Project

General

Profile

Activity

From 06/01/2010 to 06/30/2010

06/30/2010

11:10 PM Revision 1bd46c04 (ceph): client: set MetaRequest::inode to the inode or directory inode whenever...
Provides link to caps, useful when requests come back ESTALE or similar. Greg Farnum
11:10 PM Revision e5b60faa (ceph): client: set inode/dentry fields where available
Greg Farnum
11:10 PM Revision beeb08bb (ceph): client: remove now-unused authority and pick_replica functions
Greg Farnum
11:08 PM Revision fa62e9db (ceph): client: rewrite choose_target_mds to more closely mirror kclient logic ...
Greg Farnum
11:08 PM Revision 60f2672e (ceph): client: add mds_num to MDSSession struct
Greg Farnum
11:08 PM Revision 39796b47 (ceph): client: make fragmap updates a little more space efficient.
If the auth is the same as the parent, don't add to the map (and remove if
it's already there). Absence is interprete...
Greg Farnum
11:06 PM Revision bfd335c2 (ceph): rbd: some header cleanup
Yehuda Sadeh
11:06 PM Revision 18c305ab (ceph): qa: set runoncfuse.sh to run cfuse in background and kill at end of tests.
This is an imperfect solution at best, since it doesn't handle errors at all,
but it'll have to do for now.
Greg Farnum
11:06 PM Revision abd26eea (ceph): client: initialize auth_caps in Inode! Prevents bad pointer derefs.
Greg Farnum
11:06 PM Revision 194986a3 (ceph): client: remove Inode::dir_auth data member
Greg Farnum
11:06 PM Revision 060d22d0 (ceph): client: remove dead code
Greg Farnum
11:06 PM Revision 4f2f78dd (ceph): client: move all mds selection code into choose_target_mds
Greg Farnum
11:06 PM Revision 0992001c (ceph): client: clean up Inode::authority
Greg Farnum
11:06 PM Revision 77a1664a (ceph): rbdtool: implement snap rollback
Yehuda Sadeh
10:44 PM Revision 2fdd43e7 (ceph): buffer: handle write_fd() on empty bufferlist
Sage Weil
09:53 PM Linux kernel client Cleanup #233 (Resolved): replace mount option fsid{major,minor} with fsid=<string>
Sage Weil
09:40 PM Revision 8410e6a6 (ceph): osd: fix, cleanup ack/disk reply logic
There was a bug where we would get no reply if we could send ondisk but
the client didn't want it. This simplifies a...
Sage Weil
09:18 PM Revision aa30dd18 (ceph): buffer: make write_fd() tolerate zero length ptrs in the bufferlist
Sage Weil
07:09 PM Revision 3235abe9 (ceph): msgr: clean up aborted message handling
No need for a dummy message. Make the (single) caller handle returning
no message as a non-error.
Signed-off-by: Sa...
Sage Weil
07:09 PM Revision 7cedafd3 (ceph): msgr: release bytes reserved from throttlers in failure paths
If we don't release those bytes, the throttler count eventually fills up
with bytes we were going to read but didn't ...
Sage Weil
06:14 PM Revision 3c80b9da (ceph): uclient: rename make_path; cleanup/move make_request_from_Meta
Document, make it clear what kind of "path" it's really building.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil
05:32 PM Revision e76ce441 (ceph): man: add man pages for cclass and cclsinfo
Yehuda Sadeh
04:44 PM CephFS Tasks #237 (Resolved): cfuse: run through full qa suite
It's not perfect, but the runoncfuse.sh script is in the repository and now runs cfuse in the background, then kills ... Greg Farnum
04:41 PM CephFS Bug #232 (Resolved): ESTALE on many copies
Done by 1bd46c0480b2d6b120773b4b122de6cd68861778, along with a number of other issues. Greg Farnum
03:52 PM Bug #222 (Resolved): add rollback/revert to rbdtool
Yehuda Sadeh
03:52 PM Bug #222: add rollback/revert to rbdtool
Implemented, commit 77a1664af6ef988c9da7d401fc592043d9bfb4ef. Yehuda Sadeh
03:44 PM Bug #243 (Resolved): Need to be able to mark certain class methods as public
Some class methods need to be public, that is they don't need the execution cap in order to execute. We need to be ab... Yehuda Sadeh
03:40 PM rbd Bug #240 (Resolved): update qemu rbd to use block names
Functionality added, commit 989d1db651aef18aec6c6826dc36cf54ef4615ea. Yehuda Sadeh
03:34 PM Revision 2f9ea76f (ceph): filejournal: fix buffer realignment condition; useful debug output on e...
We don't care about contiguous, only about page alignment. Sage Weil
03:30 PM Feature #242 (Rejected): fuse rbd driver
maybe something like,... Sage Weil
12:23 PM Linux kernel client Bug #226: kclient can hang waiting for snap caps
reliably triggered on sepia/ceph nodes with qa/workunits/untar_snap_rm.sh Sage Weil
11:03 AM CephFS Bug #241 (Resolved): cfuse: make sure fsync does the right thing; remove warning
> "10.06.30_13:16:20.556187 7f2bc5817720 client4100 fsync - not syncing
> metadata yet.. implement me"
Sage Weil
11:01 AM CephFS Bug #229 (Resolved): cfuse freezes
Sage Weil
06:01 AM CephFS Bug #229: cfuse freezes
As promised I tested this a lot (approx 5 full reformat, approx 40 rounds of cp -a; chown -R), and could not reproduc... ar Fred
10:21 AM Bug #239 (Resolved): create man pages for cclass and cclsinfo
Done, commit e76ce441314bced42a02a140d15db30d2bd26eb0. Yehuda Sadeh
05:58 AM Revision 134a0d0f (ceph): rbdtool: fix uninitialized variable
Yehuda Sadeh
12:23 AM Revision 015faa88 (ceph): config: update __isarg before reading config param
Yehuda Sadeh
12:23 AM Revision 06279651 (ceph): rbdtool: implement rename
Yehuda Sadeh

