 (ceph): rados_sync: more improvements to xattr_test
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 09:21 PM Revision d74ecc26 (ceph): mkcephfs.man: update man page
- Not beautiful, but at least it's accurate.
Signed-off-by: Sage Weil <sage@newdream.net> - 09:13 PM Revision 415db79d (ceph): rados_sync: Add xattr_test
- Add xattr_test to test if the underlying filesystem supports xattrs
Fix BackedUpObject::get_fs_path a bit.
Signed-o... - 08:43 PM Revision fb84e6b2 (ceph): Merge branch 'stable'
- 08:42 PM Revision 48d94f6e (ceph): osd: used fixed size types for fiemap/mapext/sparseread encoding
- The client expects <uint64_t,uint64_t>, so this breaks on any 32-bit osd.
Signed-off-by: Sage Weil <sage@newdream.net> - 08:15 PM Revision 739ab87d (ceph): cfuse: don't -d
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:15 PM Revision f757f134 (ceph): mds: don't journal src when not auth on rename
- If we aren't auth for the srcdn, don't put it in the journal, or else we'll
barf on journal replay.
This fixes a cra... - 08:15 PM Revision 4fbd6c23 (ceph): mds: assert auth on journal_cow_dentry
- We have no business doing cow (or journaling) non-auth dentries.
Signed-off-by: Sage Weil <sage@newdream.net> - 07:25 PM Revision 621af5e3 (ceph): PG: choose_acting needs the value of the osd, not its index
- This caused two osds to keep flipping the acting set between [2] and
[0,2] when osd.0 was far behind and needed a bac... - 07:10 PM Bug #1074 (Resolved): rados_sync: implement --delete
- Implement a --delete flag that will get rid of objects in the dest that aren't in the source.
Should be pretty sim... - 07:06 PM Revision 2315a64e (ceph): Create rados_sync tool to back up rados pools
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:10 PM Revision 0edbc75a (ceph): stop.sh: Avoid bashisms.
- I have a habit of running "sh -x stop.sh" whenever it seems
to fail, and that runs it with dash, not bash. Since it
d... - 06:07 PM Revision 6ee6261c (ceph): stop.sh: Whitespace.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 05:42 PM Bug #1073 (Resolved): osd: failed assert: info.last_complete == info.last_update
- I got this crash on several osds:...
- 04:26 PM Revision 6c366c06 (ceph): osd: fix include in cosd.cc too
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 04:26 PM Revision 88875fba (ceph): osd: rearrange #includes to get our assert
- Make sure we include boostchart headers before our common/assert.h so that
ours clobbers theirs. Otherwise the gener... - 04:10 PM Bug #1072 (Won't Fix): cfuse mount fails when monitors have incorrect time synchronization
- I've run into this a few times, but this time was the most obvious.
client debugging:
2011-05-06 21:40:11.448803 7f... - 03:07 PM Linux kernel client Bug #1071: rbd: mkfs.ext4 doesn't complete (but mke2fs -j does)
- bisected this down to
fatty:ceph-client 03:09 PM $ git bisect bad
77f38e0eeac290827f41fd2215ab82546b8f73b8 is t... - 09:51 AM Linux kernel client Bug #1071 (Resolved): rbd: mkfs.ext4 doesn't complete (but mke2fs -j does)
- root@uml:~# mke2fs /dev/rbd0
mke2fs 1.41.12 (17-May-2010)
Filesystem label=
OS type: Linux
Block size=4096 (log=... - 02:14 PM CephFS Bug #1063 (In Progress): dbench breaks if MDS and client times aren't synced
- Ran this with client debugging enabled (job 573). Not certain this is the problem, but it looks like the problem is t...
- 02:04 PM Bug #1066 (Resolved): update mkcephfs man page
- 01:45 PM rgw Bug #1059: RGW consistency issues
- IIRC we settled on:
- if pool is not in the osdmap, check for the bucket object. if that also doesn't exist, retu... - 12:36 PM rgw Bug #1059: RGW consistency issues
- Other than one test that failed due to misconfiguration, the rest failed due to the async bucket creation. We should ...
- 10:58 AM CephFS Bug #1041 (In Progress): standby-replay fails on multi-mds fsstress journals
- The problem is that the journal (for mds0) refers to mds1's stray directory. It's replaying a rename operation, where...
- 09:40 AM rbd Bug #1070 (Rejected): krbd: ^C doesn't work
- root@uml:~# dd if=/dev/zero of=/dev/rbd0 bs=1M count=100
^C
^C^C^C
100+0 records in
100+0 records out
10... - 04:42 AM CephFS Bug #1047: mds: crash on anchor table query
- I alredy many times create cluster "from scratch", but log still available.
Full mds log from start after previous...
05/05/2011
- 11:36 PM Revision 2ab3062b (ceph): PG: strays don't peer (only the primary does)
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 11:35 PM Revision 76febd2d (ceph): PG: clear peering flag when we transition from Peering to Reset
- This is safe because the only other transitions are to Pending (still
peering) and Active, which clears the state its... - 11:27 PM Revision d6ebf600 (ceph): mon: fix multi-osd 'ceph in|out N..' operations
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 11:24 PM Revision 3ee41ab8 (ceph): ceph_argparse: ignore dashes after equals sign
- When parsing argv, ignore dashes after equals signs. This is so that
things like --log-file=/tmp/foo-file will work c... - 11:17 PM Revision 57bc9b3f (ceph): Merge branch 'wip_pg_refactor'
- 11:17 PM Revision 3b92d408 (ceph): Merge branch 'stable'
- 11:12 PM Revision dc9be200 (ceph): osdmap: fix temp osd pg mapping
- If you feed in a raw pg (full precision) you should get the same mapping
out as when you plug in the effective/reduce... - 10:24 PM Revision 58ea8358 (ceph): Merge branch 'stable'
- Conflicts:
src/mds/Resetter.cc - 10:15 PM Revision 5c520fef (ceph): mon: do not stop mds0 unless all other nodes have also stopped
- If we are the root node or the tableserver, we have to shut down last.
(And even then, if we have client sessions, we... - 09:36 PM Revision 6ac55729 (ceph): PG: handle MOSDPGLog messages in Active state.
- We previously didn't, but we definitely need to as we can go
active while waiting on strays to send in logs to recove... - 09:07 PM Revision 79b1a101 (ceph): ceph_crypto: Fix ceph::crypto::init mutex for NSS.
- Even after ceph::crypto::shutdown, the library looked
already initialized; this broke the ForkDeathTest.MD5
in "make ... - 08:42 PM Revision 44900d4c (ceph): v0.27.1
- 08:38 PM Revision 27a48c1c (ceph): ceph::crypto::init: add PTHREAD_MUTEX_INITIALIZER
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 08:35 PM Revision 7d12d180 (ceph): mds: fix --reset-journal
- Don't fork. (Already fixed in master branch by the start_with_nonce
refactor, so this is just for 0.27.1.)
Signed-o... - 08:27 PM Revision 86064491 (ceph): test-obsync.py: allow better nonce,better printout
- Support deterministic nonces. Better debug printouts.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com> - 08:27 PM Revision 28ccdf42 (ceph): obsync: remove misguided strip_owner
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 08:07 PM Revision 2ca61c92 (ceph): osdmap: small cleanup
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:07 PM Revision 8460cffa (ceph): libceph: initialize keyring after conf is parsed
- Init the keyring in ceph_mount, after the user has a change to load a conf
file or parse command line args.
Signed-o... - 08:07 PM Revision e6dfcfda (ceph): fix some shadowing arguments
- Small subset of what -Wshadow turns up.
Signed-off-by: Sage Weil <sage@newdream.net> - 07:44 PM Revision 921d4b3d (ceph): crypto: fix non-reentrancy of ceph::crypto::init
- This could be called multiple times from common_preinit.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com> - 06:39 PM Revision 429bf1fe (ceph): test-obsync: use s3-tests configuration file
- Use the same configuration file format as s3-tests. This should make it
easier for people to run obsync tests!
Signe... - 06:20 PM Revision b8055b45 (ceph): osd: fix GetInfo down check
- The PgPriorSet::down set can have lots of stuff it in without it affecting
peering completion. We just need to look ... - 05:55 PM Revision db4026d2 (ceph): osd: some comment, debug output cleanup
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:54 PM Revision a284e205 (ceph): osd: reg_last_scrub on pg load
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:22 PM Revision 2b1c61e4 (ceph): obsync: remove omit_owner for acls
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 05:19 PM Revision 6d8ddbc9 (ceph): obsync: Fix ACL parsing yet again
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 05:19 PM Revision b39bb462 (ceph): boto_tool: add getacl, setacl
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 05:19 PM Revision 24f641f8 (ceph): obsync: be more verbose about set_xml_acl errors
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 05:19 PM Revision 8964359c (ceph): obsync: implement --force option
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 05:09 PM Revision 5d77c543 (ceph): osd: GetLog, GetMissing cleanups, fixes
- Added missing continue in GetMissing ctor.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 05:03 PM Revision fe988b11 (ceph): osd: only transition to Pending from GetInfo cons
- No need to do so in get_infos(). The need_up_thru requirement will only
get better as last_epoch_started floor moves... - 04:39 PM Cleanup #1009 (Resolved): osd: push pg message handling code into ReplicatedPG
- 04:38 PM CephFS Bug #1041: standby-replay fails on multi-mds fsstress journals
- I've got a log in kai:~gregf/logs/fsstress/standby-replay
- 04:37 PM Bug #910 (Resolved): Multi-MDS Ceph does not pass fsstress
- Haven't seen any new issues!
- 04:36 PM CephFS Bug #1063: dbench breaks if MDS and client times aren't synced
- I'm unable to reproduce this on my own machine, and after looking through the mds logs from autotest everything looks...
- 02:41 PM CephFS Bug #1063: dbench breaks if MDS and client times aren't synced
- Job 560 has spent 1.5 hours in cleanup now, aborting.
14:40:26 DEBUG| [stdout] 2 19 0.00 MB/sec cle... - 12:55 PM CephFS Bug #1063: dbench breaks if MDS and client times aren't synced
- My bad, the cleanup phase starts at 600 seconds, so kclient only had a few seconds of cleanup.
The cfuse re-run is... - 12:50 PM CephFS Bug #1063: dbench breaks if MDS and client times aren't synced
- Job 555 broke, here's a re-run: http://autotest.ceph.newdream.net/afe/#tab_id=view_job&object_id=556
And that conf... - 09:14 AM CephFS Bug #1063: dbench breaks if MDS and client times aren't synced
- Note that the test I ran was on cfuse (most likely because I had kclient trouble, and wanted to isolate that out).
... - 04:30 PM Revision d2865501 (ceph): osd: consistent naming
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 03:54 PM Revision 04e343c9 (ceph): osd: handle notify+info explicitly in GetInfo state
- This fixes a few things:
- do not proceed past GetInfo if there are down osds. ever.
- if we get a new info that m... - 03:28 PM CephFS Bug #1047: mds: crash on anchor table query
- BTW, if you know what directory the hard link(s) in this directory reference (it'll be the first time the linked file...
- 03:27 PM CephFS Bug #1047: mds: crash on anchor table query
- It's the crash above, I take it?
Can you include a full mds log that ends with an 'ls' and crash?
It sounds lik... - 03:24 PM Bug #1048 (Resolved): MDS never finishes "stopping"
- commit:5c520fefce50c29fbf05a174a37346d8f728c3ef
i suspect if we have no sessions there might be problems, but that... - 03:18 PM Revision ade1fcb7 (ceph): osd: statechart whitespace
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 03:14 PM Revision 565de261 (ceph): osd: initialize pg state event counters
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 03:12 PM Revision c24859f1 (ceph): osd: fix GetInfo querying
- Don't query for info we already have, or have already requested. Remove
unneeded helper so that this is simpler and ... - 03:11 PM Revision 1fbefb32 (ceph): osd: handle event notify/info/log from Initial
- We shouldn't post a creation event and jump into peering/stray based on
pg creation when we are about to process more... - 02:31 PM Feature #1069 (Resolved): rados: support attrs in import/export
- store these as xattrs on the files... user.rados.* i guess!
- 02:30 PM Feature #1068 (Resolved): rados: incremental import/export
- Skip objects when size/mtime and attrs match on source and destination. Or sync always. (Make it an option.)
We ... - 02:01 PM Bug #1058 (Resolved): pg_refactor: OSD crash when marking several out
- Haven't seen a recurrence of this.
- 02:01 PM Bug #1062 (Resolved): pg_refactor: active primary is getting MPGLog
- Fixed my bug with commit:6ac5572946337e8e74b5014fc299e0ee10c70d9f and I think Sage already got his, too.
- 01:35 PM CephFS Bug #1064: all mds's dies one by one after restart
- 01:22 PM CephFS Bug #1064: all mds's dies one by one after restart
- Hi Sergey,
Can you attach the full mds log for journal replay? (probably need to gzip, it'll be big!)
Also, ca... - 03:52 AM CephFS Bug #1064 (Can't reproduce): all mds's dies one by one after restart
- At first all cfuse client hungs while trying access files on mounted ceph. I restart all nodes with ceph -a stop && c...
- 01:18 PM CephFS Bug #1065 (Resolved): mds: can't authenticate with --reset-journal
- commit:7d12d1807fde72d6d87c732a0bda6b33bb4d8f7c
- 09:38 AM CephFS Bug #1065 (Resolved): mds: can't authenticate with --reset-journal
- 08:54:46 AM) Tsipa: trollface: when i'm running cmds -i 0 -c /etc/ceph/ceph.conf --reset-journal 0 i get messages lik...
- 01:16 PM Feature #1067 (Resolved): mkcephfs: magically group osds on same host into subtrees in the genera...
- In theory we can look at the host field in the ceph.conf to generate a sane crushmap by default. As things stand, an...