06/29/2010

11:25 PM Revision 4d9f49a7 (ceph): debian: include cclsinfo
Sage Weil
11:23 PM Revision 013f9e52 (ceph): Makefile: include cclsinfo; lose the old .cc
Sage Weil
11:08 PM Revision 0812b8f4 (ceph): Makefile: include cclass.in in dist
Sage Weil
11:00 PM Revision 0f4ddbac (ceph): cls: cls_read, cls_cxx_read return the number of bytes read
Yehuda Sadeh
11:00 PM Revision c9930900 (ceph): cclass.in: LIBDIR=.libs in certain cases
Yehuda Sadeh
11:00 PM Revision 96b1db80 (ceph): rbdtool: init rbd block id, later will be used for rename
Yehuda Sadeh
11:00 PM Revision f9dc4b90 (ceph): buffer: write_fd should skip empty buffers
Yehuda Sadeh
09:40 PM Revision 2ec729d1 (ceph): config: use <<20 for MB
Sage Weil
09:40 PM Revision fcc39c81 (ceph): msgr: use dedicated reaper thread
We were calling the reaper from the wait() loop. The problem is that
the OSD has two messengers, and only the first ...
Sage Weil
09:40 PM Revision 2df8b9fd (ceph): script/plot.pl: don't pause
Run like so:
$ script/plot.pl path/to/log osd c_wrb [smooth bezier] | gnuplot -persist
Sage Weil
09:38 PM Revision 3e334024 (ceph): osd: removed unused RepGather::indata
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
09:38 PM Revision 852ab94a (ceph): osd: change write osd logging timing
Sage Weil
09:32 PM Revision 419bd914 (ceph): osd: always use original Connection when replying
...even when the op came from another OSD. Not that that should happen
anyway, since we don't forward messages curre...
Sage Weil
09:31 PM Revision def4b40e (ceph): osd: always include osd op result, result code in the first reply
Sage Weil
09:21 PM Revision ff8df7dc (ceph): osd: add 'logger reset' command
Sage Weil
09:21 PM Revision e85d98ba (ceph): osd: track open repops in logger
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
09:21 PM Revision fc1d1665 (ceph): journal: set max journal write to 10MB
If we take too big a bite of data to write in a single writev(2), we can
end up making performance worse, because eve...
Sage Weil
05:19 PM rbd Bug #240 (Resolved): update qemu rbd to use block names
Just had an on-disk header format change that decouples the block names from the rbd image names. Should fix qemu-rbd... Yehuda Sadeh
05:16 PM Bug #224: rbdtool copy / rename
rename implemented at 0627965198ddd8a0c9af458e15b4da1a8a645b42. Yehuda Sadeh
05:14 PM Bug #239 (Resolved): create man pages for cclass and cclsinfo
Yehuda Sadeh
04:59 PM Revision 1d517986 (ceph): conf: fix parsing when there's no eol at the end of file
Yehuda Sadeh
04:06 PM CephFS Feature #238 (Resolved): cfuse: log to file if run as daemon
e.g. /var/log/ceph/cfuse.$pid, with client12312 symlink
You can always run in the foreground (f) and log to stdout...
Sage Weil
04:02 PM CephFS Tasks #237 (Resolved): cfuse: run through full qa suite
Is there a script in qa/ already to do this? If not, let's add one. Sage Weil
04:01 PM CephFS Cleanup #236 (Resolved): cfuse: clean up mds session handling
- mds session map should probably map to pointers (MDSSession*)
- realign code with kclient behavior, starting with ...
Sage Weil
03:59 PM CephFS Feature #235 (Resolved): cfuse: allow specifying server path to mount on command line
Sage Weil
03:34 PM Revision d9dc7cb5 (ceph): msg: fix entity_addr_t::parse() to return false on failure
Sage Weil
03:22 PM Revision 0cb7a71c (ceph): mkcephfs: Fix wrong maxosd when OSD ids are random ordered in ceph.conf
Hi
I got a trouble that mkcephfs will have wrong "maxosd" when you have
ceph.conf with OSD ids in random order like:...
CC Lien
09:41 AM Bug #234 (Resolved): conf: skips last line if there's no newline
fixed by 1d517986a87e89a281eb1529e72add72f9de7e93 Yehuda Sadeh
09:34 AM CephFS Bug #153 (Resolved): mds: fix snap dentry replication vs readdir on frag auth
This was resolved back in commit:c4bbb0008b2b6dd2a8d377a5c6424592221ca846 Sage Weil
09:24 AM Bug #202 (Can't reproduce): OSD crash during reads from cluster
Sage Weil
09:24 AM Bug #202 (Closed): OSD crash during reads from cluster
I'm going to close this.. not much to be done without a stack trace or more specific information. If it comes up aga... Sage Weil

06/28/2010

07:18 PM Linux kernel client Bug #227: caps flush races with caps export
There are multiple issues, one is that if we have pending caps on old session, we need to flush those caps in the new... Yehuda Sadeh
06:34 PM Revision 50f254d0 (ceph): filejournal: fix journal write_pos advance
This was broken by bd4188a02abff9efffb87a0a2031efe51c1b4d9a. @pos needs to
be advanced (it is pass by reference) or ...
Sage Weil
04:57 PM Revision d9554d5d (ceph): mount.ceph: update mount options
Signed-off-by: Thomas Mueller <thomas@chaschperli.ch>
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil
11:46 AM CephFS Bug #232: ESTALE on many copies
So this is happening when the client tries to create and open a new directory after the parent directory's auth mds h... Greg Farnum
10:29 AM Bug #234 (Resolved): conf: skips last line if there's no newline
conf parser should tolerate a missing newline on the last line. Sage Weil
09:49 AM Linux kernel client Cleanup #233 (Resolved): replace mount option fsid{major,minor} with fsid=<string>
Sage Weil

06/26/2010

08:34 PM Bug #199 (Closed): OSD crash when rebalancing data
I can't verify because the stack traces have no symbols, but I'm going to guess this is the same crush map update iss... Sage Weil
05:29 PM Revision 6bae200b (ceph): msgr: fix throttle deadlock
Do msgr throttle after peer policy throttle. The msgr (dispatch) throttle
is shortlived and won't deadlock (unless d...
Sage Weil
04:47 AM Revision 59b114a0 (ceph): crush: fix "in" threshold to be 1.0, not 0.1
We were effectively counting any item with weight > .1 to be weight 1.0. Sage Weil
04:47 AM Revision 928512ff (ceph): crushtool: add simple test function
Sage Weil
04:47 AM Revision 8f2731bc (ceph): crushwrapper: gracefully handle crush error
crush_do_rule can return <0 in certain error cases (e.g., forcefed device
does not exist in crush map). We should ta...
Sage Weil

06/25/2010

11:10 PM Revision 19b4a5ff (ceph): cfuse: remove some NPEs with ESTALE from MDSes.
Under certain circumstances this continues to let you get ESTALE
and not handle it, but those are still being analyze...
Greg Farnum
10:00 PM Bug #230 (Resolved): OSD crash when injecting new CRUSH map
This was a problem with teh CrushWrapper error handling (the error was due to a forcefed device no longer existing in... Sage Weil
11:12 AM Bug #230 (Resolved): OSD crash when injecting new CRUSH map
I just wanted to take out a few OSD's since their performance was lacking, doing so took 50% of the OSD's down.
Th...
Wido den Hollander
04:14 PM CephFS Bug #232 (Resolved): ESTALE on many copies
Discovered while exploring #229.
To reproduce:
Start up a multi-mds system in ceph dir.
Mount ceph with cfuse.
Co...
Greg Farnum
11:52 AM CephFS Bug #229: cfuse freezes
yes, unstable from a few days ago: bf3d52a4b725a0f2d3db39ea9ad5b412171ea0ad 2010-06-20 23:41:19 ar Fred
09:27 AM CephFS Bug #229: cfuse freezes
Is this the unstable branch of ceph.git? Sage Weil
03:31 AM CephFS Bug #229 (Resolved): cfuse freezes
I can mount a ceph fs using cfuse, but not a lot more:
As a first test, I tried to cp -a the ceph working dir (inclu...
ar Fred
11:22 AM Feature #231 (Rejected): Slow OSDs shouldn't destroy cluster performance
Wido was testing on an 8-OSD cluster and getting only ~25MB/s out of Ceph. Running OSD self tests revealed that a num... Greg Farnum
11:08 AM CephFS Bug #219 (Resolved): Client doesn't properly flush snapshots
Hurrah, looks like Sage's MDS fixes got this working properly. At least I can't reproduce it again. Greg Farnum

06/24/2010

11:49 PM Revision 9795fabb (ceph): mds: fix client cap condition
In 551a12f52e36 we fixed a bug with cow_inode() where the
cap->client_follows didn't match last precisely. Instead, ...
Sage Weil
11:49 PM Revision eeede270 (ceph): qa: read recently written/deleted data back from snap
Sage Weil
11:49 PM Revision bef06294 (ceph): mds: keep cap follows above in->first in FLUSHSNAP
The client has a follows of 0 initially, which is correct (it does follow
0, and there are no prior snaps). But the ...
Sage Weil
09:45 PM Bug #114 (Resolved): osd: corrupted pglog
I'm going to chalk this one up to #212. Sage Weil
06:51 PM Revision 478fe723 (ceph): ceph_fs: add CEPH_LOCK_IFLOCK so its inclusion elsewhere continues to b...
Greg Farnum
06:37 PM Revision 62827156 (ceph): mds: add IFLOCK to wait bits to prevent collisions with lock branch
Greg Farnum
05:42 PM Revision 7ce03386 (ceph): crush: fix recursion through intervening types
This fixes pretty core behavior when doing recursion down the tree. I
suspect it was broken when changing the retry ...
Sage Weil
05:40 PM Revision 241d011f (ceph): crush: make CHOOSE_LEAF to behave when leaf type is encountered
We may not want to recursively call crush_choose() if we start out with a
leaf. If that happens, we need to fill out...
Sage Weil
05:39 PM Revision 8f7df4ed (ceph): client: resync with kernel's ioctl.h
This got munged up by the #ifndef/#define guard cleanup. Sage Weil
05:39 PM Revision 07cfbad8 (ceph): mds: fix SimpleLock wait_shift()
DVERSION was missing, others were overlapping... Sage Weil
05:02 PM Linux kernel client Bug #221 (Resolved): Deleting files can cause empty snapshots of them
This is fixed by commit:9795fabb63f6b6b291c1054ca578b213a6a0bf83 and commit:bef062942ad1745808287c7483478adaa0b91fc2 ... Sage Weil
11:21 AM RADOS Feature #228 (Resolved): crush unit tests
We need to set up some crush unit tests.
Need to test basic maps, some more complex hierarchies, some failure case...
Sage Weil
10:08 AM Linux kernel client Bug #227 (Resolved): caps flush races with caps export
This leads to sync hanging.
relevant log on the client side:
Jun 23 23:54:58 uml kernel: [ 482.100000] ceph: ...
Yehuda Sadeh
09:54 AM Linux kernel client Bug #226 (Resolved): kclient can hang waiting for snap caps
... Sage Weil

06/23/2010

11:35 PM Revision 5634ce8d (ceph): ceph_fs: add CEPH_FEATURE_FLOCK to ceph_fs so its bit doesn't get cover...
Greg Farnum
09:12 PM Revision 58f4dceb (ceph): osdmap: negative osd ids do not exist
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
09:08 PM Revision b7ad8aa9 (ceph): crush: behave when chooseleaf is given leaf type
Fill in the out2 choose_leaf vector if it's defined. This is necessary
because we may not recursively call choose on...
Sage Weil
05:30 PM Linux kernel client Feature #23: fcntl/flock advisory lock support
Hmm, this was halfway done before but it's in properly now. Greg Farnum
01:24 PM Linux kernel client Feature #23: fcntl/flock advisory lock support
BTW these should all be __le32 etc. if the values go over the wire. And the kclient code that uses them needs to use... Sage Weil
04:38 PM Linux kernel client Bug #218 (Resolved): fix estale handling to look at auth cap migrate_seq
Should be fixed in bc863c3207c216fb245fda06cd6bf19c6940ad0e. Instead of maintaing a count of stale replies, it switch... Greg Farnum
04:32 PM Bug #225 (Resolved): rbdtool import / export
Import/export a volume from/to a file.
Pay attention to holes. On export, seek past holes to create a sparse file...
Sage Weil
04:28 PM Bug #224: rbdtool copy / rename
Shouldn't be too hard to implement copy. Rename is a bit tricky -- basically we'd need to copy and erase -- unless we... Yehuda Sadeh
04:19 PM Bug #224 (Resolved): rbdtool copy / rename
It'd be helpful to be able to copy and/or rename rbd volumes. Andrew F
01:20 PM Cleanup #223 (Resolved): msgr: move supported/required feature bits out of ceph_fs.h, into cosd/c...
The current msgr logic has a different required depending on the peer type.. a mon talking to an osd will require som... Sage Weil
10:55 AM Linux kernel client Bug #220 (Resolved): oops on add
Yehuda Sadeh

06/22/2010

09:11 PM Revision 364521ac (ceph): mds: handle_export_caps, copy cap_import map (instead of swap content)
This fixes #200. The client_map is later on swapped again in the new ESession(),
which left finish->client_map empty.
Yehuda Sadeh
04:53 PM Linux kernel client Bug #220: oops on add
This was already fixed previously at commit e95e9a7ae4c1e7655a0438579f891b3c60178d77. Should be corrected once the st... Yehuda Sadeh
03:49 PM Linux kernel client Bug #220 (Resolved): oops on add
... Andrew F
04:19 PM Bug #222 (Resolved): add rollback/revert to rbdtool
Sage Weil
04:14 PM Linux kernel client Bug #221 (Resolved): Deleting files can cause empty snapshots of them
Fairly simple test case, although it's possible a smaller one would work too
mount -t ceph xxx mnt/
mkdir mnt/a
mk...
Greg Farnum
04:11 PM Linux kernel client Bug #218: fix estale handling to look at auth cap migrate_seq
This is taking more time than I expected since I'm running into some other issues with my test case. I think I have i... Greg Farnum
11:00 AM Linux kernel client Bug #218 (In Progress): fix estale handling to look at auth cap migrate_seq
Greg Farnum
02:11 PM Linux kernel client Bug #200 (Resolved): umount hangs with clustered mds
Fixed by 364521acb070ab60540f869f4ccd79b468c3d9b0. Yehuda Sadeh
11:00 AM Bug #215 (Resolved): osd crash: FAILED assert(seq >= last_committed_seq)
Sage Weil
01:42 AM Bug #215: osd crash: FAILED assert(seq >= last_committed_seq)
I'm attaching the commit_op_seq file, as the content is not what I was expecting, it indeed has a 0 in it, but it als... ar Fred
09:25 AM CephFS Feature #45 (Closed): Investigate adding Connection * to mds Session
This got pulled into unstable a while ago. Greg Farnum