- 11:11 AM Bug #1066 (Resolved): update mkcephfs man page
- 10:36 AM rgw Bug #1059: RGW consistency issues
- Here is my run of s3-tests. Looks like these tests failed:
test_s3.test_bucket_list_empty
test_s3.test_bucket_cre... - 10:22 AM Bug #1057 (Resolved): obsync: implement --force
- implemented by commit:8964359c9d0a56e72b64c81a2ceda1ec3c29c5be
- 12:25 AM Revision d6347392 (ceph): rgw: don't output optional DisplayName if not set
- Don't output optional DisplayName if not set. Be a little more explicit
about zeroing other optional fields during xm...
05/04/2011
- 11:44 PM Revision b5cb4c5e (ceph): osd: debug handle_*
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 11:19 PM Revision a544bda7 (ceph): rgw: don't assume XML is valid
- XML parsing functions in RGW now return a bool, indicating whether they
were able to get the fields they needed to ou... - 11:17 PM Revision 4d10126b (ceph): OSD: fill in rctx properly for pg->handle_create in get_or_create_pg
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 11:10 PM Revision 4d661999 (ceph): osd: rename states to reflect nesting; fix enter/exit msgs
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 11:10 PM Revision 9ebcd365 (ceph): osd: fix min_time in state stats
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 09:58 PM Revision d2c245c4 (ceph): osd: first pass at pg peering stats
- The numbers are a bit off it seems. Also lots of potential for cleanup
here. But it (basically) works!
Signed-off-... - 09:36 PM CephFS Bug #1063: dbench breaks if MDS and client times aren't synced
- this is probably a kclient thing.. testing against latest for-linus
- 04:56 PM CephFS Bug #1063 (Can't reproduce): dbench breaks if MDS and client times aren't synced
- http://autotest.ceph.newdream.net/afe/#tab_id=view_job&object_id=554
one mds, one osd, cfuse
dbench never compl... - 09:30 PM Revision 228e857e (ceph): OSD: assert contents exist when erasing from last_scrub_map.
- Insert PG into last_scrub_map on creation so that this doesn't
break right away.
Signed-off-by: Greg Farnum <gregory... - 09:12 PM Revision a347d180 (ceph): osd: use const char * state names
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 08:52 PM Revision ca7a3724 (ceph): PG: proc_replica_info, oinfo not info
- The method param info shadowed PG::info.
- 08:05 PM Revision db8f96c9 (ceph): osd: move directly to Reset state on pg load
- Add Initial -> Reset transition on pg load. This avoids doing any
activation-type stuff (like sending messages) befo... - 07:23 PM Revision d622a6fb (ceph): OSD: start PG state machine when loading pre-existing PGs
- This caused a crash when restarting a killed OSD because the Initial
state was receiving the ActMap event.
Signed-of... - 07:03 PM rgw Bug #1059: RGW consistency issues
- Can you specify which tests are failing? I haven't seen this happening, but I was probably running it against a diffe...
- 04:40 PM rgw Bug #1059: RGW consistency issues
- I think this issue is causing a lot of the s3-tests failures I'm seeing.
- 03:27 PM rgw Bug #1059 (Resolved): RGW consistency issues
- RGW is supposed to implement read-after-write consistency, but it often does not....
- 06:36 PM Revision c3fe4e3d (ceph): PG: ReplicaActive must repond to requests from discover_all_missing
- If the peer does not yet have the pg during GetMissing, there won't be
a peer_missing entry for that peer. In that c... - 05:50 PM Revision c9859c2f (ceph): uclient: only try to update caps on the auth MDS.
- Previously we would send updates on things like the max_size we
wanted to the first MDS in our list, which was bad if... - 05:50 PM Revision d417fb0b (ceph): uclient: fill in InodeCap::wanted member on send_cap.
- Previously it was never used, which I think led to spamming the MDS
with cap messages!
Hopefully this won't reveal a... - 05:30 PM Bug #1053: rgw XML parsing exploits and flaws
- that should read:
commit:a544bda7577321c4d6ecf7664a9363180984da56 and commit:d6347392634678b93f510f98d3d42407d05a956c - 05:29 PM Bug #1053 (Resolved): rgw XML parsing exploits and flaws
- I was afraid that there were more mistakes like #1055 in the code, but it looks like the other XML parsing stuff isn'...
- 10:49 AM Bug #1053 (Resolved): rgw XML parsing exploits and flaws
- RGW must never segfault on bad network input. It should handle optional XML fields.
- 05:28 PM Revision 9c192e58 (ceph): PG: collapse crashed transitions to happen on any unexpected event
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 05:27 PM Revision 8d301d29 (ceph): PG: use a state_name member instead of overriding get_state_name
- Also add debugging to each state constructor. Since dout uses
the recovery machine context, anything using it in the ... - 04:57 PM Tasks #1055 (Resolved): RGW segfaults if the Owner field is not set in an ACL (subtask)
- fixed by a544bda7577321c4d6ecf7664a9363180984da56
- 10:53 AM Tasks #1055 (Resolved): RGW segfaults if the Owner field is not set in an ACL (subtask)
- The following code explains the situation quite well, I think:...
- 04:52 PM Bug #1062: pg_refactor: active primary is getting MPGLog
- I have a slightly different crash, but i think it's the same problem. see this:...
- 04:17 PM Bug #1062 (Resolved): pg_refactor: active primary is getting MPGLog
- Logs are in kai:~gregf/logs/pg_refactor/active_gets_pglog
Same steps to reproduce as #1058.
Causes a crash in t... - 04:17 PM Bug #1058: pg_refactor: OSD crash when marking several out
- So the problem is that OSD::get_or_create_pg calls pg->handle_create using an rctx that is empty except for an empty ...
- 02:09 PM Bug #1058 (Resolved): pg_refactor: OSD crash when marking several out
- To reproduce:
1) Start up with 4 OSDs (using vstart)
2) mark two of the OSDs out
3) Wait a bit
4) Notice that the... - 11:48 AM Bug #1057 (Resolved): obsync: implement --force
- Implement --force, which causes all copies to happen, even if the source and destination appear to be in sync.
- 11:46 AM Bug #1056 (Won't Fix): obsync: add warning when source owner is not the same as dest owner (after...
- when -v is used, we should spit out a little message when we change the Owner during a source->dest copy
- 10:54 AM Bug #1054 (Duplicate): RGW segfaults if the Owner field is not set in an ACL
- re-created this as a subtask of 1053 (which I always wanted it to be)
Apparently you can't subtask-ize things afte... - 10:51 AM Bug #1054 (Duplicate): RGW segfaults if the Owner field is not set in an ACL
- The following code explains the situation quite well, I think:...
- 10:16 AM CephFS Tasks #1039 (Resolved): cfuse: requests max_size from non-auth MDS
- Looks good. Pushed to master in commit:c9859c2fc8005566ad6159a3d66e2ba10f82a986.
- 05:48 AM Bug #1018: error on building ceph on red hat 5.5
- I have had the same problem using 0,27 version.
The problem seems to be in libedit.
i have user libedit from RPMfor... - 12:58 AM Revision 879d6b03 (ceph): Revert "osd: simplify check for unconsumed events"
- This reverts commit ab34a3ce3e757a54816bd9b884c3f900361d4930.
It turns out that unconsumed_event supersedes checking... - 12:19 AM Revision 31f6a8cf (ceph): PG: Primary should also discard the ActMap event
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 12:03 AM Revision ab34a3ce (ceph): osd: simplify check for unconsumed events
- No need for the Crashed pseudo state.
Signed-off-by: Sage Weil <sage@newdream.net> - 12:02 AM Revision dda3261e (ceph): PG: ActMap should be dicarded if no outer state handles it
05/03/2011
- 11:38 PM Revision efcab968 (ceph): osd: fix event names
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:38 PM Revision 71abe265 (ceph): osd: make debug output include state name
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:28 PM Revision 28fdffcc (ceph): PG.h: transition to crashed on unhandled message
- 11:13 PM Revision fdc67915 (ceph): obsync: improve ACL handling again
- LocalAcl: store ACLs in memory. They're very small, and the tempfile
stuff was just getting cumbersome.
LocalAcl.equ... - 10:52 PM Bug #1040: obsync: preserve content-type, misc metadata
- note to self: The "miscellaneous metadata" is found in the X-amz-meta headers.
- 10:51 PM Bug #1052 (Resolved): obsync: add rados backend tests to test-obsync.py
- I need to add tests for the rados backend to the test-obsync.py script.
- 10:50 PM Bug #1051 (Resolved): obsync: create a librgw to parse binary ACLs generated by RGW
- obsync: create a librgw to parse binary ACLs generated by RGW
This is already partially done in the wip-obsync-rad... - 10:46 PM Bug #1050 (Won't Fix): obsync: implement --filter to allow certain objects in the source to be sk...
- 10:33 PM Revision 0802cfde (ceph): obsync: fix some bugs
- * Allow parsing of AclPolicy elements that don't have owner_id fields.
* Put all XML attributes in the correct names... - 10:31 PM Revision c71583d0 (ceph): osd: feed new pg mapping into state machine
- instead of recalculating it. Also pass the last map into warm_restart,
while we're at it. Drop the Reset state cons... - 10:29 PM Revision d0dd5497 (ceph): osdmap: fix some constedness
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:38 PM Revision 39dc0846 (ceph): osd: turn off recovery oid sets
- This is slow, eats memory, and dumps huge amounts of crap to the debug
logs when enabled. Leave it off unless we are... - 09:37 PM CephFS Bug #594 (Resolved): mds: frag split/merge vs replay
- closing this out. the bugs i'm hitting now are rstat related or general issues not specific to frags and resolve/rej...
- 09:28 PM Revision 1a204a60 (ceph): Merge branch 'master' into wip_pg_refactor
- 09:27 PM Revision b659fd02 (ceph): osd: only specify start version for Qeury::LOG
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:26 PM Revision 892e58d0 (ceph): PG: handle info in proc_replica_log just like we did in _process_pg_info
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 09:26 PM Revision c96f3e9b (ceph): PG: fix proc_master_log output
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 09:26 PM Revision 9c70fdfb (ceph): PG: send notifies when a stray or an active replica gets an ActMap
- This was present before refactoring.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> - 09:26 PM Revision 258fe7c0 (ceph): PG: don't become clean in purge_strays
- Our state is already clean here.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> - 09:26 PM Revision eac23e17 (ceph): PG: remove peer_info_requested member
- This is internal to the GetInfo state now.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> - 09:23 PM Revision f175d27a (ceph): obsync: check if ACLs match
- If all other aspects of two objects match, we should make sure the ACLs
match before deciding that there's nothing fo... - 09:06 PM Revision 780ec44b (ceph): osd: use enum instead of const static int members
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:06 PM Revision a5f352cc (ceph): osd: leave recovery hooks in PG
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:08 PM Revision 90ee7cf9 (ceph): osd: fix pg log entry types to not always be delete
- This was broken by the osd_trans work merged in 01f3526b62. We need to
use the obs reference to new_obs. This cause... - 07:37 PM Revision 85131220 (ceph): mon: add 'ceph osd rm N...' command
- So we can mark an old osd as deleted and have it not appear in the osdmap
dump, summary count.
Signed-off-by: Sage W... - 07:36 PM Revision c0c20299 (ceph): Merge remote branch 'origin/stable'
- Conflicts:
src/mon/OSDMonitor.cc - 07:34 PM Revision f680eca7 (ceph): osdmap: allow incremental to represent osd deletion
- Convert new_down to new_state, with values xored onto the old state. We
preserve compatibility with old incrementals... - 07:28 PM Revision 890dc2ae (ceph): objecter: remove useless mark_down code
- We already check sessions a bit further down, and this code only worked
when we got incrementals, not full maps. Tak... - 06:07 PM Revision f39f5c81 (ceph): test-obsync: test ACL translation, run unit tests
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 05:58 PM Revision 472d7bee (ceph): obsync: remove --owner, elide owner from ACL XML
- Just omit the owner field from the ACL XML. It is optional anyway.
Don't supply an --owner switch. The owner will al... - 05:20 PM Revision a6383e94 (ceph): obsync: better usage
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 05:19 PM Revision 789b9672 (ceph): OSD.cc: handle_pg_create fix initial last_epoch_started value
- last_epoch_started == same_acting_since should not be true before the pg
goes active for the first time. - 05:19 PM Revision fe30d90a (ceph): TestSnaps.cc: default to testing with the data pool
- 05:19 PM Revision 1b0dfcf5 (ceph): PG: Add gen_prefix method for generating the pg error prefix
- This should make it easier to add dout macros for non-pg methods
- 05:19 PM Revision 1477c068 (ceph): PG: Refactor build_prior into a PgPriorSet constructor.
- 05:19 PM Revision 21d8e72a (ceph): PG: Extract query map generation from recover_master_log
- PgPriorSet::gen_query_map now generates the initial info query map.
- 05:19 PM Revision f06269de (ceph): PG: choose_log_location
- Choosing the master log holder and deciding whether to generate a
backlog are now handled by choose_log_location. - 05:19 PM Revision 09f6d22d (ceph): OSD,PG: Move pg reset code from OSD::advance_map to PG
- OSD::advance_map previously handled resetting the PG for peering. Now,
PG::acting_up_affected returns true if peerin... - 05:19 PM Revision 48eb343b (ceph): OSD,PG: Peering refactor
- Previously, peering was handled by a defacto state machine in do_peer
and related methods. Peering state will now be... - 05:06 PM Revision a8a16c71 (ceph): obsync: only require --owner if --xuser is set
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 02:25 PM Bug #1049 (Resolved): obsync: synchronize ACLs
- resolved by commit:f175d27a48b8bfdf83aeebd589211677b5db4073
- 02:14 PM Bug #1049 (Resolved): obsync: synchronize ACLs
- If ACLs differ between the source and destination buckets, we should make sure they're synchronized.
- 12:52 PM Bug #1045 (Resolved): master doesn't pass testsnaps while changing replication
- This should be fixed by commit:90ee7cf91157413f8c6bff341d258772fef6ab9a
- 11:09 AM Bug #1038 (Resolved): obsync: support --xuser
- Added to test-obsync.py
- 10:59 AM CephFS Tasks #1039: cfuse: requests max_size from non-auth MDS
- Testing out a fix now based on only updating max_size on the auth_cap but it'll take a few runs to verify and I want ...
- 09:54 AM CephFS Tasks #1039: cfuse: requests max_size from non-auth MDS
- So the replica mds0 caps are examined before the auth mds1 caps are, and then the client requests a new max_size from...
- 09:47 AM CephFS Tasks #1039: cfuse: requests max_size from non-auth MDS
- Okay, the replica MDS is behaving appropriately -- it's issuing only shared caps. It looks like the problem is that f...
- 08:51 AM CephFS Tasks #1039 (In Progress): cfuse: requests max_size from non-auth MDS
- 10:51 AM Bug #1048 (Resolved): MDS never finishes "stopping"
- Running "ceph mds stop foo" tells the MDS to stop, but it doesn't seem to be able to finish stopping.
This is on a... - 10:45 AM Linux kernel client Bug #970: Kernel crash (cause?: lots of small files)
- Make that ca20892db7567c40e8ed0668f46cf0d085d7db6d in for-linus instead.
- 09:15 AM Linux kernel client Bug #970 (Resolved): Kernel crash (cause?: lots of small files)
- Fixed in ceph-client.git master...
- 05:12 AM CephFS Bug #1047: mds: crash on anchor table query
- Now I have a directory 'ls' in which make crash mds.
- 04:48 AM CephFS Bug #1047 (Resolved): mds: crash on anchor table query
- Attempt delete directory with backup created by BackupPC.
2011-05-03 14:12:37.288166 7fcc61d6f700 mds0.cache.dir(1... - 01:41 AM Revision 441b54c1 (ceph): obsync: implement --owner
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 01:23 AM Revision 5ac87ffd (ceph): cfuse: encode/decode dev_t properly
- The fuse layer passes through "encoded" dev_t values (probably for
compatibility reasons or something). I copied the...
05/02/2011
- 11:54 PM Revision 8bd2305d (ceph): obsync: implement user translation (--xuser)
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 10:57 PM Revision fa2da0c5 (ceph): rgw: fix ACL XML generation
- Put AccessControlPolicy in the http://s3.amazonaws.com/doc/2006-03-01/
namespace.
Signed-off-by: Colin McCabe <colin... - 09:47 PM Revision 931b5804 (ceph): obsync: refactor LocalCopy
- Combine LocalCopy, S3StoreLocalCopy, and RadosStoreLocalCopy into one
class called LocalCopy.
Signed-off-by: Colin M... - 08:47 PM Revision 1701804d (ceph): FileStore: use proper object names for linking
- They were backward before, which broke EVERYTHING.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 08:16 PM Revision ac23196b (ceph): MDS: fix handle_client_rename use of path_traverse.
- It was using the MDS_TRAVERSE_DISCOVERXLOCK flag, which allows
path_traverse to return success if it encounters a NUL... - 06:18 PM Bug #1046 (Resolved): rgw: changing object owners
- We need to find out whether Amazon allows the object Owner to be changed by a setacl operation.
Actually, it break... - 06:16 PM Bug #1013 (Can't reproduce): filejournal buffer::rebuild crash
- 06:15 PM Bug #996 (Can't reproduce): osd: ReplicatedPG::do_osd_ops
- 06:10 PM CephFS Bug #1031 (Resolved): dev node inconsistency between cfuse and kernel client
- fixed by commit:5ac87ffd36c7a3561266d198726eefc9f6a11036
- 04:57 PM Bug #1038: obsync: support --xuser
- implemented by 8bd2305d1c244fc472693aa66ec2164c07612bcb.
Need to write some tests for test-obsync.py - 10:24 AM Bug #1038 (Resolved): obsync: support --xuser
- We need to support username translation. The users that exist on Amazon S3, RackSpace, or any other S3-compatible sto...
- 04:49 PM CephFS Bug #1022 (Can't reproduce): every mds crash: Program terminated with signal 11, Segmentation fault.
- I think the trail is cold on this one. Let's keep an eye out for this in case it comes up again.
- 03:53 PM Bug #1045 (Resolved): master doesn't pass testsnaps while changing replication
- To reproduce:
1) start up cluster (I used 4 OSDs, 1 mon/mds)
2) start testsnaps
3) change pool replication (I set ... - 03:23 PM Feature #1044 (Resolved): librbd: discard support
- 02:52 PM Bug #1037 (Rejected): obsync: handle LFN for rados://
- 01:12 PM Bug #1037: obsync: handle LFN for rados://
- Right. I checked rgw, worked with the max bucket names and object names sizes allowed by the API. We should probably ...
- 12:57 PM Bug #1037: obsync: handle LFN for rados://
- I don't think obsync has to do anything special; rados will now handle object names up to 4k (or whatever). The hash...
- 10:22 AM Bug #1037 (Rejected): obsync: handle LFN for rados://
- However RADOS ends up doing LFN, we need to be able to do that, in order to support the rados:// backend.
Based on... - 02:09 PM Bug #1043 (Resolved): Filestore is broken on object pushes
- Got Yehuda to take a look at this, then pushed a patch that seems to fix it!
- 12:39 PM Bug #1043 (Resolved): Filestore is broken on object pushes
- This is probably a bug with transaction handling rather than pushes specifically.
Steps to reproduce:
1) Start a cl... - 12:04 PM Cleanup #1042 (Resolved): need const iterator for bufferlist
- There should be a bufferlist::const_iterator to match bufferlist::iterator.
The fact that we don't have this makes... - 10:26 AM CephFS Bug #1041 (Resolved): standby-replay fails on multi-mds fsstress journals
- Things break, figure out why.
- 10:25 AM Bug #1040 (Resolved): obsync: preserve content-type, misc metadata
- We should preserve the Content-Type of the object we got out of S3. We should preserve the miscellaneous metadata. (B...
- 10:25 AM CephFS Tasks #1039 (Resolved): cfuse: requests max_size from non-auth MDS
- See kai:/home/gregf/logs/fsstress/cfuse_caps
The export of caps seems to go well, and the client drops them, but t... - 10:21 AM Bug #1036 (Won't Fix): obsync: handle LFN for file://
- obsync needs to have a way to store long object names when given a file:// source or destination.
Otherwise, it's ... - 10:16 AM Linux kernel client Bug #970: Kernel crash (cause?: lots of small files)
- The same.
[ 1877.996453] libceph: msg_new can't allocate 512 bytes
[ 1877.996607] libceph: msg_new can't create t...
04/30/2011
- 12:46 AM Revision 7d19f184 (ceph): mds: trim non-auth swallowed subtrees during resolve
- Consider:
- peer auth for /foo
- ambiguous import /foo/bar
- peer claims /foo, swallows /foo/bar.
- disambiguate_... - 12:46 AM Revision 9e4e3452 (ceph): mds: fix replay of EFragment rollback
- Remove from the uncommitted list.
Also, make uncommitted list updated unconditional: we need to do it even
if the in... - 12:17 AM Revision a09eb0c3 (ceph): rgw: log bytes received
04/29/2011
- 11:15 PM Revision 03d82a3f (ceph): rgw_admin: dump also user email
- 11:15 PM Revision 6a160190 (ceph): rgw: fix some logging problems
- 09:48 PM Revision e97ce8ec (ceph): test/ceph_crypto: Check that the shutdown/fork/init trick works for NSS.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 09:10 PM Revision fc36eb6b (ceph): filestore: fiemap should close the fd
- 09:09 PM Revision e4cdc583 (ceph): filestore: fiemap should close the fd
- 08:19 PM Revision 264829b5 (ceph): common, cfuse: Hook into daemonization and shutdown/init NSS.
- NSS cannot tolerate forks without this.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> - 08:17 PM Revision 98b08771 (ceph): msgr, common: Refactor to extract daemonization out of messenger.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 08:08 PM Revision 0e6bacc6 (ceph): msgr: Rename SimpleMessenger::start(daemonize, nonce) to start_with_nonce.
- Otherwise, once we remove daemonize from the prototype,
all the existing ->start(false) calls will be taken
to mean n... - 08:08 PM Revision 84454c24 (ceph): ceph_crypto: Assert that NSS initialization works.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 06:29 PM Revision 4107e296 (ceph): common_init: create common_init_daemonize
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 05:39 PM Revision 2d82fefc (ceph): config: Update sample config with more examples
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Signed-off-by: Wido den Hollander <wido@widodh.nl> - 05:23 PM Revision 2047b59d (ceph): common_init: set log_file, not log_dir, by default
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 05:21 PM Revision 689a1bdd (ceph): common_init: don't modify log_per_instance
- check it in DoutStreambuf instead.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com> - 04:49 PM Revision 0a2d3f25 (ceph): msgr: remove dup .start() call check, remove cruft
- There is now no ordering constraint wrt the daemonize bits; those can
safely be pulled out.
Signed-off-by: Sage Weil... - 03:43 PM Revision e0ec4138 (ceph): hadoop: cleanups for libceph type update
- Signed-off-by: Jim Schutt <jaschut@sandia.gov>
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 03:28 PM rgw Bug #1035 (Resolved): incorrect rgw log data
- bad data in the following fields:
- HTTP status
- Object size
- Data sent
Need also to verify that there are... - 10:59 AM rgw Bug #1025 (Resolved): s3-tests should test S3 object extended attributes ("developer-added metada...
- a test that checks creation of custom metadata has been added at commit:5861b129bc6097cb5e758f58c39ff4d0d8a69fa7.
- 07:22 AM Linux kernel client Bug #970: Kernel crash (cause?: lots of small files)
- ...
- 05:44 AM Bug #1034 (Resolved): librados: Calling connect twice causes a segfault
- While working on phprados I called rados.connect() twice by accident, this resulted in:...
- 02:31 AM Bug #1033 (Resolved): osd: CephxClientHandler::handle_response
- On one of my OSD's I noticed the following crash:...
- 01:08 AM Bug #1032 (Can't reproduce): osd: Marked down and become zombies after killing
- I've discussed this a bit with Tv on IRC, but it's still unclear to me what is really happening.
At first I saw OS...
04/28/2011
- 11:01 PM Revision c9712e4f (ceph): lfn: put lfn outside of user.ceph namesapce
- This completely hides the lfn from the ObjectStore interface users.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 10:55 PM Revision 3a146f07 (ceph): mdsmap: show mds name in summary
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:52 PM Revision f4687421 (ceph): hadoop: update libceph types
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:52 PM Revision 347bc9f2 (ceph): hypertable: update libceph types
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:49 PM Revision 101506aa (ceph): libceph: error out if USE_FILE_OFFSET64 not defined
- Otherwise struct dirent will not match user code and badness on readdir
will ensure.
Signed-off-by: Sage Weil <sage@... - 10:45 PM Revision 6e727a9b (ceph): Merge remote branch 'origin/master' into lfn
- 10:44 PM Revision 95cea34e (ceph): lfn: don't return ENOENT if it's not lfn in some cases
- 10:17 PM Revision e9fac67f (ceph): mds: ignore fragment_notify when dft state doesn't match
- In particular, if there is a resolve in there somewhere, we may have found
out about this refragment from the src bec... - 10:02 PM Revision 1c58f806 (ceph): mds: do not send fragment_notify to <= recovering nodes
- They will get sorted out during rejoin.
Signed-off-by: Sage Weil <sage@newdream.net> - 09:57 PM Revision 26145838 (ceph): client: do not send request to mds -1
- If we can't find a target, or the chosen target isn't active, wait.
Signed-off-by: Sage Weil <sage@newdream.net> - 09:57 PM Revision 4f39fae0 (ceph): mds: handle import cancel while logging EImportStart
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:57 PM Revision 27ca30dc (ceph): mds: fix uninint warning on cur
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:57 PM Revision aee20973 (ceph): lfn: set hash and file name constants
- 08:51 PM Revision 9b3c3aaf (ceph): osd: remove warning about max object name length
- 08:44 PM Revision 87efc952 (ceph): mds: try_trim_non_auth_subtree on any canceled import (including resolve)
- We were trimming on journal replay of an import failure, but not on a
canceled ambiguous import during resolve. Fix ... - 08:34 PM Revision e942a2a0 (ceph): mds: make trim_non_auth paths complete filepaths (not dnames)
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:22 PM Revision 21cc059e (ceph): mds: fix steal_dentry dir_auth_pins adjustment
- Pass down the correct value for dir_auth_pins (dh->auth_pins plus the
inode's auth_pins, but nothing nested beneath t... - 08:08 PM Revision 81041de1 (ceph): mon: use tcmalloc
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:00 PM Revision 8e4eed58 (ceph): mds: fix export_prep trace format
- The prep message includes a spanning tree in the interior of the subtree
that includes all parent inodes of bounding ... - 07:42 PM Revision 47afbdae (ceph): mon: make 'ceph osd (down,out,in) N' take mulitple osd numbers
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 07:34 PM Revision 5d6718e6 (ceph): libceph: no _t types
- Signed-off-by: Sage Weil <sage@newdream.net>
- 06:24 PM Revision 4b9c093c (ceph): lfn: short fn length is constant and accurate
- also, disabling real hashing for now
- 06:16 PM Revision c8859f04 (ceph): osd: bump up max object name size
- 06:15 PM Revision 7dd592aa (ceph): crypto: add support for SHA256
- 06:11 PM Revision 1fd2784d (ceph): libceph: typedef struct mystruct *mystruct_t
- Needed to drop the ceph_ prefix on the internal ceph_dir_result_t type
to prevent the ceph_dir_result_t typedef from ... - 06:04 PM Revision aad7006f (ceph): Merge commit 'origin/master' into lfn
- 05:37 PM Revision deb27efb (ceph): libceph: include 'struct' in declarations for C compilation
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:09 PM CephFS Bug #1031 (Resolved): dev node inconsistency between cfuse and kernel client
- A dev node created on a cfuse mount is displayed correctly by ls -l on the same mount point:
crw-rw-rw- 1 root roo... - 04:38 PM rgw Bug #985 (Resolved): radosgw listing keys of a bucket with name >=251 characters fails with NoSuc...
- Fixed, commit:95cea34e8d813236064c2d975e870c83e9224e00.
- 04:37 PM Feature #1008 (Resolved): filestore: handle long object names
- Done, merged at commit:c9712e4ffcaf91e212f73bc95c1f18e062dd0f22.