06/21/2010

11:27 PM Revision 43a7ec4c (ceph): client: properly handle ESTALE by redirecting to auth MDS
Greg Farnum
11:27 PM Revision c89afb4c (ceph): client: don't send cap snap message to MDS if not dirty or writing.
From Sage. Greg Farnum
06:43 PM Revision 027b6c3e (ceph): rados: more descriptive ls usage failure, stdout set implicitly
Yehuda Sadeh
06:35 PM Revision 2cd04f47 (ceph): mds: rename handle_client_opent
Sage Weil
06:35 PM Revision 2e73f737 (ceph): mds: only acquire_locks once in handle_client_open
Subsequent calls will just return with 'already locked' Sage Weil
06:27 PM Revision 4d86180e (ceph): rbdtool: fix --list
Yehuda Sadeh
05:36 PM Revision 90511120 (ceph): osd: fix incorrect logic check on fsid comparison
Greg Farnum
04:46 PM Revision 9bbeec47 (ceph): osd: Warn and shutdown on a mismatched fsid, instead of failing an assert
Greg Farnum
04:38 PM Linux kernel client Bug #217 (Resolved): client needs to open sessions to mds export targets
Sage Weil
12:43 PM Linux kernel client Bug #217 (Resolved): client needs to open sessions to mds export targets
Sage Weil
04:36 PM CephFS Bug #211 (Resolved): Cfuse won't unmount properly with snapshot activity
Well, fixed the immediate problem in c89afb4c8b526dbd86e53b6fafb221a82749bf88.
But there are many issues with snapsh...
Greg Farnum
04:36 PM CephFS Bug #219 (Resolved): Client doesn't properly flush snapshots
Perform the steps in #188. Depending on how long you take, it'll hang when you try to read the file.
This can be mit...
Greg Farnum
04:26 PM Bug #208 (Resolved): Can't create snapshots in cfuse on mds cluster
Fixed in 43a7ec4c88e5367a6f8faef175e86859b286ae8a Greg Farnum
04:13 PM Linux kernel client Bug #189: leaked dentry
Sage Weil wrote:
> this is fixed by commit:01048745dd99bfc21d4e38863ec86597185e57d7
simpler fix in commit:17c688c...
Sage Weil
04:05 PM Linux kernel client Bug #189 (Resolved): leaked dentry
this is fixed by commit:01048745dd99bfc21d4e38863ec86597185e57d7 Sage Weil
04:05 PM Linux kernel client Bug #216: splice_dentry error
Sage Weil wrote:
> we shouldn't crash when splice_dentry fails. fixed by commit:61671a81b82e414b0b4e81ce1282a9b92e4...
Sage Weil
10:43 AM Linux kernel client Bug #216 (In Progress): splice_dentry error
Sage Weil
10:43 AM Linux kernel client Bug #216: splice_dentry error
we shouldn't crash when splice_dentry fails. fixed by commit:61671a81b82e414b0b4e81ce1282a9b92e4834b6
as for why ...
Sage Weil
09:12 AM Linux kernel client Bug #216 (Resolved): splice_dentry error
since 2 days 1 of my tests fail and crash my machine.
the script crashing the machine is:
http://github.com/vinz...
Sage Weil
03:33 PM Revision c9af6def (ceph): add helptext for option "snapdirname" to manpage of mount.ceph
[ The following text is in the "UTF-8" character set. ]
[ Your display is set for the "iso-8859-1" character set....
Thomas Mueller
03:07 PM Linux kernel client Bug #218 (Resolved): fix estale handling to look at auth cap migrate_seq
Sage Weil
11:07 AM Linux kernel client Bug #144 (Can't reproduce): GPF at con_close_socket+0x40/0x9f
Sage Weil
11:07 AM Linux kernel client Bug #162 (Can't reproduce): list bug during shrink_dcache_for_umount
Sage Weil
10:57 AM Linux kernel client Feature #206: make a 'soft' mode
the problem is that umount session close stage _does_ actually time out already (same timeout as mount), but the 'flu... Sage Weil
10:56 AM Bug #215: osd crash: FAILED assert(seq >= last_committed_seq)
Oh.. it may have written the bad (0) value to current/commit_op_seq. Can you confirm that file has 0 in it? If so, ... Sage Weil
05:40 AM Bug #215: osd crash: FAILED assert(seq >= last_committed_seq)
I got a crash after restarting that osd, same stacktrace (if you ignore line numbers difference due to your recent co... ar Fred
10:51 AM Linux kernel client Bug #210 (In Progress): GPF in ceph_con_revoke_message+0x2c/0x152
Sage Weil
10:29 AM Linux kernel client Bug #210: GPF in ceph_con_revoke_message+0x2c/0x152
r12 is 5a5a5a.., on this code... Sage Weil
09:44 AM Bug #214 (Resolved): don't fail on assertion when mkcephfs is mis-used
OSD will now warn to log and shutdown on a bad fsid. (Map updates can only come from trusted sources, so if it gets a... Greg Farnum

06/20/2010

09:41 PM Revision bf3d52a4 (ceph): journal: initialize applied_seq during journal replay
This should avoid
#0 0x00007f41b1a18a75 in raise () from /lib/libc.so.6
#1 0x00007f41b1a1c5c0 in abort () from /li...
Sage Weil
04:45 PM Revision 2540ea48 (ceph): mkcephfs: push conf to remote machines
Signed-off-by: Fred Ar <ar.fred@yahoo.com>
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil
04:44 PM Revision 3bfabd41 (ceph): mon: allow 10ms clock drift before complaining
Sage Weil
02:53 PM Bug #215: osd crash: FAILED assert(seq >= last_committed_seq)
this should be fixed by commit:bf3d52a4b725a0f2d3db39ea9ad5b412171ea0ad... can you please confirm?
thanks!
Sage Weil
10:39 AM Bug #215 (Resolved): osd crash: FAILED assert(seq >= last_committed_seq)
this is ceph unstable c626ac384678661b765c1ae1dee8db48b2c70993... ar Fred
10:34 AM Bug #214: don't fail on assertion when mkcephfs is mis-used
handle_osd_map should log an error and return if the fsid doesn't match Sage Weil
09:37 AM Bug #214 (Resolved): don't fail on assertion when mkcephfs is mis-used
3 boxes, each with 1 mon 1 mds 1 osd
I wanted a clean base for further testing, so on each boxes, I did a:...
ar Fred

06/19/2010

03:41 PM Revision 775506e9 (ceph): debian: include cclass
ar Fred
03:40 PM Revision d4173fa7 (ceph): initscript: fix for dash
Signed-off-by: Fred Ar <ar.fred@yahoo.com> ar Fred
03:39 PM Revision 1f2725bc (ceph): cclass: fix for dash
Signed-off-by: Fred Ar <ar.fred@yahoo.com> ar Fred
08:30 AM Bug #213 (Resolved): non-idempotent transactions (clone) under ext3 may not replay correct result
The writeahead journaling will restore the store to a known state regardless of which operations have committed, but ... Sage Weil
04:26 AM Revision 6d833475 (ceph): initscript: remove class loading for now
- only need to do it once, by connecting to a random monitor, not for
each monitor
- not sure we should try it ever...
Sage Weil
02:12 AM Revision b3dc5ecf (ceph): vstart: only need to load classes once, not for each monitor
Sage Weil

06/18/2010

11:32 PM Revision c626ac38 (ceph): Merge branch 'rbd-class' into unstable
Sage Weil
11:31 PM Revision 3a2c9169 (ceph): Revert "class: able to add classes when doing mkfs"
This reverts commit 65371482dd661c6dc3d251fb9fd4e01812bdaa0e. Sage Weil
10:59 PM Revision fb1ad6e7 (ceph): filestore: op_start when op is _queued_, so that q is drained on commit
We need the store in a consistent state on commit, which means flushing
transactions such that we have all ops <= a g...
Sage Weil
10:09 PM Revision 6a261eb1 (ceph): journal: maintain applied_seq, use that value during the commit.
Track which seq's have successfully applied.
This fixes writeahead mode. Parallel mode is still broken...
Sage Weil
09:30 PM Revision ed768c9a (ceph): buffer: fix includes for writev/iovec stuff in write_fd()
Sage Weil
09:09 PM Revision a3e906e3 (ceph): filestore: make sync() and friends actually sync!
Sage Weil
08:56 PM Revision ae90ba18 (ceph): initscripts: fix verbose output for root commands
Sage Weil
08:06 PM Revision 10d41d2c (ceph): filejournal: only pad to align for data segments above 64 KB
Sage Weil
08:00 PM Revision f98c0b4f (ceph): filejournal: make alignment optional (<0 == no preferred alignment)
Sage Weil
07:49 PM Revision 2be1480a (ceph): Merge branch 'unstable' of ceph.newdream.net:git/ceph into unstable
Sage Weil
07:48 PM Revision 3fbc2a2a (ceph): buffer: remove debug cruft
Sage Weil
07:47 PM Revision d1626090 (ceph): filejournal: pad entries on disk based on preferred alignment
Adjust pre/post padding to align entry payload with it's preferred
alignment.
Sage Weil
07:46 PM Revision f59d77be (ceph): objectstore: track offset, alignment of largest data segment [encoding ...
Sage Weil
07:44 PM Revision 0995f28f (ceph): buffer: list::rebuild_page_aligned()
Rebuild bufferlist such that all segments/ptrs are page sized/aligned.
(Avoids copying/reallocating segments that are...
Sage Weil
06:38 PM Revision 25116b27 (ceph): client: if checking caps on a snap, return, don't assert
Greg Farnum
05:10 PM Revision bd4188a0 (ceph): filejournal: use buffer::write_fd() instead of open coding
Avoid dup code, and also handle short writes. Sage Weil
04:40 PM Revision ca9b7563 (ceph): osd: implement bench command
'bench [bsize] [total bytes]'
Result is reported via logclient.
Sage Weil
04:24 PM Bug #212 (Resolved): osd: journal vs filestore sync in writeahead move
Sage Weil
04:24 PM Bug #212: osd: journal vs filestore sync in writeahead move
many commits, culminating in commit:fb1ad6e746a52a99d82d864d4a6efeda09be2440 Sage Weil
02:39 PM Bug #212 (Resolved): osd: journal vs filestore sync in writeahead move
The journal is incorrectly dropping entries in writeahead mode Sage Weil
04:19 PM Revision e4b9dd4b (ceph): msgr: avoid calculating data crc is peer didn't either
Otherwise we're just wasting CPU cycles! Sage Weil
03:34 PM Revision 2bb94b36 (ceph): msgr: Fix crash in policy.throttler->get(message_size) when message_siz...
Signed-off-by: Simone Gotti <simone.gotti@gmail.com>
Signed-off-by: Sage Weil <sage@newdream.net>
Simone Gotti
12:08 PM CephFS Bug #188 (Resolved): cfuse crashes on snapshot file read
This was a simple fix, just remove a dumb assert! Done in 25116b27388293ce19aef0472b1a5bd6c42527c3.
However, leads...
Greg Farnum
12:08 PM CephFS Bug #211 (Resolved): Cfuse won't unmount properly with snapshot activity
Perform the steps in #188, then ctrl-C cfuse. It won't unmount!
If you unmount and remount before creating the sna...
Greg Farnum
10:32 AM Linux kernel client Bug #210 (Resolved): GPF in ceph_con_revoke_message+0x2c/0x152
osd was repeated being restarted, probably doing weird things.... Sage Weil
10:02 AM Bug #98: reserved identifier violation
I don't actually remember how they were created, but according to the Readme file, it's javah, yes.
Those files aren...
Greg Farnum
09:49 AM Bug #98: reserved identifier violation
Do you use the tool ""javah":http://java.sun.com/javase/7/docs/technotes/tools/solaris/javah.html" for these header f... Markus Elfring
09:35 AM Bug #98: reserved identifier violation
Markus Elfring wrote:
> Do you mean that a tool for the "Java™ Native Interface":http://java.sun.com/javase/6/docs/t...
Sage Weil
09:18 AM Bug #98: reserved identifier violation
Do you mean that a tool for the "Java™ Native Interface":http://java.sun.com/javase/6/docs/technotes/guides/jni/index... Markus Elfring
09:03 AM Bug #98: reserved identifier violation
Markus Elfring wrote:
> Who is responsible for the tool that generates the affected header files?
Oh.. if those a...
Sage Weil
08:55 AM Bug #98: reserved identifier violation
Who is responsible for the tool that generates the affected header files? Markus Elfring
08:48 AM Bug #98: reserved identifier violation
Markus Elfring wrote:
> Would you also like to adjust any symbols with the prefix "_Included"?
> Example: source:sr...
Sage Weil
08:41 AM Bug #98: reserved identifier violation
Would you also like to adjust any symbols with the prefix "_Included"?
Example: source:src/client/hadoop/org_apache_...
Markus Elfring

06/17/2010

08:44 PM Revision 35095434 (ceph): qa: another mds test fix... wait long enough for the previous death to ...
Sage Weil
08:37 PM Revision c6067131 (ceph): msgr: ref count Pipe to avoid use after free
The Connection has a Pipe pointer to facilitate
send_message(Message, Connection)
but the reaper() clears that point...
Sage Weil
08:09 PM Revision 920b2d89 (ceph): qa: fix mdstable failure tests
Sage Weil
05:51 PM Revision 4d66a72a (ceph): ceph: fix straggler header ifdef guards
Sage Weil
05:47 PM Revision f4b9d9d8 (ceph): Bug #98: Unique names for include guards
A couple of preprocessor symbols for include guards tampered with the reserved namespace.
Signed-off-by: Markus Elfr...
Markus Elfring
05:36 PM Revision 6de2dde7 (ceph): ceph: remove leading _ from macro
Reported-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil
05:34 PM Revision 9013832c (ceph): Bug #98: Movement of an underscore for a data structure identifier
A leading underscore was moved to the back of a data structure identifier.
Signed-off-by: Markus Elfring <elfring@us...
Markus Elfring
05:13 PM Revision 8c5ee65b (ceph): osd: fix snap_trimmer AccessMode interaction
Recheck access mode every time we retake the pg lock (each object). Sleep
if necessary.
Sage Weil
05:13 PM Revision af2d023c (ceph): osd: don't requeue null OSDOp on apply_and_flush_repops
(this triggers during snap trimming) Sage Weil
05:13 PM Revision e6b033ac (ceph): osd: make clean_up_local remove hardlinks from collection dirs
Sage Weil
05:13 PM Revision 081bbe15 (ceph): mds: fix cdir head/snap items/null accounting
We were mixing up primary vs remote, partly due to the weird placement of
the counter adjustments. Make those sane a...
Sage Weil
05:13 PM Revision 57d79aaa (ceph): Revert "mkcephfs: cosd mkfs as root, then chown"
This reverts commit 0383878c4f5133f43ec16067a8917d3080adc690. Sage Weil
05:04 PM Revision f6501564 (ceph): Merge branch 'unstable' of ssh://ceph.newdream.net/home/sage/ceph.newdr...
Sage Weil
04:29 PM Revision b30ff171 (ceph): logclient: clean up interaction with monclient, monitor
Use monclient where available. Otherwise, we are a monitor, so send to
ourselves.
Conflicts:
src/mon/MonmapMonito...
Sage Weil
04:29 PM Revision b4727229 (ceph): osd: optionally periodically check pglog for corruption
...at least until we find this bug, periodically check pglog for corruption
and log it to the monitor when it happens...
Sage Weil
04:29 PM Revision 583f9f42 (ceph): mkcephfs: error out of journal dev is included in btrfs devs
Sage Weil
04:29 PM Revision f976bbdc (ceph): filejournal: journal write cache is safe on >= 2.6.33
Sage Weil
02:16 PM CephFS Bug #172 (Closed): OSD and MDS crash on rm -r
Closing this one. The osd crash was a snap_trimmer bug fixed a few days ago.
Added a qa workunit that repeats t...
Sage Weil
02:01 PM Bug #209 (Rejected): mkdir freezes on cfuse
I think I missed when diagnosing this one; looks like it was an error in my patch that I didn't actually compile out ... Greg Farnum
11:47 AM Bug #209 (Rejected): mkdir freezes on cfuse
This suddenly cropped up while testing my solution to 188 for no apparent reason, and now I can't get rid of it no ma... Greg Farnum
11:57 AM Bug #98 (Resolved): reserved identifier violation
Okay, applied these with a few fixes (and without the trailing gibberish in #1). Thanks Markus! Sage Weil
11:43 AM Bug #208 (Resolved): Can't create snapshots in cfuse on mds cluster
While trying to reproduce 188, I keep getting "mkdir: cannot create directory `mnt/a/.snap/1': No such file or direct... Greg Farnum
10:42 AM Bug #179 (Closed): corrupted LogEntry in mon data
Sage Weil
10:34 AM Linux kernel client Bug #204 (Resolved): crush update crash
fixed by commit:cebc5be6b6c82a99231e9c9af451e9e3d3399ec6 Sage Weil
10:18 AM Bug #203 (Rejected): osd journal full deadlock?
Sage Weil
10:18 AM Bug #173 (Resolved): Throttle client requests on OSD
Sage Weil
10:02 AM Linux kernel client Bug #207 (Resolved): NULL pointer reference when adding a block device
Actually this is probably due to the interface change in ceph_calc_raw_layout.
Should be fixed with commit 7a06cc4c2...
Yehuda Sadeh
01:43 AM Linux kernel client Bug #207 (Resolved): NULL pointer reference when adding a block device
I've been seeing this error a few times lately, but it seems i have some more information about it.
Building the r...
Wido den Hollander
09:40 AM Bug #205 (Resolved): remove journal write cache warning?
warning updated in commit:f976bbdcf700e52c9ef92964551b2c73b014686c Sage Weil