- 04:33 PM Bug #1030 (Resolved): osd: list pool/bucket contents excludes missing objects
- listing pool contents only lists objects stored locally, which excludes anything missing on the primary.
we could ... - 04:30 PM Revision 8aab0eca (ceph): mds: fix auth_pin check
- The inode only gets an auth_pin if the dirfrag is not a subtree root.
Signed-off-by: Sage Weil <sage@newdream.net> - 03:55 PM Revision d2a18f69 (ceph): config: Remove debug output in conf_get
- Signed-off-by: Wido den Hollander <wido@widodh.nl>
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 10:59 AM Cleanup #813 (Resolved): libceph interface cleanup
- 12:08 AM Revision a61b5195 (ceph): Merge branch 'master' of ceph.newdream.net:git/ceph
- 12:07 AM Revision a490d1e4 (ceph): mds: handle freeze completion delayed by frozen inode
- We can't complete a freeze_tree if we are not a subtree and the parent
inode is frozen. If that's the case, we were ...
04/27/2011
- 11:35 PM Revision f998bf64 (ceph): lfn: replace hash function
- for some reason crashes when using libnss
- 11:34 PM Revision 0a80865f (ceph): mds: add 'mds debug auth pins' option
- This counts dirfrag auth_pins and ensure the inode's nested_auth_pins
count is correct. Helped catch the bug fixed i... - 11:33 PM Revision d994e8b4 (ceph): mds: fix nested_auth_pin accounting on refragment
- The diri gets an auth_pin on the first frag pin when it is not a subtree
root. When we are moving dentries between f... - 10:52 PM Revision 27135c9e (ceph): mds: maintain dn pinning invariants during freezing for refragmenting
- fragment_mark_and_complete aims to complete the in-cache directory,
mark+pin every dentry, then drop a final auth_pin... - 10:09 PM Revision d6917cd7 (ceph): mds: freeze fragments during split/merge
- Freeze the target fragment(s) before unfreezing the old fragment(s) to
avoid any weird events going off when the unfr... - 08:03 PM Revision af6ed098 (ceph): lfn: some more fixes
- 07:16 PM Revision c9825f08 (ceph): automake: Make debug targets known but not built by default in non-debu...
- With this, "./configure --without-debug && make -C src testceph" will work.
Before this, it would use make builtin ru... - 06:24 PM Revision 63b0cfa3 (ceph): mds: remove erroneous fixme.
- This is for the client map journaling, but that's handled
elsewhere within this function...no idea why it ever had
a ... - 05:59 PM Revision d1116818 (ceph): mds: handle discovers that race with refragmenting
- Consider:
- send discover on frag X
- X refragments
- we take the waiter and rediscover on frag Y
- we get the... - 05:52 PM Revision a76d5831 (ceph): mds: Replay new client sessions on slave-rename importing.
- We've been logging the sessions for ages but never
actually opened them.
Signed-off-by: Greg Farnum <gregory.farnum@... - 05:14 PM Revision 33d1ea0d (ceph): mds: pay attention to *stat staleness during split
- Leave only the first frag stale, since we are already doing that with the
accounted_ differential.
Signed-off-by: Sa... - 05:00 PM Revision 7aef5444 (ceph): mds: merge accounted_* stats
- Signed-off-by: Sage Weil <sage@newdream.net>
- 01:14 PM CephFS Tasks #1002 (Resolved): Assert failure in Locker::handle_file_lock
- 10:29 AM CephFS Bug #92 (Resolved): mds: journal client_map for rename importing inode
- commit:a76d5831929d57b1505101445317fce778f08ed3
- 10:07 AM Feature #709 (Resolved): nagios plugin
- 06:57 AM Revision 512ab307 (ceph): obsync: use lxml to parse XML ACL
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 03:45 AM Revision 698b1ead (ceph): libceph: move header file to include/ceph/libceph.h
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 01:18 AM Bug #1029 (Rejected): ceph 0.27 run gceph, printf "Caught signal (Segmentation fault) " at a cli...
Hi ,
ceph 0.27,
I copy ceph.conf from a mon host to a client host /etc/ceph folder,
run "gceph" ,then printf " C...- 01:00 AM Bug #1028 (Resolved): segfault in OSDMap::object_locator_to_pg
- As reported yesterday on IRC, this is a crash I get when starting an OSD.
this is at v0.27
*From the logs:*
<p... - 12:24 AM Revision 6f074241 (ceph): lfn: some fixes
04/26/2011
- 11:49 PM Revision 12542c8a (ceph): lfn: amend long file name hashing
- 11:46 PM Revision a68340e4 (ceph): mds: ignore resolve messages received prior to resolve stage
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:39 PM Revision 68c2b578 (ceph): mds: handle aborted export during pre-export sync
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:33 PM Revision 2f16916b (ceph): lfn: push cid/oid translation down
- compiles now, not tested, probably doesn't work
- 11:28 PM Revision f6d1ccb6 (ceph): mds: drop messages to down mdss
- ...instead of asserting in MDSMap::get_inst.
Signed-off-by: Sage Weil <sage@newdream.net> - 11:18 PM Revision dd183ca0 (ceph): mds: do not send heartbeat when degraded
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:09 PM Revision e37878e0 (ceph): mds: fix discover tid assignment
- Hmm!
Signed-off-by: Sage Weil <sage@newdream.net> - 10:51 PM Revision 35efa2ba (ceph): vstart.sh: remove cruft
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:44 PM Revision 1f5b6202 (ceph): mon: fix standby-replay assignment (again)
- Only assign a random node to standby-replay if they are marked as
STANDBY_ANY.
Signed-off-by: Sage Weil <sage@newdre... - 10:39 PM Revision 319c20f2 (ceph): auth: Avoid const mismatch in nss_aes_operation
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Signed-off-by: Jim Schutt <jaschut@sandia.gov> - 10:37 PM Revision 9854e27f (ceph): configure.ac: check for supported compiler flags
- Ancient versions of gcc, such as the gcc 4.1.2 in RHEL 5.5, don't
support some -W flags that newer versions do. Fix ... - 10:31 PM Revision 00a25206 (ceph): vstart.sh: set up pairs for each rank when -s is on
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:26 PM Revision 28edbe5f (ceph): mon: rework assignment of standby-replay, expansion nodes
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:43 PM Revision 53a8e7d6 (ceph): mon: fix standby-replay assignment logic
- Assign a standby-replay at any time based on rank, name, or no preference.
Previously this could only happen when the... - 08:40 PM Revision 01f3526b (ceph): Merge branch 'osd_trans'
- 08:40 PM Revision 7c771108 (ceph): Merge remote branch 'origin/stable'
- 08:40 PM RADOS Bug #1017: ceph 0.26 ,mkcephfs --crushmap crush.new ,wait for very long time,mds stat is still "...
- hi
ceph 0.27
take the following steps ,this issue doesn't exist.
1.# crushtool --num_osds 6 -o file --build ho... - 08:39 PM Revision 6025dee1 (ceph): osd: move watch/notify effects out of do_osd_ops
- Apply watch/notify side effects in do_osd_op_effects() only if the
transaction will succeed.
Signed-off-by: Sage Wei... - 08:28 PM RADOS Bug #1016: ceph 0.26,crushmap change,mount fail.
- Hi ,
ceph 0.27 ,
i take the following steps, this issue doesn't exit.
1).
root@ubuntu-mon0:/etc/ceph/crushmap# cr... - 07:36 PM Revision 0aeab99c (ceph): obsync: implement RadosStore
- Implement RadosStore, a storage backend which accesses librados
directly, without going through RGW (Rados GateWay).
... - 07:34 PM Revision ccf11fbe (ceph): osd: mention invalid snapc in log
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:10 PM Revision 896de0ac (ceph): osd: include (some) osd op flags in MOSDOp print method
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 07:10 PM Revision b08ee2c6 (ceph): osd: add RWORDERED osd op flag
- Order this op wrt reads the same way a read-modify-write would be.
(Otherwise we may get a fast/stale read result on ... - 06:23 PM Revision a44065d7 (ceph): radostool: fix getxattr / setxattr return code
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:04 PM Revision 9c2f0f0c (ceph): rbd: make showmapped output a bit prettier
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:55 PM Revision 539f6719 (ceph): rbd: showmapped
- Show mapped rbd devices.
Fixes: #1024
Signed-off-by: Sage Weil <sage@newdream.net> - 05:49 PM Revision df1e1c80 (ceph): pybind-rados: fix Ioctx::close
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 05:39 PM Revision dd99226e (ceph): mds: only include head dentries in check_rstats() rstat check
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:35 PM Revision e643642b (ceph): osd: move ObjectState side effects out of do_osd_ops
- We want to be able to handle a failure mid-way through an OSDOp
transaction and bail out with no side effects. This ... - 05:29 PM Revision 101ca58e (ceph): objectstore: implement Transaction::swap()
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:29 PM Revision f922b64e (ceph): objectstore: transaction::append()
- Combine two transactions into one.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 05:29 PM Revision 424116f9 (ceph): buffer: use std::swap
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:07 PM Revision 604e76f5 (ceph): test-obsync.py: add tests with --no-preserve-acls
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 04:53 PM Revision 24133026 (ceph): osd: move snapset_context into ObjectContext from ObjectState
- ObjectState is now just static info (object_info_t and bool exists).
Signed-off-by: Sage Weil <sage@newdream.net> - 04:53 PM Revision 3210fe70 (ceph): osd: remove obsolete noop cruft
- The noop branching is all dead code.
Signed-off-by: Sage Weil <sage@newdream.net> - 04:53 PM Revision a31a6c12 (ceph): objectstore: drop decode support for <= v0.19 encoded transactions
- This only affects online upgrade or journal replay of v0.19 generated
transactions.
Signed-off-by: Sage Weil <sage.w... - 04:53 PM Revision 08265b1d (ceph): mon: fix pg stat summary
- Had the pg state counts in there twice.
Signed-off-by: Sage Weil <sage@newdream.net> - 04:40 PM Revision 9b30040d (ceph): mds: undump-journal
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:40 PM Revision a4c0cfac (ceph): buffer: break out read_fd method
- Read N bytes from the provided fd into the bufferlist.
Signed-off-by: Sage Weil <sage@newdream.net> - 01:26 PM Bug #963 (Resolved): osd: errors part way through multiple ops leave inconsistent object context
- commit:01f3526b62891b36333d89981e83c444253fa8e0
- 11:03 AM Feature #1024 (Resolved): rbdtool: list current kernel mappings
- 10:49 AM rgw Feature #1027 (Resolved): rgw log operations on non-existent bucket
- When logging an operation on non-existent bucket we should append the log on a special log object and not create an o...
- 12:15 AM Revision 55ae580e (ceph): rgw: check if bucket is empty before removing it
04/25/2011
- 11:39 PM Revision 87ad8da6 (ceph): obsync: another fix for --no-preserve-acls
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 11:03 PM Revision 010cc35d (ceph): obsync: fix bug in --no-preserve-acls
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 10:09 PM Revision dcca1460 (ceph): mds: Don't twiddle lock states in the middle of an import.
- This should have gone in a028c8954ca240ec9a12682678aaee02eb507ae3.
Signed-off-by: Greg Farnum <gregory.farnum@dreamh... - 09:34 PM Revision 3f820413 (ceph): Merge branch 'stable'
- Conflicts:
src/mds/MDLog.cc
src/osdc/Journaler.cc
src/osdc/Journaler.h - 09:32 PM Revision 904af336 (ceph): rgw: send content length on put operation
- 09:31 PM Revision 99c347a3 (ceph): rgw: send content length on put operation
- 09:14 PM Revision 6cc67880 (ceph): mds: wait for blacklisting osdmap on standby-replay -> replay final pass
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:14 PM Revision 885acf58 (ceph): journaler: separate out trimmed_pos setter
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:14 PM Revision 74644732 (ceph): mds: small journaler cleanups
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:14 PM Revision 68bafc06 (ceph): mds: only write head once after expiring logsegments
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:14 PM Revision b31400d7 (ceph): mds: always trim standby segments after rereading the head
- When we re-read the head we may get an expire_pos that has moved forward in
time. That is the appropriate time to tr... - 09:14 PM Revision e8847b2c (ceph): mds: only move the journaler expire_pos forward
- We were seeing weird trim errors because expire_pos was getting moved
backwards after a standby-replay -> replay tran... - 06:07 PM Revision a59153ee (ceph): librados python binding: always use 64-bit offsets
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:05 PM Revision ed7c583e (ceph): CephFSInterface: don't include Timer.h
- We don't use it.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com> - 06:05 PM Revision 0da60ead (ceph): client, libceph: clean up layout methods
- Signed-off-by: Sage Weil <sage@newdream.net>
- 06:05 PM Revision 34a72e1f (ceph): libceph: Remove *_precise
- In Linux, struct stat includes nanosecond resolution already. No need to
create a separate stat structure that duplic... - 06:05 PM Revision 4ebf73de (ceph): Client.cc: fix mode/flags confusion
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:05 PM Revision e8ac7b5c (ceph): hadoop: get hadoop bindings to build again
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:05 PM Revision 5b4690d8 (ceph): libceph: re-add set_default_preferred_pg
- Hadoop needs it.
Signed-off-by: Sage Weil <sage@newdream.net> - 06:05 PM Revision 8cb90183 (ceph): hadoop: re-add ceph_set_default_preferred_pg
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:05 PM Revision 6b830d8b (ceph): hypertable: update bindings to use new libceph API
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:05 PM Revision 57cfd767 (ceph): pybind-rados: fix read API
- Read should have the arguments in the same order as pread.
Add a test for reading from a nonzero offset.
Signed-off-... - 06:05 PM Revision 54782bf9 (ceph): libceph API change
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:05 PM Revision bff3004f (ceph): Client: unmount should not be able to fail
- If unmount fails, what is the API users supposed to do?
The client needs to be able to clean up after itself.