06/16/2010

09:15 PM Revision d7b9f39d (ceph): filejournal: log if journal item is larger than journal
Sage Weil
05:53 PM Revision 5dfc4119 (ceph): osd: warn when failing to mount journal on ENOTTY
suggest that the problem was due to journal size not configured Yehuda Sadeh
05:14 PM Revision d5995661 (ceph): conf: fix buffer initalization
This fixes a bug where we didn't initialize the variable
post processing buffer, which would sometimes lead to
garbag...
Yehuda Sadeh
05:14 PM Revision 5c001f4e (ceph): conf: can specify environment variables for substitution
Yehuda Sadeh
05:13 PM Revision ce909c2c (ceph): osd: error out when failing to read journal header
This fixes bug #201. Yehuda Sadeh
02:08 PM Bug #203: osd journal full deadlock?
maybe the journal was just too small:
> > > 10.06.11 21:46:37.335878 40cec950 journal check_for_full at 4694016 :
...
Sage Weil
09:30 AM Bug #203 (Rejected): osd journal full deadlock?
Sage Weil
11:56 AM Linux kernel client Feature #206 (New): make a 'soft' mode
On Wed, 16 Jun 2010, Peter Niemayer wrote:
> Hi,
>
> trying to "umount" a formerly mounted ceph filesystem that h...
Sage Weil
11:53 AM CephFS Bug #188 (In Progress): cfuse crashes on snapshot file read
Greg Farnum
11:43 AM Feature #138: Try out tcmalloc
All right, this is on hold while we work through some of the bugs that have been reported recently. Greg Farnum
10:03 AM Bug #205 (Resolved): remove journal write cache warning?
Sage Weil
09:57 AM Linux kernel client Bug #204 (Resolved): crush update crash
> mkcephfs -c /etc/ceph/ceph.conf --mkbtrfs (1mds, 1mon, 2osd (2 phyiscal disks$
> start ceph
> mount ceph fs
> wr...
Sage Weil

06/15/2010

12:39 PM Bug #201 (Resolved): Floating point exception when journal path is a directory
Fixed by 862bb864908ec22ec70b616ee2eddcf31e497742.
Now it'll exit cleanly and logs should be more descriptive abou...
Yehuda Sadeh
06:04 AM Bug #201 (Resolved): Floating point exception when journal path is a directory
When trying to add a new OSD i forgot that the journal had to be a file or a blockdevice, but instead a created a dir... Wido den Hollander
12:04 PM Bug #202: OSD crash during reads from cluster
I tried doing a fresh mkfs of only osd5, this is what i did:
* Removed all data in /srv/ceph/osd5
* Ran cosd with -...
Wido den Hollander
09:49 AM Bug #202 (Can't reproduce): OSD crash during reads from cluster
Today i noticed one crashing OSD during read operations (rsync) from my cluster.
I don't know if it matters, but t...
Wido den Hollander

06/14/2010

07:22 PM Revision d971bb06 (ceph): osd: mkfs failures are colored red
Yehuda Sadeh
04:07 PM Linux kernel client Bug #200: umount hangs with clustered mds
Seems to be waiting forever here:
wait_event(mdsc->cap_flushing_wq, check_cap_flush(mdsc, want_flush));
Yehuda Sadeh
03:21 PM Linux kernel client Bug #200 (Resolved): umount hangs with clustered mds
Happens on both current master and the unstable branches (6/14). The umount at the following scenario never exits:
...
Yehuda Sadeh
06:38 AM Bug #199 (Closed): OSD crash when rebalancing data
Today i wanted to expand my number of OSD's from 5 to 7.
After i loaded my new crushmap the rebalancing of data st...
Wido den Hollander

06/13/2010

10:45 AM Linux kernel client Bug #194: MOSDMap memory leak?
fixed by commit:ae32be31341a5fecfa16c5b3eb78095207182cce Sage Weil
10:43 AM Linux kernel client Bug #194 (Resolved): MOSDMap memory leak?
Sage Weil

06/12/2010

12:10 PM Bug #98: reserved identifier violation
Would you like to integrate any changes from the appended name adjustments into your source code repository? Markus Elfring

06/11/2010

10:10 PM Bug #198 (Can't reproduce): mds: repeated probing of inode
see 1000008b414.00000000 on current sepia.a mds instance Sage Weil
09:05 PM Revision bdda73fd (ceph): monc: handle mon0 or mon.a syntax when pull mon addrs from .conf
Sage Weil
09:03 PM Revision aabaa065 (ceph): monc: more debug info on monmap receipt
Sage Weil
08:56 PM Revision 690ea1c1 (ceph): mon: MONNAMES feature is supported by all userland
Sage Weil
08:34 PM Revision ddf739f6 (ceph): mon: simplify request forwarding
Use the MonSession to track proxy state, NOT the PaxosServiceMessage header
hackery.
Sage Weil
05:15 PM Revision 8cc096f6 (ceph): monmaptool: don't allow dup names, addrs to be added to the map
Sage Weil
05:12 PM Revision e5ff5189 (ceph): mds: add force_wrlock to lock states; use for filemax changes
This lets us write out a max_size change when we revoke caps from a client
(thus excl->sync) and the client releases ...
Sage Weil
05:12 PM Revision 658d51da (ceph): mon: make send_reply always consume reply ref (even if not sent); fix c...
Sage Weil
05:08 PM Revision 6a40008c (ceph): mon: make send_reply always consume reply ref (even if not sent); fix c...
Sage Weil
04:57 PM Revision 33850a22 (ceph): monmaptool: fix usages tring
Sage Weil
04:56 PM Revision 9fddee98 (ceph): mkcephfs: behave with new mon naming scheme
Sage Weil
10:46 AM Bug #197 (Resolved): osd: FAILED assert(state == DELAYED || state == RMW)
Sage Weil
10:18 AM Bug #197 (Resolved): osd: FAILED assert(state == DELAYED || state == RMW)
... Sage Weil

06/10/2010

11:01 PM Revision 3336d9d0 (ceph): rgw: put_obj uses write_full
Yehuda Sadeh
10:26 PM Revision 0b0009cf (ceph): cls_rbd: use write_full when writing image header
Yehuda Sadeh
10:26 PM Revision 5d2e85d2 (ceph): class: implement write_full interface
Yehuda Sadeh
10:15 PM Bug #35: osd: pg split should queue transaction(s) under appropriate sequencer(s)
splitting is broken in other ways as well.. postpone for v0.22. Sage Weil
10:15 PM Bug #192 (Resolved): inconsistent md5sum on repeated read of file
Sage Weil
05:08 PM Bug #192: inconsistent md5sum on repeated read of file
Problem seem to be rbd branch related, introduced by the splitting of calc_layout to helper function: plen is not upd... Yehuda Sadeh
12:48 PM Bug #192 (Resolved): inconsistent md5sum on repeated read of file
BTW: I think the .snap portion is not required for this to fail.... Sage Weil
10:14 PM Feature #195 (Resolved): monitor naming and removal support
see mon-remove branch. let's merge this after v0.21. Sage Weil
10:13 PM Linux kernel client Bug #193: protocol error after control-c
Yehuda Sadeh wrote:
> This was on the rbd branch, does it also happen on the unstable branch? The wait_for_completio...
Sage Weil
05:18 PM Linux kernel client Bug #193: protocol error after control-c
This was on the rbd branch, does it also happen on the unstable branch? The wait_for_completion_killable() might have... Yehuda Sadeh
04:42 PM Linux kernel client Bug #193 (Resolved): protocol error after control-c
Saw this on wido's machine:... Sage Weil
10:11 PM Linux kernel client Bug #194 (Resolved): MOSDMap memory leak?
Code audit looks ok. Could this be a false alarm somehow?... Sage Weil
09:45 PM Revision 80d2afc1 (ceph): cclsinfo: utility to display class information
Yehuda Sadeh
09:45 PM Revision e3b23bd0 (ceph): cclsinfo: some fixes
Yehuda Sadeh
09:45 PM Revision d071cb1c (ceph): cclsinfo: replace error message
Yehuda Sadeh
09:45 PM Revision 203af22e (ceph): cls: export relevant functions
Yehuda Sadeh
09:45 PM Revision 057ccbbf (ceph): cclsinfo.sh: shell script to dump class info
Yehuda Sadeh
09:45 PM Revision d87c057f (ceph): cclsinfo.sh: better architecture detection
Yehuda Sadeh
09:45 PM Revision 65371482 (ceph): class: able to add classes when doing mkfs
Yehuda Sadeh
09:45 PM Revision e737e635 (ceph): class: more flexible class loading, new cclass.sh script
Yehuda Sadeh
09:45 PM Revision 7584fef1 (ceph): class: modify scripts, fix configuration
Yehuda Sadeh
09:45 PM Revision 3bb153c3 (ceph): class: modify startup scripts to add classes on mon startup
Yehuda Sadeh
09:45 PM Revision ae5bb842 (ceph): cclass: add some options
Yehuda Sadeh
09:45 PM Revision 912e3c85 (ceph): osd: fix rollback when head points at the rolled back snapshot
Yehuda Sadeh
09:45 PM Revision f34c5b91 (ceph): cls_rbd: fix snapshots seq number
Yehuda Sadeh
09:45 PM Revision b58e1b9a (ceph): rados: update documentation to mention mkpool and rmpool
Greg Farnum
09:45 PM Revision 4716b486 (ceph): rbd: snapshots management via class mechanism
Yehuda Sadeh
09:45 PM Revision c5abf58d (ceph): class: add CLS_LOG macro
Yehuda Sadeh
09:45 PM Revision 2991c300 (ceph): rbd: add snapshot creation via rbd class
Yehuda Sadeh
09:45 PM Revision a6e50c24 (ceph): rbd: implement snap revert header manipulation via class
Yehuda Sadeh
09:45 PM Revision e297aa0b (ceph): rbd: snap revert header manipulation fixes
Yehuda Sadeh
09:45 PM Revision 94308d13 (ceph): cls-rbd: some adjustments, debug info
Yehuda Sadeh
09:42 PM Revision 7739cafb (ceph): testradospp: add a test for librados trunc
Yehuda Sadeh
09:41 PM Revision 42ff45b4 (ceph): librados: add trunc operation
Yehuda Sadeh
09:12 PM Revision 3de397fc (ceph): testradospp: update test, use write_full
Yehuda Sadeh
09:04 PM Revision d1c779c9 (ceph): librados: implement write_full
Yehuda Sadeh
06:55 PM Revision 92f2ecd3 (ceph): osd: fix null dereference in dout
Yehuda Sadeh
05:17 PM Revision effe5db3 (ceph): mds: be extra careful
Probably implied by the refs == 0, but be explicit anyway. Sage Weil
05:17 PM Revision 607ba5dd (ceph): mds: fix another instance of bad stray trimming code to use proper helper
Sage Weil
04:10 PM Revision 673fdc7a (ceph): mds: remove erroneous return statement
Greg Farnum
04:06 PM Revision 8be5b029 (ceph): mds: a checker function like _is_dir_nonempty should only report results.
Remove the call to reply_request and fix up the callers that need it. Greg Farnum
03:47 PM Feature #184: librados support for truncate, writefull
And related rgw commit:
3336d9d0fab7513c12a48879ab9a50cba2ab475e
Yehuda Sadeh
03:43 PM Feature #184 (Resolved): librados support for truncate, writefull
implemented.
commits:
d1c779c96a0afeaf245ade6c5d4c8de818fcd66b
42ff45b4eec31b992a1ecc1cc27a0f513f6cadde
Yehuda Sadeh
12:52 PM rbd Feature #41: Support snapshots
The qemu BlockDriver interface includes a bdrv_snapshot_goto callback that is being used to select a snapshot. Snapsh... Yehuda Sadeh
12:44 PM rbd Feature #41: Support snapshots
Yehuda Sadeh wrote:
> Then kvm-rbd snapshots implementation also needs to include snapshots rollback.
How would t...
Sage Weil
12:35 PM rbd Feature #41: Support snapshots
Then kvm-rbd snapshots implementation also needs to include snapshots rollback. Yehuda Sadeh
12:39 PM Feature #191 (Rejected): rbd needs locking mechanism
Certain operations on rbd image cannot happen without a proper locking mechanism. This includes all rbd image header ... Yehuda Sadeh
12:32 PM Feature #160 (Resolved): rbd revert-to-snapshot
snap_rollback is implemented and seems to be working. Actually, there's no need for the rbd-class specific code for i... Yehuda Sadeh
12:28 PM Linux kernel client Feature #190: krbd: DISCARD support
Yeah, it's called 'discard'. In order to get a block device to support it we need to do something like:
queue_flag_...
Yehuda Sadeh
10:26 AM CephFS Bug #177 (Resolved): unlinked inode during try_to_expire()
Hit this one myself (with full mds logs) and found the bug. Fixed in commit:607ba5dd14e11fe28f1a37cf8a29d4c48d181e0b Sage Weil
05:17 AM Revision 214a4279 (ceph): mds: handle dup anchorclient ACKs gracefully
One recovery scenario sees crisscrossing 'agree' and 'commit':
C->S --> commit1
S->C --> agree
C<-S <== agree
...
Sage Weil