Signed... - 06:05 PM Revision 66b84fa7 (ceph): hadoop: whitespace fixes
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:05 PM Revision 529ef2d5 (ceph): libceph: avoid DIR*, combine connect and mount
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:05 PM Revision d3c0b420 (ceph): libceph: fix some bugs
- Fix some bugs in libceph and testceph.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com> - 06:05 PM Revision f7e51550 (ceph): testceph: add more tests
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:05 PM Revision 0bd7ee50 (ceph): do_autogen.sh: don't clear CFLAGS, CXXFLAGS
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:05 PM Revision e9fb106a (ceph): do_autogen: add -H for --with-hadoop
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:05 PM Revision 4d415071 (ceph): hadoop: convert to new libceph interface
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 05:21 PM Revision e38fc4f2 (ceph): mkcephfs: Fail if there are no mons defined.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 05:21 PM Revision 21504a06 (ceph): mkcephfs: Fail if a mon has no address set.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 05:20 PM Revision 3207c5df (ceph): mkcephfs: Remove temp dir, not just its contents.
- Also fixes the case where no temp files were created in the dir.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dream... - 05:15 PM rgw Bug #1026 (Resolved): rgw deletes non-empty buckets
- Fixed, commit:55ae580e0c7c823acd6fef63218dcc8b45b536fd.
- 04:10 PM rgw Bug #1026 (Resolved): rgw deletes non-empty buckets
- 05:01 PM Revision 829ca526 (ceph): journaler: fix flush completion when nothing to flush
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:44 PM Revision aca14f99 (ceph): journaler: default to readonly; fix asserts
- Previously were were never in a readonly state, which made all the existing
asserts meaningless.
Signed-off-by: Sage... - 04:14 PM Revision 0c38da26 (ceph): vstart.sh: fix -s
- Signed-off-by: Sage Weil <sage@newdream.net>
- 02:43 PM rgw Bug #1025: s3-tests should test S3 object extended attributes ("developer-added metadata")
- rgw should support it, tho it's not tested recently. So first step is to add it to s3-tests.git
- 02:41 PM rgw Bug #1025 (Resolved): s3-tests should test S3 object extended attributes ("developer-added metada...
- From the S3 developer's guide, 2006-03-01, page 272:...
- 02:34 PM CephFS Bug #92 (In Progress): mds: journal client_map for rename importing inode
- Generally, importing node journals session info for the imported caps. During the cross-MDS rename paths it's not jou...
- 02:07 PM CephFS Tasks #1002: Assert failure in Locker::handle_file_lock
- Okay, this was the same problem as commit:a028c8954ca240ec9a12682678aaee02eb507ae3.
- 01:28 PM CephFS Tasks #1002 (In Progress): Assert failure in Locker::handle_file_lock
- This popped back up again. It appears to be the result of a newly-imported inode getting mixed (from sync), which sen...
- 02:06 PM CephFS Bug #1023 (Resolved): just-recovered mds fails journaler assert (to > trimming_pos);
- fixed by commit:e8847b2cddbadf4f31972b490d80944dcb9f992d and others
- 08:51 AM CephFS Bug #1023: just-recovered mds fails journaler assert (to > trimming_pos);
- When it went fron standby-replay to replay a second replay thread was being forked. Cleaning this up in stable.
- 11:04 AM Feature #1024 (Resolved): rbdtool: list current kernel mappings
- rbd kernel list|show?
- 11:02 AM Bug #910 (In Progress): Multi-MDS Ceph does not pass fsstress
- Ran across at least one issue again....
04/24/2011
- 04:05 AM Revision a6ac9303 (ceph): mon: consisder osd recovery state in health check
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 04:04 AM Revision 2f95d920 (ceph): mon: include unfound count in pg recovery summary
- Fixes: #1003
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
04/23/2011
- 11:02 PM Revision 52b74811 (ceph): mon: fix up osd health report
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 10:08 PM Revision a9d12cb5 (ceph): mon: fix up pg health report
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 10:07 PM Revision 70640bf1 (ceph): mon: generalize health check a bit
- Any PaxosService can return a status (or not).
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 09:32 PM Feature #975: osd: use fallocate(FL_PUNCH_HOLE) for zero
- This doesn't appear to be in btrfs yet anyway.. let's wait!
- 09:27 PM Bug #1003 (Resolved): mon: health should show % degraded, unfound (and warn appropriately)
- 08:09 PM Revision fcf095c7 (ceph): Merge branch 'master' of ssh://ceph.newdream.net/home/sage/ceph.newdrea...
- 01:38 PM Feature #958 (Resolved): rbd: map/unmap kernel rbd device via rbd(?) tool
- 12:22 AM Revision 4368e974 (ceph): Makefile.am: add -fno-strict-aliasing
- Until we audit every place we have a typecast to make sure it's safe,
this should be off.
Signed-off-by: Colin McCab... - 12:17 AM Revision 4fe53fca (ceph): Makefile.am: Wpointer-arith, Wstrict-null-sentinel
- Add Wpointer-arith, Wstrict-null-sentinel, Winit-self
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
04/22/2011
- 11:52 PM Revision 793034c6 (ceph): v0.27
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:41 PM Revision 4b547cbb (ceph): Makefile: add some new warnings to CXXFLAGS
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 11:39 PM Revision 268f1897 (ceph): clitests: fix osdmap unit test
- Broken by removal of casdata in 8cd3f1cd2546a61bb5402fa374de7f37147dc3a0.
Signed-off-by: Sage Weil <sage.weil@dreamh... - 11:20 PM Revision 474be659 (ceph): mds: don't daemonize when doing journal reset.
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 10:31 PM Revision 625e7851 (ceph): rbd: rename kernel add/remove to map/unmap
- Unmap takes a device now, and uses the major number
to find the right sequence number in sysfs.
Also updated the man... - 08:39 PM Revision f5e20331 (ceph): Merge remote branch 'origin/next'
- 08:34 PM Revision 4cc88f62 (ceph): common, mount.ceph: move functions for working with secrets into secret.h
- Use sprintf instead of safe_cat, since we're just writing a string once.
Signed-off-by: Josh Durgin <josh.durgin@dre... - 08:34 PM Revision 20719c7a (ceph): rbd: use rados' init_with_config because we already called common_init
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 08:34 PM Revision bffb9edf (ceph): addr_parsing: move implementation out of header
- Also include missing headers and make it linkable with C,
since it's duplicated from mount.ceph.
Signed-off-by: Josh... - 08:34 PM Revision def36668 (ceph): addr_parsing: rename mount_resolve_dest to resolve_addrs and don't modi...
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 08:34 PM Revision 2ff3c82b (ceph): addr_parsing: use strtok_r to be safe
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 08:34 PM Revision 98698596 (ceph): mount.ceph: use common implementations of secret handling and address r...
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 08:34 PM Revision c87fc696 (ceph): rbd: add commands for manipulating the kernel sysfs interface
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 07:30 PM Revision 88ebb304 (ceph): Merge remote branch 'origin/next'
- 06:37 PM Revision 8cd3f1cd (ceph): osd: drop 'casdata' bucket by default
- We don't use it for anything. It just means we create a bunch of useless
PGs.
Signed-off-by: Sage Weil <sage@newdre... - 06:37 PM Revision cb8237e1 (ceph): testlibrbd: fix signed/unsigned comparisons
- testlibrbd.c: In function 'write_test_data':
testlibrbd.c:191: warning: comparison between signed and unsigned intege... - 05:33 PM Revision b419f3d7 (ceph): filestore: lfn_unlink removes the entry as last step
- so that if it crashes in the middle of operation we're not left
with a hole in the list of objects. In case of a cras... - 01:37 PM CephFS Bug #1023 (Resolved): just-recovered mds fails journaler assert (to > trimming_pos);
- 3 mdses configured for standby-replay. mds.1 was active, the other two?!? (not sure) were apparently following it. ...
- 12:17 PM Linux kernel client Bug #970: Kernel crash (cause?: lots of small files)
- probably a memory leak?
- 12:13 PM CephFS Bug #1022: every mds crash: Program terminated with signal 11, Segmentation fault.
- This looks like damage from a bug in the session journaling. Can you dump a copy of your journal so we can take a cl...
- 12:34 AM Revision 00ffafa8 (ceph): cmds: make journal-check mode run in the foreground.
- daemonize does a bunch of stuff we don't want to do.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 12:10 AM Revision 804a6d6c (ceph): mds: massage handling of oneshot-replay.
- We accidentally broke it in our last round of changes to support
standby-replay; patch it up again.
Signed-off-by: G...
04/21/2011
- 08:18 PM Revision 7979fa5c (ceph): OSDMon: make the defaults in reweight-by-utilization work.
- an oload <= 100 fails out; set the new default to 120.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 05:06 PM CephFS Bug #1006 (Resolved): clean up cmds journal-check mode
- Well, it will still take over the mds.a symlink if you start it up as a pre-existing MDS, but you shouldn't do that. ...
- 06:22 AM CephFS Bug #1022 (Can't reproduce): every mds crash: Program terminated with signal 11, Segmentation fault.
- A few seconds after startup, all my MDSes crash with the following message:...
- 03:50 AM Revision 8109f745 (ceph): testlibrbd: fix signed/unsigned comparisons
- testlibrbd.c: In function 'write_test_data':
testlibrbd.c:191: warning: comparison between signed and unsigned intege... - 03:50 AM Revision c8059372 (ceph): osd: drop 'casdata' bucket by default
- We don't use it for anything. It just means we create a bunch of useless
PGs.
Signed-off-by: Sage Weil <sage@newdre... - 12:11 AM Revision 1cff807c (ceph): filestore: lfn fixes
- also bumping up max object len to 2048, we'll probably want to change
that to a higher number (4096?), need to make s...
04/20/2011
- 10:16 PM Revision 4e21db6e (ceph): auth: const cleanup
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 09:35 PM Revision 1421d70d (ceph): obysnc: use python2.5 compatible exception syntax
- Apparently using "as" in "except" blocks is a new (and not
backwards-compatible) thing in Python 2.6.x. Who knew?
Si... - 08:54 PM Revision 3d97c33b (ceph): PGMon: use the config observer framework
- We now register observers on mon_osd_full_ratio and nearfull_ratio
to update the OSD full/nearfull lists.
Signed-off... - 08:51 PM Revision 19408759 (ceph): filestore: fix getxattr
- 08:51 PM Revision f940ee86 (ceph): ProfLogger: add NULL to KEYS in the config observer.
- I believe that without the null pointer it will overrun into
uninitialized memory.
Signed-off-by: Greg Farnum <grego... - 08:51 PM Revision 0e828416 (ceph): config: add comment clarifying virtual destructor.
- Just in case anybody else is like me and gets confused.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 08:49 PM Revision e209db4a (ceph): PGMonitor: unregister the config obs in ~PGMonitor
- Using the new unregister call, unregister the config observer in
~PGMonitor.
Signed-off-by: Colin McCabe <colin.mcca... - 08:38 PM Revision 527ecd4d (ceph): config: add remove_observer
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:58 PM Revision 5b218b27 (ceph): filestore: introduce long-file-names
- still needs testing, adjusting of constants and using a real hash function
- 05:58 PM Revision 7dc5a7f9 (ceph): PGMap: fill in full OSD sets on decode.
- Previously these sets were only modified when applying an incremental,
which might have caused problems when restarti... - 01:26 PM Feature #1010 (Resolved): mon: adjust mon-osd-[near]full-ratio on the fly
- This seems to be working in master on commit:3d97c33bea5144cbe5ed1b40704f74fff1ec0fb1.
- 10:19 AM Subtask #843 (Resolved): Decouple dout from g_conf
- implemented by commit:42a7013907e312d864cfcf591cca932cf9f343b2
- 10:19 AM Bug #1011 (Resolved): config observer structure to eliminate SIGHUP requirement
- implemented by commit:6e49c06ca90dc7aa696cbe298b4362dd4cb124ba, commit:8ebbd60a865605e7cc88e07b2b3f2f84521934a9
- 09:25 AM Bug #1021 (Can't reproduce): osd: _process_pg_info FAILED assert(pg->log.tail <= pg->info.last_co...
- ...
- 07:34 AM CephFS Bug #1019 (Resolved): mds: ~MDSlaveUpdate while on LogSegment list
- 04:55 AM Revision 07f287c6 (ceph): Merge remote branch 'origin/classdist'
- 12:59 AM Revision 8ebbd60a (ceph): conf: reopen proflogger on conf change
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 12:28 AM Revision 6e49c06c (ceph): conf: add observer framework
- Objects can now register as configuration observers interested in a
subset of the configuration keys. The observers w...
04/19/2011
- 11:11 PM Linux kernel client Feature #42 (Resolved): Resize of rbd image
- commit:e56433a0330b61e56489779e21f68fdc4c45f5be
- 10:33 PM Revision 36f00685 (ceph): cauthtool: -C not -c in man page
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 10:23 PM Linux kernel client Feature #819: robust nfs re-export
- There are patches queued for .40 that also try LOOKUPINO on unconnected fh's. This all needs testing.
- 10:22 PM Linux kernel client Bug #811 (Can't reproduce): rbd warning and crash
- 10:21 PM Cleanup #892 (Resolved): osd: remove class distribution infrastructure?
- 10:19 PM Tasks #584 (New): do throughput scaling tests on sepia
- 10:03 PM Revision 9a38acf0 (ceph): dout: remove DOUTSB_FLAG_STDOUT
- This was used to implement log_to_stdout, but that doesn't exist any
more. Instead of we have log_to_stderr and the o... - 10:03 PM Revision 433deec0 (ceph): dout: make dout a member of md_config_t
- Since logging options are per-config, logically DoutStreambuf instances
should also be per-config. This also allows u... - 10:02 PM Revision 0b6a023f (ceph): PGMap: add redo_full_sets() function for when ratios change.
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 09:55 PM Revision af92e8bf (ceph): PGMap: always decode pg_remove.
- pg_remove has been included for longer than we've had versions
in the struct, so this check for end is useless -- if ... - 09:55 PM Revision a2613f82 (ceph): PGMap: add [near]full_ratio to the Incremental and encoding.
- This way these ratios can be distributed by map updates.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 09:55 PM Revision 515c7677 (ceph): osdmon: Clean up debug output on map full flag.
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 09:32 PM Revision f9056d0d (ceph): osd: better debug output on replay completion
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 09:13 PM Revision 634dfc90 (ceph): mkcephfs: allow a prebuild osdmap to be specified
- Otherwise we'll create one with osdmaptool --createsimple with the default
generic settins.
Signed-off-by: Sage Weil... - 08:57 PM Revision ad71955a (ceph): cfuse, mds, dout: Do not create "rank" symlinks for log files.
- Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 07:05 PM Revision 4428d1ec (ceph): Revert "Revert "autoconf: Complain if tcmalloc is not found.""
- This reverts commit 05c281bfa9e9d69ea3d0197590950c8e6845a13a.
This should be okay now. - 07:05 PM Revision f6179fc3 (ceph): debian: Handle missing tcmalloc on Debian lenny.
- lenny doesn't have a suitable libgoogle-perftools-dev, and
release.sh edits it out of build-deps. Detect that and tel... - 07:05 PM Revision 0d98a62c (ceph): debian: Build without tcmalloc on non-i386/amd64.
- This is not strictly needed as of 05c281bfa9e9d69ea3d0197590950c8e6845a13a,
but that reverting is hopefully only temp... - 06:59 PM Revision bd7922a1 (ceph): remove old debian build helper scripts.
- This is now handled by ceph-build.git
Signed-off-by: Sage Weil <sage@newdream.net> - 06:33 PM Revision 7c04f81c (ceph): mon: remove class distribution infrastructure
- This is now the admin's job. Removes a lot of code with limited testing
and coverage.
We rev the internal monitor p... - 06:11 PM Revision deb0ee90 (ceph): osd: move ClassHandler.{cc,h} to osd/
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 06:09 PM Revision 964a0a6e (ceph): osd: load classes from a fixed location off disk
- Simplify the class loading code to just load out of a local directory.
Do not request classes from the monitor.
Sign... - 05:28 PM Revision 54284c0a (ceph): common: add environment.cc/environment.h
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 04:51 PM Bug #1020 (Duplicate): osd: replay_queued_ops crash
- duplicates 990. Working on a peering/recovery refactor which should take care of this.
- 02:35 PM Bug #1020 (Duplicate): osd: replay_queued_ops crash
- ...
- 04:50 PM Bug #906: clustered mds: lchown not setting uid/gid
- Here's an idea: run the autotest say 10 times (after the test, ssh to the sepia machines and ensure they've rebooted,...
- 04:43 PM Bug #906: clustered mds: lchown not setting uid/gid
- Still unable to reproduce this locally, and running it again on the autotest cluster it didn't fail.
It's possible... - 04:37 PM CephFS Bug #1006 (In Progress): clean up cmds journal-check mode
- Okay, it's more broken than that -- somehow it ends up in standby-replay instead of oneshot-replay!
- 04:25 PM Revision d55399ff (ceph): mds: remove MDSlaveUpdate from list on deletion
- These are added to the LogSegment list on the slaves, but also need to be
removed from that list when we replay a COM... - 11:43 AM Linux kernel client Bug #1014: kclient can't complete fsstress on multi-mds cluster
- Not high priority right now, so unassigning.
- 09:13 AM CephFS Bug #1019: mds: ~MDSlaveUpdate while on LogSegment list
- commit:d55399ffec224206ea324e83bb8ead1e9ca1eddc
- 08:52 AM CephFS Bug #1019 (Resolved): mds: ~MDSlaveUpdate while on LogSegment list
- ...
- 08:54 AM Bug #1015 (Rejected): ceph 0.26, mkcephfs : ERROR: error creating empty object store
- You need to create the directory yourself and this is deliberate. It prevents administrators from not fully setting u...
- 08:31 AM Bug #1018 (Can't reproduce): error on building ceph on red hat 5.5
- building ceph on rh 5.5 i have obtained this error.
if g++ -DHAVE_CONFIG_H -I. -I. -I. -Wall -D__CEPH__ -D_FILE... - 12:54 AM Revision 87def518 (ceph): common_init: move version printout to common_init
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 12:32 AM Revision ae0f5f03 (ceph): interval_set: slightly better API for erase
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 12:18 AM RADOS Bug #1017 (Closed): ceph 0.26 ,mkcephfs --crushmap crush.new ,wait for very long time,mds stat i...
- Hi ,
ceph 0.26 + btrfs +ubuntu 10.04 x86_64;
we want to use a special crushmap when do mkcephfs,but wait for very v... - 12:12 AM RADOS Bug #1016 (Closed): ceph 0.26,crushmap change,mount fail.
- Hi ,
ceph 0.26 ,change crushmap,then at a client ,mount ceph ,but fail.ceph.conf/crush.new.txt/crush.origin.txt/ a...
04/18/2011
- 11:51 PM Bug #1015 (Rejected): ceph 0.26, mkcephfs : ERROR: error creating empty object store
- Hi ,
when do mkcephfs ,if it doesn't create osdN directory manually, then ,mkcephfs fail.
1. ceph 0.26 + btrfs +ubu... - 11:26 PM Revision faffcc56 (ceph): Change some global config options to env vars
- Options that are inherently global, like malloc settings, and also
inherently debugging or profiling settings should ... - 11:26 PM Revision e4e2b742 (ceph): Merge commit '8038c491ba90a8cbcd569e84d4cafc8bbdff81d5' into next
- 11:23 PM Revision c93c6619 (ceph): Merge remote branch 'origin/stable' into next
- 10:32 PM Revision 2e41f084 (ceph): journaler: fix do_flush adjustment
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:30 PM Revision bb4cfabc (ceph): osd: assert on query on deleting pg
- This shouldn't happen; assert if it does.
Signed-off-by: Sage Weil <sage@newdream.net> - 10:29 PM Revision 67721b00 (ceph): osd: do not create pgs on query
- We do not need to create the pg on query. If we are a new replica we can
create it when we get the PGLog activate me... - 10:06 PM Revision b05f1ba4 (ceph): journaler: truncate/zero ahead of write position
- Remove/zero objects N periods ahead of the journal write position. This
ensures that when we reprobe the journal len... - 10:06 PM Revision 974d859e (ceph): filer: remove whole objects on zero()
- Make filer::zero() remove any whole objects. This is required by the
Journaler, given the way it probes the journal ... - 10:06 PM Revision 0f0c1c85 (ceph): interval_set: implement erase(iterator)
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:06 PM Revision eaf52413 (ceph): Merge branch 'next'
- 09:34 PM Revision e6393525 (ceph): journaler: check return code on _finish_write_head.
- If we get an error code and assume we successfully wrote the head,
there are going to be all kinds of issues on repla... - 08:55 PM Revision 68863bb4 (ceph): osd: make ZERO on non-existent object a no-op
- Fixes bug where oi.size gets out of sync with the object size because we
actually write zeros. (This explains #933.)... - 08:12 PM Revision ab9dc122 (ceph): vstart tests: specify ceph.conf
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 08:12 PM Revision 42a70139 (ceph): dout: remove references to g_conf
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 07:54 PM Revision 878f4a45 (ceph): rgw: return appropriate error for unresolvable email in acl
- 06:53 PM Revision b8e791bc (ceph): config: reorder config_option struct members
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:52 PM Linux kernel client Bug #1014 (Closed): kclient can't complete fsstress on multi-mds cluster
- cfuse is doing great with fsstress on multi-mds systems now, but the kclient won't finish. Analysis is needed.
- 06:48 PM Bug #910 (Resolved): Multi-MDS Ceph does not pass fsstress
- I've been unable to break this under cfuse in master all day.
- 06:47 PM CephFS Tasks #1002 (Resolved): Assert failure in Locker::handle_file_lock
- 11:36 AM CephFS Tasks #1002: Assert failure in Locker::handle_file_lock
- I suspect this got fixed up by some of the other changes, but want to leave it open for a little longer just to make ...
- 06:44 PM Revision 3f275bcf (ceph): clitests: eliminate use of old-style section name
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:44 PM Revision 756a2acc (ceph): config: remove unused OPT_NONE type
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 06:44 PM Revision 8038c491 (ceph): clitests: fix radosgw_admin test
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 05:41 PM Revision 6058a36c (ceph): MDS: move slave rename xlock handling before finish_export_inode.
- finish_export_inode changes states! That's not good for our checks,
so just handle unpinning and stuff before we fini... - 05:41 PM Revision 14dd2994 (ceph): improve debug printing
- 05:41 PM Revision d8579833 (ceph): mds: Unify migration-handling code in _commit_slave_rename.
- We need to handle locks and pins on exported inodes but we
were using a separate if block with its own (non-matching!... - 05:40 PM Revision 6bd20815 (ceph): mds: _commit_slave_rename needs to drop auth_pins for exported xlocks.
- Otherwise these pins are never dropped from the inode since we
don't go through our normal xlock teardown code. Now w... - 05:40 PM Revision 1a6f4376 (ceph): MDS: Make _rename_apply inode import auth_pinning more intelligent.
- We don't want auth_pins on the locallocks (they're never auth_pinned)
and we only want new auth_pins that are for loc... - 05:40 PM Revision 478c6173 (ceph): mds: If we're a slave, clean up xlocks when we export an inode.
- Because we can do an inode import during a rename that skips the usual
channels, we were getting into an odd state wi... - 05:40 PM Revision 5299aabe (ceph): mds: properly drop imported xlocks.
- Because we can do an inode import during a rename that skips the usual
channels, we were getting into an odd state wi... - 05:36 PM Revision 97e357c4 (ceph): MDS: Server takes auth_pins for xlocks on imported inodes.
- Should fix #934.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 05:15 PM Revision 216fd776 (ceph): objecter: resub ops on full->nonfull transition
- This was broken a while ago during the last refactor. Whoops! Clean it
up to be smarter (and work at all).
Signed-... - 04:58 PM Revision 879adb61 (ceph): Merge remote branch 'origin/stable'
- Conflicts:
src/osdc/Journaler.cc - 04:57 PM Revision c966410f (ceph): osd: show "full" or "nearfull" in osdmap summary line
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 04:56 PM Revision fa7061d2 (ceph): Merge branch 'rgw_uid'
- 03:56 PM Revision 796528c3 (ceph): rgw: remove get_user_info() and clean up
- rename all the get_uid_by_* to get_user_info_by_*, remove get_user_info()
and call the appropriate function instead (... - 03:32 PM Revision d8fe208d (ceph): rgw: store user info on all indexes in the same format
- this breaks backward compatibility, we'll have to deal with that
later. - 03:15 PM Revision 11f1e2ef (ceph): rgw_admin: can lookup user by access key
- 02:54 PM CephFS Bug #873 (Resolved): MDS journaler needs to truncate ahead of writes
- commit:b05f1ba4c46976bd96a1df8a582dffd89860eb34
- 10:53 AM CephFS Bug #873 (New): MDS journaler needs to truncate ahead of writes
- 02:03 PM Bug #1013 (Can't reproduce): filejournal buffer::rebuild crash
- ...
- 12:41 PM rgw Bug #982 (Resolved): radosgw should fail with UnresolvableGrantByEmailAddress on add_email_grant ...
- Fixed, commit:878f4a45ceebd3038a6983a97064b0fdcfec11fe.
- 10:12 AM rgw Bug #982: radosgw should fail with UnresolvableGrantByEmailAddress on add_email_grant to unknown ...
- At this point, instead of returning an error, we just ignore the bad entry.
- 11:35 AM Tasks #1005 (Resolved): xlock is not unpinning during rename across MDSes
- Looks like this is fixed.
- 11:20 AM Bug #1012 (Rejected): Autotest: Measure RADOS IO performance under read and write loads
- We've had sporadic but steady reports about writes starving reads. Write an autotest to measure various kinds of RADO...
- 11:00 AM Feature #974 (Resolved): autotest: include ffsb benchmarks
- 10:56 AM Bug #935 (Can't reproduce): ceph client heavy loading in Metadata server
- 10:47 AM Bug #1011 (Resolved): config observer structure to eliminate SIGHUP requirement
- 10:11 AM rgw Bug #980 (Resolved): radosgw returns access_key instead of user_id when fetching acl
- Fixed as of commit:796528c3db66d63d0bd75c880cb871d5e4f0322a.
- 09:58 AM Feature #1010 (Resolved): mon: adjust mon-osd-[near]full-ratio on the fly
- The nearfull and full ratios are set in the PGMap constructor, and the lists for maintained privatley by PGMap. That...
- 09:42 AM Tasks #419 (Closed): 24/7 testing
- 09:41 AM CephFS Bug #523 (Can't reproduce): cfuse locks don't wake on mds reconnect?
- 09:37 AM Linux kernel client Bug #1004 (Resolved): hanging writes, bisected to i_state locking change
- commit:283a85d
- 04:58 AM Revision d7789218 (ceph): mount.ceph: behave when CONFIG_KEYS is not compiled in
- In that case we get ENOSYS. This also implies an old version of the client
and that we should fall back.
Signed-off... - 12:42 AM Revision d21bdd6e (ceph): radosgw_admin: Update manpage to new syntax
- Signed-off-by: Wido den Hollander <wido@widodh.nl>
Signed-off-by: Colin McCabe <cmccabe@alumni.cmu.edu>
04/17/2011
- 04:04 AM Revision 1eccc019 (ceph): MDS: Fix Locker::handle_reqrdlock for xlocked locks.
- We previously dropped the request but that was inappropriate for that
one case because the replica has no way to trig... - 04:03 AM Revision 79cac5ee (ceph): mds: Always _open_parents when opening a new snaprealm
- Signed-off-by: Sage Weil <sage@newdream.net>
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 04:03 AM Revision a028c895 (ceph): mds: don't run all of try_subtree_merge on a rename across MDSes.
- Previously we'd try and do the whole thing, which meant that
the replica got a lock twiddle before it had finished th... - 04:02 AM Revision 6250e82c (ceph): mds: adjust LocalLock can_xlock_local().
- I don't remember why we needed can_xlock_local() to begin with, but
I can tell that adding this get_xlock_by() check ... - 04:02 AM Revision 5a65a04a (ceph): mds: Extend use of find_ino_peers.
- Missed a few places that need it.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
Signed-off-by: Sage Weil... - 04:02 AM Revision bea966af (ceph): mds: Make use of find_ino_peers
- Previously we just had to give up on ESTALE. Now
we can attempt to recover!
Signed-off-by: Greg Farnum <gregory.farn... - 04:01 AM Revision 22e8519d (ceph): random commenting
- 04:01 AM Revision ace54db0 (ceph): MDS: Remove inappropriate assert from _logged_slave_rename.
- The slave also can hold some auth pins from locks which the
master has asked it to grab. It's possible we can intelli... - 04:01 AM Revision ac045dc3 (ceph): MDS: Server::handle_slave_rename_prep now accounts for dir snaplock.
- Previously it ignored the auth pin required to hold snap xlock, which
is currently always held for a rename on a dir.... - 04:00 AM Revision 597e30ed (ceph): MDS: Don't move inode to snaprealms if not primary inode.
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 03:59 AM Revision 08bd2ef1 (ceph): MDCache: update assert to account for being a slave.
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 03:59 AM Revision 569cce39 (ceph): Server: push_projected_linkage in _link_remote
- _link_remote_finish will pop the linkage if inc==true, so we'd
better push it to match!
Signed-off-by: Greg Farnum <... - 03:59 AM Revision 5b825c3a (ceph): Server: ensure slave mdses have full dest tree
- We were already taking rdlocks on the source tree, to make
sure that each slave MDS could traverse to the source dent...
04/16/2011
- 10:13 PM Cleanup #1009 (Resolved): osd: push pg message handling code into ReplicatedPG
- There is a lot of code in OSD.cc that does PG-specific work, mostly in the handle_pg_* message handlers. Those in tu...
- 10:07 PM Feature #1008 (Resolved): filestore: handle long object names
- extN and btrfs both limit filenames to 255 characters, but we want to store object names that are much longer than th...
- 10:03 PM Bug #906: clustered mds: lchown not setting uid/gid
- This isn't popping up with single mds... probably a clustering thing.
- 09:42 PM Feature #1007 (Resolved): qa: osd failure and cluster recovery test(s)
- We need tests of OSD failures that verify the cluster is able to recover. Eventually this will need to be fleshed ou...
- 09:33 PM CephFS Bug #994 (Resolved): EOpen reply on non-auth MDS is busted
- I was wrong about the diagnosis before. Pretty sure commit:777bcba0 fixes this.
As for the non-auth caps, I forgo... - 12:20 AM Revision 544ce94a (ceph): rgw: basic support for separate uid and access key
04/15/2011
- 11:32 PM Revision 777bcba0 (ceph): mds: don't skip inodes in journal that may be trimmed during replay
- During replay we trim non-auth inodes on EExport or EImportFinish abort.
Subtree trimming may be delayed, too.
Skip ... - 11:32 PM Revision c7385c1d (ceph): mds: use helpers for import_reverse
- Use helpers for common code shared between handle_export_cancel and
handle_mds_failure_or_stop.
Also include handlin... - 11:32 PM Revision e15d9ca1 (ceph): mds: cancel exports in PREPPING state on any failure
- The prepping nodes may need to discover bounds from the failed node and
may hang indefinitely. Meanwhile, we won't s... - 11:32 PM Revision 07098fa5 (ceph): mds: clean up trim_non_auth_subtree output
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:32 PM Revision d94c69e5 (ceph): mds: fix export cancel during IMPORT_PREPPING
- If we are in PREPPING, we need to drop the stickydirs() on the inodes, and
not the pins on the dirfrags. Do this in ... - 11:32 PM Revision f8551514 (ceph): mds: keep import/export subtree_map state in sync with journal
- We were being sloppy before with the ESubtreeMap vs import/export events.
Fix that by doing a few things:
- add an ... - 11:32 PM Revision 24f35e79 (ceph): mds: fix null deref in debug
- The *dir isn't always non-null (namely, during DISCOVERING state).
Signed-off-by: Sage Weil <sage@newdream.net> - 10:54 PM Revision 2c0b8440 (ceph): man: Update cmds documentation.
- You always need to specify a rank if you do journal-check.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 10:29 PM Revision 92d349c6 (ceph): config: warn about old-style conf section names
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 10:11 PM Revision ff5bc8fd (ceph): mkcephfs: fix check for highest osd
- This breaks on osd0. I was doing something stupid with sed but I can't
figure out what right now, but osdN support i... - 09:46 PM Revision e34e332b (ceph): vstart.sh: use new-style section names in config
- Use new-style section names in vstart.sh.
Also update sample.ceph.conf.
Signed-off-by: Colin McCabe <colin.mccabe@dr... - 09:40 PM Revision cc0e5668 (ceph): mon:don't check for old-style monitor section name
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 09:34 PM Revision a6f0ce42 (ceph): cconf: update man page
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 09:04 PM Revision 925a2e0e (ceph): mkcephfs, init-ceph: tolerate complete lack of a type
- We were bailing out of mkcephfs with a config with no mds's defined
(because we set -e and grep returns an error here... - 09:04 PM Revision a7e7bdee (ceph): objecter: log when we defer a write because of FULL osdmap flag
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 09:03 PM Revision c9154c09 (ceph): mkcephfs, init-ceph: tolerate complete lack of a type
- We were bailing out of mkcephfs with a config with no mds's defined
(because we set -e and grep returns an error here... - 09:03 PM Revision a0a5ea4e (ceph): config: do not accept old-style section names
- Stop accepting old-style section names of the form $type$id. Instead,
we want section names of the form $type.$id. ... - 08:58 PM Revision b7406701 (ceph): cconf: fix usage; clean up some code
- cconf: fix obsolete usage message. Add --list-all-sections flag.
Use new ceph_argparse stuff. Update tests.
Signed-o... - 08:18 PM Revision ba69603e (ceph): config: normalize key names, cleanup
- Normalize key names in md_config_t::get_val and md_config_t::set_val
Remove unused fields from struct config_option.... - 06:15 PM Revision 9b7f223a (ceph): rgw: fix other err related issues
- also remove the now redundant formatter->flush()
- 05:52 PM Revision 303420bf (ceph): rgw: adjustments to error handling
- fixing mixup between s3 error code and s3 error message
- 05:38 PM Revision 54bc4b69 (ceph): libceph: implement ceph_conf_set and ceph_conf_get
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 05:24 PM Tasks #1005 (In Progress): xlock is not unpinning during rename across MDSes
- Okay, reproduced with my extra logging. Locks 0x1163068 and 0x1162fb8 take an auth_pin but don't put one; these are t...
- 01:45 PM Tasks #1005 (Resolved): xlock is not unpinning during rename across MDSes
- See logs in kai:~gregf/logs/fsstress/freeze_tree_assert.
I managed to narrow it down to inode 20000000166 having a... - 03:22 PM CephFS Bug #1006 (Resolved): clean up cmds journal-check mode
- I'm not sure it should run in background instead of foreground.
Even if it should run in background, it should not t... - 12:18 PM CephFS Tasks #1002: Assert failure in Locker::handle_file_lock
- Yeah, Sage said this looks like the new auth is sending messages before it should, probably due to some kind of twidd...
- 11:25 AM Linux kernel client Bug #1004 (Resolved): hanging writes, bisected to i_state locking change
- ...
- 10:33 AM Feature #899 (Resolved): autotest: hammer rbd mount(s) with standard fs benchmarks
- Pushed to autotest master now.
- 04:18 AM Revision 13c6b902 (ceph): mds: init metablob MDLog* for EImportStart
- This will initialize metablob.my_offset, which makes the parent inode
journaling logic work properly.
Signed-off-by:... - 04:17 AM Revision 68653b38 (ceph): init-ceph: no log_dir default
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:17 AM Revision 6150f581 (ceph): mds: fix journal offset types
- Always uint64_t!
Signed-off-by: Sage Weil <sage@newdream.net> - 04:17 AM Revision f5b566b0 (ceph): mds: show migration state names on cancel
- Signed-off-by: Sage Weil <sage@newdream.net>
- 12:13 AM Revision b5f6eb12 (ceph): rgw: rework error handling a bit
- Rados Gateway: get rid of RGWOp::err. We already have req_state::err and
that represents the same thing.
Standardize...
04/14/2011
- 10:52 PM Revision 4eb9d4f7 (ceph): config: add test for override ordering, comment
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 10:49 PM Revision a1994162 (ceph): config: de-globalize reading config file
- Reading a config file into any md_config_t structure except g_conf used
to be impossible. This is because the config_... - 10:18 PM Revision 22dbbe85 (ceph): radosgw_admin: fix make check
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 10:14 PM Revision a3a1a043 (ceph): config: make md_config_t.name a value, not ptr
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 09:59 PM Revision a3144a11 (ceph): rgw: don't modify object owner when setting acls
- 09:43 PM Revision 54913d43 (ceph): radosgw_admin: add 'bucket unlink' option
- 09:43 PM Revision 6f730af1 (ceph): rgw: allow changing acl using canned acl
- 06:38 PM Revision 08e9855d (ceph): mkcephfs: Actually do a mkfs.btrfs
- Signed-off-by: Wido den Hollander <wido@widodh.nl>
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com> - 05:14 PM rgw Bug #977 (Resolved): radosgw should provide error code for bad bucket name errors
- fixed by commit:b5f6eb12e1004888bf9dec6aa9c4b0499093ebfb
- 11:34 AM rgw Bug #977: radosgw should provide error code for bad bucket name errors
- An RGW error return for an illegal mkbucket:...
- 02:47 PM rgw Bug #981 (Resolved): radosgw bucket.set_acl() seems to always fail with AccessDenied
- Fixed at commit:6f730af1926f9d4fe5904ac10dbe019c0a6aef8d.
- 11:22 AM Bug #924: Various OSD/FileStore bugs
- This actually may have been fixed in e26626a8b4d91bb827a4909fd7f45f2c5f06f331.
- 11:19 AM CephFS Tasks #1002 (In Progress): Assert failure in Locker::handle_file_lock
- Looks like there's a problem because the inode in question is being renamed across MDSes (big shocker, I know!). The ...
- 11:16 AM Bug #959 (Resolved): use sizeof rather than if (0) in logging macros (and other macros)
- I checked back on this, and gcc (now) seems to be pretty smart about omitting code that's inside an if (0) { } block....
- 12:40 AM Revision 141178f1 (ceph): MonitorStore: use sync_filesystem when available
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
04/13/2011
- 10:36 PM Revision 09d4c96d (ceph): dout: log_per_instance should work with log_file
- Now log_per_instance (the symlink dance) works with both log_file and
log_dir. This will facilitate gradually removin... - 10:05 PM Revision 98911b6c (ceph): RadosModel: error handling fixes
- ReadOp should read the recieve length to prevent buffer error.
Check error codes on WriteOp and ReadOp.
Signed-off-... - 09:51 PM Revision 839b4cac (ceph): filestore: fix do_getxattr check
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 09:23 PM Revision 9ac7825d (ceph): FileStore: give better error message about xattrs
- Fixes #952.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com> - 08:58 PM Revision 607ce44a (ceph): mds: do not start_new_segment on replay_start
- We do not need to start a new segment after replay. And in fact must not
journal an ESubtreeMap prior to doing resol... - 08:58 PM Revision 7dc82d09 (ceph): mds: during export list target second
- We need to maintain the invariant that (dir_auth.first==whoami) == is_auth.
Signed-off-by: Sage Weil <sage@newdream.... - 08:58 PM Revision 9e0565cd (ceph): mds: fix dn unlocking on export_reverse
- Triggered by mds_kill_import_at 5. We were clearing the export_locks
prior to calling export_unlock (der!).
Signed-... - 08:58 PM Revision 4001b81d (ceph): mds: fix choose_lock_state() on xlocked object
- This crops up on inodes during clientreplay when we reconnect the cap
on the newly created (and still xlocked) object... - 08:58 PM Revision aa074898 (ceph): mds: fix _freeze_dir assert for refragment case
- The is_freezeable_dir() is true at freeze time but not forever after over
the lifetime of the freeze. We split later... - 08:58 PM Revision 4fe48ed8 (ceph): mds: don't check_rstats on non-auth or frozen dirs
- If we are, say, auth but frozen (mid-import) the dir content isn't valid
and check_rstats will likely fail.
Signed-o... - 08:58 PM Revision c9ce4cf9 (ceph): mds: fix resolve
- This was broken by a01fba175b646f6 when an ambiguous import was changed
from CDIR_AUTH_UNKNOWN to <whoami,whoami> and... - 08:58 PM Revision 338c9a66 (ceph): mds: queue rejoin_waiters on rejoin_ack survivor
- For recovering nodes, we eventually open_snap_parents and much later
requeue these waiters. A surviving node wasn't ... - 08:58 PM Revision 7c17cd32 (ceph): mds: fix bad import_state check on handle_export_discover
- This populates import_state[] with an bad value and leads to crashes like
mds/Migrator.h: In function 'static const ... - 08:45 PM Revision e341fe0b (ceph): osd: Use syncfs when available
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 08:29 PM Revision 5c06fc1c (ceph): rgw: create bucket with empty name should return a valid error
- 06:52 PM Bug #1003 (Resolved): mon: health should show % degraded, unfound (and warn appropriately)
- (if it doesn't already)
- 05:39 PM Revision 59309b37 (ceph): rgw: recreation of bucket returns success
- unless it was owned by a different user, at which case it
returns -EEXIST. - 05:36 PM Revision b7b66ac9 (ceph): mds: update rstats on stray dir when you rename over existing inode.
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 05:02 PM Revision cc162771 (ceph): sample.ceph.conf: add log file and pid file
- These really should be included in a sample...
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com> - 05:01 PM Revision 694c4379 (ceph): vstart.sh: use "log file" instead of "log dir"
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 04:05 PM Bug #910: Multi-MDS Ceph does not pass fsstress
- Okay, been pecking away at this and I think I'm now down to one bug that Sage says he's fixed in his branch, and #100...
- 04:05 PM CephFS Tasks #1002 (Resolved): Assert failure in Locker::handle_file_lock
- ...
- 03:45 PM Revision fd0290a0 (ceph): rgw: listing non existent bucket returns NoSuchBucket
- 02:24 PM Bug #952: Make lack of btrfs/user_xattr more obvious in mkcephfs
- I'm actually glad to see a better error message go here. This was a very common problem for users!
- 02:23 PM Bug #952 (Resolved): Make lack of btrfs/user_xattr more obvious in mkcephfs
- fixed by commit:9ac7825dc1afe2e052287a669130a56cadd21af1
- 02:08 PM Bug #989 (Resolved): rstats and fragstat messages in mds logs
- Seems to be working. Pushed to master in commit:b7b66ac95e406076608df24424ac6d95d72a9ac6.
- 01:47 PM rgw Bug #985: radosgw listing keys of a bucket with name >=251 characters fails with NoSuchKey
- I added too-long-object-name error checking to rados with commit:694c4379ceb892a78a9e0f63bfe11070eff53a84 . Yehuda is...
- 01:46 PM Bug #953 (Resolved): osd, mon: use sys_syncfs() when it hits glibc
- implemented by commit:e341fe0b1854aa1d6e961395877e643a0e8b2306
- 01:27 PM rgw Bug #982: radosgw should fail with UnresolvableGrantByEmailAddress on add_email_grant to unknown ...
- Actually, looking at the code we currently just ignore entries that don't resolve. Failing with the correct error sho...
- 01:17 PM rgw Bug #983 (Resolved): radosgw hangs, gives 500 internal server
- Fixed, commit:5c06fc1c8b4e983acd7f01f7b908ba8f357621b2.
- 11:02 AM rgw Bug #999 (Resolved): Duplicate Bucket Created
- Fixed now, commit:59309b376c5356afd97a2e72f126159d2a4877ba.
- 10:29 AM rgw Bug #978 (Resolved): radosgw bucket creation should succeed on pre-existing bucket if the owner m...
- Fixed now, commit:59309b376c5356afd97a2e72f126159d2a4877ba.
- 09:22 AM Bug #1001 (Resolved): dead mds remains up, won't let others take over
- 08:34 AM rgw Bug #976 (Resolved): Non-existent bucket error code should be NoSuchBucket, not NoSuchKey
- Fixed at commit:fd0290a00ac76bbfe15bb12ee35e54dc58cf074f.
- 05:20 AM Bug #990: osd: PG::replay_queued_ops
- According to sjust this should have been fixed in the osd_wip1000 branch, but I just hit the bug again on several OSD...
- 02:57 AM Revision baeab784 (ceph): Merge remote branch 'origin/mon_mds'
- 12:20 AM Revision 02e93108 (ceph): osd: move MAX_CEPH_OBJECT_NAME_LEN into object.h
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 12:09 AM Revision 40828086 (ceph): osd: check obj name length to avoid ENAMETOOLONG
- Since the object store is ultimately based on ext3, ext4, or btrfs, and
object names ultimately get translated into f...
04/12/2011
- 11:40 PM Revision 2380e70a (ceph): librbd: don't write to stdout
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 09:31 PM Revision 1eae9d6d (ceph): Add test_mutate
- Add test_mutate, in an effort to track down an objecter bug.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com> - 09:14 PM Revision 9c731edd (ceph): mdsmap: initialize standby_for_rank
- This is initialized in MDSMonitor anyway; do so where for completeness.
Signed-off-by: Sage Weil <sage.weil@dreamhos... - 09:13 PM Revision 5e27a079 (ceph): mon: simplify mds follow checks
- Instead of assigning followers in the last_beacon laggy check loop, do it
at the end, the same way we let standby nod... - 09:08 PM Revision 2b59bc61 (ceph): mon: simplify mds laggy check
- We should never have a laggy standby, so technically this doesn't change
any behavior, but it makes the flow less con... - 09:08 PM Revision e9afe17e (ceph): mon: don't take over for a standby-replay
- If a standby-replay is laggy we shouldn't "take over" for them (they're
not part of the cluster yet). They should be... - 09:06 PM Bug #989: rstats and fragstat messages in mds logs
- All right, try this patch and see if it fixes it?...
- 09:04 PM Revision 2b2766dd (ceph): rados-tool: use init_with_config interface
- Programs that use both librados and common_init should use
init_with_config.
Signed-off-by: Colin McCabe <colin.mcca... - 07:39 PM Revision 466306de (ceph): mds: make _create_system_file dirty dentries properly
- Properly dirty the new dentries so they get written to the directory
objects later on.
Signed-off-by: Sage Weil <sag... - 07:39 PM Revision d7544dd6 (ceph): mds: fix create_mydir_hierarchy to save dir
- Mark the dentries dirty so they get saved to disk (they're not journaled!).
This fixes rstat problems on startup, whe... - 06:12 PM Revision 43d74721 (ceph): mds: reset dirty->flushing on rejoin scatterflush
- Reset dirty/flushing state during rejoin.
Signed-off-by: Sage Weil <sage@newdream.net> - 06:12 PM Revision c9872a44 (ceph): mds: send any dirty scatterlock state on rejoin
- Not just inodes for auth dirfrags, but for any inode with dirty scatterlock
state. Include the root inode.
Signed-o... - 06:12 PM Revision c7f9d2f9 (ceph): mds: clear flush state on rejoin ack
- If we sent scatterlock state during rejoin, the auth will send us an inode
base. Clear scatterlock flush state if th... - 06:12 PM Revision bc98fe7e (ceph): mds: improve scatterlog debug msg
- 06:12 PM Revision 2a1af8b8 (ceph): mds: drop debugging cruft
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 06:12 PM Revision 0f10e954 (ceph): mds: make _create_system_file dirty dentries properly
- Properly dirty the new dentries so they get written to the directory
objects later on.
Signed-off-by: Sage Weil <sag... - 06:12 PM Revision 31fc9edb (ceph): mds: fix create_mydir_hierarchy to save dir
- Mark the dentries dirty so they get saved to disk (they're not journaled!).
This fixes rstat problems on startup, whe... - 06:06 PM Bug #997 (Won't Fix): qemu-iotest 016 fails for rbd
- We're skipping this test instead of being growable by writing to a larger offset than our size.
- 06:05 PM Bug #998 (Can't reproduce): qemu/librbd race conditon
- Stefan had no core file, and neither he nor I could subsequently reproduce this.
- 05:55 PM Revision f4d86777 (ceph): radosacl: read Ceph configuration file
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 05:24 PM rgw Bug #985: radosgw listing keys of a bucket with name >=251 characters fails with NoSuchKey
- this is related to #963
- 03:07 PM rgw Bug #985: radosgw listing keys of a bucket with name >=251 characters fails with NoSuchKey
- This is a problem with long pool names in the Object Storage layer....
- 04:40 PM Revision ceba04f4 (ceph): cephtool: don't print anything on SIGTERM, SIGINT
- Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
- 03:00 PM Bug #1001: dead mds remains up, won't let others take over
- mds went from up:replay to up:standby-replay:...
- 01:17 PM Bug #1001 (In Progress): dead mds remains up, won't let others take over
- 01:15 PM Bug #1001: dead mds remains up, won't let others take over
- All 3 nodes were running 0.26 plus stable patches c494689062c9, plus a patch that relaxes the journaler _trim_finish ...
- 01:09 PM Bug #1001 (Resolved): dead mds remains up, won't let others take over
- 3-node cluster, with 3 mons, 3 mdses (all configured for standby-replay), 3 osdes (but node 0 down, because I'm using...
- 01:16 PM CephFS Bug #966 (Can't reproduce): mds: scatterstat error
- Can't reproduce this one. Maybe it was resolved by commit:466306de3aeca22311993bf5a1955281499d751d.. or something ear...
- 01:06 PM CephFS Bug #933 (Can't reproduce): mds: standby-replay incorrectly probed journal for live mds
- i give up! maybe this was triggered prior to the WR flag being set during filer probe.
- 11:38 AM Bug #1000 (Closed): osd: PG::replay_queued_ops
- Uh, my bad, this is a duplicate of #990.
- 10:16 AM Bug #1000: osd: PG::replay_queued_ops
- Likely caused by handle_pg_notify calling do_peer on an active pg.
- 10:01 AM Bug #1000 (Closed): osd: PG::replay_queued_ops
- On my cluster (40 OSD's) I'm seeing multiple OSD's going down with this backtrace:...
- 11:34 AM Bug #802 (Closed): osd: failing to send heartbeats (btrfs hang?)
- We're chalking this up to insufficient CPU to handle all of the threads. There are some tricks we could play (bumpin...
- 11:33 AM CephFS Bug #637 (Resolved): mds: check replica scatterlock flush on rejoin
- fixed by commit:c7f9d2f9a8607d1147c4ee49f8fb565fde2f3278 and prior commits.
- 11:23 AM rbd Bug #944 (Duplicate): rbd snapshots not exposed as read-only
- Forgot about this ticket - it was fixed in #927.
- 10:35 AM rgw Bug #983: radosgw hangs, gives 500 internal server
- I reproduced this. I'm still trying to figure out why this happened. Best guess so far is a timeout on the Rados end ...
- 09:47 AM Bug #993 (Resolved): ceph -w whines on quit
- Resolved by commit:ceba04f4dde5b6538ddc648af740575090a9bf60
- 09:45 AM Bug #881 (Resolved): confutils: memory leaks
- I don't see any obvious way to get valgrind to stop warning about these "potential leaks" which are not leaks at all....
- 04:09 AM Revision 21df0427 (ceph): mds: don't crash on bad export_dir command
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 04:09 AM Revision fb8c09b0 (ceph): mds: fix file_eval on subtree roots
- We were going from mix->sync when we shouldn't. Fix mis-coded filelock
and look at _lock_ state, not inode's!
Signe...
04/11/2011
- 11:30 PM Revision 1f23a229 (ceph): Merge remote branch 'origin/dead-code'
- 11:24 PM Revision 60b645e5 (ceph): osd: fix race in op enqueuing
- This is never really exposed except when op_threads == 0.
Signed-off-by: Sage Weil <sage@newdream.net> - 11:24 PM Revision 6768586c (ceph): osd: take reference for RepModify
- We put in the completions on done; take the matching reference.
Signed-off-by: Sage Weil <sage@newdream.net> - 11:24 PM Revision 7ca69ebe (ceph): osd: fix ref leak on pg when queueing
- op_wq.queue() takes a ref; don't take one here too. We were leaking like
crazy.
Signed-off-by: Sage Weil <sage@newd... - 09:23 PM rbd Bug #944: rbd snapshots not exposed as read-only
- was this fixed already? i forget!
- 09:23 PM Tasks #895 (Resolved): make backlogs charts work
- 09:18 PM rgw Bug #999: Duplicate Bucket Created
- i recently changed the creation code some. and see also #978.
- 05:38 PM rgw Bug #999 (Resolved): Duplicate Bucket Created
- I think I managed to created a bucket called 'foobuckat' on both my account (webid matwod) and Sage's account. I thi...
- 06:43 PM Bug #989: rstats and fragstat messages in mds logs
- The log file up until a ways after the first check_rstats problem was just over 5MB, so I split it up here such that ...
- 11:35 AM Bug #989: rstats and fragstat messages in mds logs
- Okay. An old filesystem wouldn't have explained the negative rstats anyway.
Let me know what you come up with! - 11:12 AM Bug #989: rstats and fragstat messages in mds logs
- Every test I run is on a freshly installed cluster.
We've automated all the underlying stuff such that it's pretty q... - 11:09 AM Bug #989: rstats and fragstat messages in mds logs
- Well the MDS directory is a permanent thing -- once it's broken it's going to stay broken. Ideally we'd reproduce wit...
- 10:59 AM Bug #989: rstats and fragstat messages in mds logs
- This may be something popping out of the MDS changes intended for NFS support (inode lookup).
I'm going to retest by... - 09:11 AM Bug #989: rstats and fragstat messages in mds logs
- The more I look at this the less sense it makes. The only things in the mds dir are the journal and the stray dirs. Y...
- 05:37 PM Bug #993: ceph -w whines on quit
- I guess it's ugly that it echoes it twice. In general, we probably don't need to blast the message out to every possi...
- 04:45 PM Revision eacfb8d3 (ceph): TestSnaps: Fix compile error
- Introduced in 0e371de79e4047b92317dee353f6d75c2aba4260.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> - 04:43 PM Revision cc5dd6d6 (ceph): mon: simplify osd health output
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 04:36 PM Revision 9c0d42fe (ceph): osd: only log scrub errors (not ok's)
- Otherwise we fill up the error log with "foo is ok!" messages.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 03:22 PM Linux kernel client Feature #448 (Rejected): support dns resolution in libceph
- 03:22 PM Linux kernel client Feature #448: support dns resolution in libceph
- Indeed, that's the plan: #958
- 03:15 PM Linux kernel client Feature #448: support dns resolution in libceph
- How about writing a userspace wrapper for that echo >/sys, instead? There's no reason for this functionality to be in...
- 03:13 PM Bug #998 (Resolved): qemu/librbd race conditon
- As reported in http://marc.info/?l=kvm&m=130225223223016&w=2:
There's a race condition that sometimes causes aio_r... - 03:11 PM Bug #997 (Won't Fix): qemu-iotest 016 fails for rbd
- This test treats an rbd image as a 'growable' block device, which will accept reads and writes at large offsets and r...
- 02:43 PM Feature #745 (Resolved): qa: radosgw tests
- 01:19 PM Bug #906: clustered mds: lchown not setting uid/gid
- Re-running as job 409, clocks are in decent sync:...
- 11:42 AM Bug #931 (Resolved): opening up security. xattr
- Believe the patch from last week fixed this.
04/10/2011
- 09:28 AM Bug #996: osd: ReplicatedPG::do_osd_ops
- The OSD code was briefly broken last week -- it looks like you managed to pull down a bad one. Get the latest master ...
- 01:32 AM Bug #996 (Can't reproduce): osd: ReplicatedPG::do_osd_ops
- I had an issue that my cluster would not recover, spoke with joshd about this on IRC ( http://irclogs.ceph.widodh.nl/...
Also available in: Atom