06/09/2010

09:43 PM Revision c35cb294 (ceph): mds: fix export caps
Don't mangle sessionmap version by incrementing twice; pv is returned by
prepare_force_open_sessions().
Sage Weil
09:19 PM Revision 0349c789 (ceph): mds: allow import caps pin from multiple replicas at once
e.g. on dentry unlink, replicas send their caps to the auth. There may
be multiple replicas.
Sage Weil
08:50 PM Revision 1a3fac44 (ceph): osd: return EINVAL when snapc is invalid and trying to write
Yehuda Sadeh
08:30 PM Revision e74250d8 (ceph): osd: don't clobber racing pg_info on active pg
Wido saw a pg go active, but an activate log+info update crossed paths with
a pg_notify info, and the primary overwro...
Sage Weil
07:29 PM Revision 42738093 (ceph): osd: refine SnapContext::is_valid()
Sage Weil
07:27 PM Revision 2648e403 (ceph): osd: implement SnapContext::is_valid()
Sage Weil
05:56 PM Revision 7c780592 (ceph): init-ceph: don't fail if we fail to umount
It may not be mounted to begin with. Sage Weil
02:40 PM Linux kernel client Feature #190 (Resolved): krbd: DISCARD support
TRIM does exist, somewhere in Linux. RBD should support it so if the client system is using a supporting filesystem, ... Greg Farnum
05:34 AM Revision 12798de3 (ceph): osd: add --dump-pg-log command
Sage Weil
05:25 AM Revision 464fcd0e (ceph): monmap: use this here vector size to be clear
Sage Weil
04:52 AM Revision 16a46710 (ceph): mon: send old format monmap to old clients (backward compatible)
Also add some Connection smarts to monitor session. Sage Weil
04:36 AM Revision fb1c3b92 (ceph): osd: clear newly_removed_snaps on osdmap update if unchanged
We only want to apply _newly_ removed snaps once, or else we try to trim
the same snaps multiple times, and crash lik...
Sage Weil

06/08/2010

11:43 PM Revision 15a7a839 (ceph): mds: use helper to send message to client; fix send to null connection
Sometimes session->connection is NULL; use session->inst in that case. Sage Weil
11:33 PM Revision c992d020 (ceph): mds: remove erroneous bracket
Greg Farnum
11:25 PM Revision 2a88e2e5 (ceph): add checks for being a snapshot root to dir_is_nonempty
Greg Farnum
11:11 PM Revision 0d8c2975 (ceph): Merge branch 'unstable' into mon-remove
Sage Weil
11:03 PM Revision e3c4459e (ceph): monclient: track cur_mon by name, not rank
Sage Weil
10:59 PM Linux kernel client Bug #189 (Resolved): leaked dentry
Running unstable, commit:e041c5f
I think this is triggered by bonnie.sh. The bonnie.sh below is the dir where the...
Sage Weil
10:53 PM Bug #114: osd: corrupted pglog
Running 'src/script/check_pglog.sh $osd_data_dir' (from ceph.git) periodically will let you check the osd for any cor... Sage Weil
10:48 PM Revision 1d162972 (ceph): mon: rename whoami rank, simplify rank change logic
Sage Weil
10:37 PM Revision 0dc95695 (ceph): mds: fix stale lease trimming xlist iterator abuse
Sage Weil
10:37 PM Revision 26a4d0ea (ceph): throttle: allow take(0)
Sage Weil
10:17 PM Revision 2fa4a069 (ceph): mon: identify monitors by name, not rank
Sage Weil
10:13 PM Revision c196851b (ceph): osd: init auid to CEPH_AUTH_UID_DEFAULT in case authorizer doesn't set it.
We should probably also require the authorizer to set it for us. Greg Farnum
10:13 PM Revision 76fb75e9 (ceph): buffer: fix padding distances
Greg Farnum
10:13 PM Revision 7c856462 (ceph): mon: fix memory-leaked messages
Greg Farnum
09:48 PM Bug #56 (Closed): osd: crash on repop completion
Sage Weil
09:48 PM Bug #56 (Rejected): osd: crash on repop completion
I haven't seen this in forever. Closing out. Sage Weil
08:50 PM Feature #138: Try out tcmalloc
Going to implement this as a compile-time option (based on available libraries) once I've audited the mds and osd for... Greg Farnum
08:38 PM Revision 80c42d06 (ceph): mds: scan stray dir, eval strays on mds startup
Sage Weil
08:31 PM Bug #179 (In Progress): corrupted LogEntry in mon data
Sage Weil
08:31 PM Bug #179 (Rejected): corrupted LogEntry in mon data
Hmm, yeah i give up on this one. I see that it's corrupt, but not in any particularly suggestive way. No idea what ... Sage Weil
12:49 AM Bug #179: corrupted LogEntry in mon data
I also had some problems using gdb...
gdb won't work if cmon is not in /usr/bin and debug symbols for cmon (which I ...
ar Fred
06:39 PM Revision da520d7b (ceph): mon: clean up monmapmonitor warnings, style
Sage Weil
06:37 PM Revision 76191d23 (ceph): logclient: clean up interaction with monclient, monitor
Use monclient where available. Otherwise, we are a monitor, so send to
ourselves.
Sage Weil
06:27 PM Revision 0ab54c70 (ceph): monclient: make get_monmap_privately() clean up after itself
- set cur_mon=-1 when we're done
- clean up connections
Sage Weil
06:22 PM Revision 0b44ef02 (ceph): monclient: Make MonClient update cur_mon on getting new monmap
A MonClient starting with an incorrect monmap (i.e. mon id in the
starting map does not match the actual mon id found...
Sage Weil
04:42 PM Revision 2e1b0d35 (ceph): mon: make mon lease clock check protocol change backward compatible
Sage Weil
04:29 PM Bug #186 (Resolved): BUG: failed to decode message of type 66 v1: buffer::exception
Sage Weil
09:38 AM Bug #186 (In Progress): BUG: failed to decode message of type 66 v1: buffer::exception
This was due to commit:29a42efe2e4c789092f59b98b29632bdc4b88a80, which made a protocol change. I'll fix it up today ... Sage Weil
06:41 AM Bug #186 (Resolved): BUG: failed to decode message of type 66 v1: buffer::exception
While my cluster was in a degraded state due to a disk failure at random 2 out of my 3 monitors crashed.
I really ...
Wido den Hollander
04:25 PM Feature #180 (Resolved): Return ENOTEMPTY when trying to remove a directory which has a snapshot
As of 2a88e2e54ee0b9449e86cec02315e2809b75ca8b it will return ENOTEMPTY if you try to delete a dir which roots a snap... Greg Farnum
04:23 PM CephFS Bug #188 (Resolved): cfuse crashes on snapshot file read
gregf@pudgy:~/ceph/src$ sudo mkdir mnt/a
[sudo] password for gregf:
gregf@pudgy:~/ceph/src$ sudo mkdir mnt/a/b
gr...
Greg Farnum
03:18 PM Bug #181 (Resolved): monitor eats 8G of memory before beeing oom killed
Found and fixed many more monitor memory leaks in 7c85646240a02a3e82a727045de6e4432cc2ed9e. Valgrind is a lot happier... Greg Farnum
01:00 AM Bug #181: monitor eats 8G of memory before beeing oom killed
Ok, here is an update 1 day after posting comment #2:
mon0 is dead, mon1 is also dead, both OOM-killed I guess (no...
ar Fred
10:42 AM RADOS Bug #187 (Rejected): crush: high variance, latency for straw buckets
Sage Weil
09:47 AM Cleanup #103: Introduction of namespaces
Markus Elfring wrote:
> Can a bit of "C++ namespaces advice":http://stackoverflow.com/questions/713698/c-namespaces-...
Sage Weil
03:06 AM Cleanup #103: Introduction of namespaces
Can a bit of "C++ namespaces advice":http://stackoverflow.com/questions/713698/c-namespaces-advice help to clarify yo... Markus Elfring
07:49 AM Revision bc9fba0e (ceph): Introduced ceph mon remove command
Added ceph mon remove <ip>:<port> command. The command will remove
the target monitor from the monmap and shutdown th...
Paul Chiang
05:18 AM Revision 58fe4b8d (ceph): qa: add untar_snap_rm.sh
Sage Weil
05:05 AM Revision ac10d837 (ceph): osd: print rollback osd_op nicely
Sage Weil
03:55 AM Bug #99: Check return codes everywhere
The C/C++ programming language makes it easy to "overlook unused return values":http://stackoverflow.com/questions/12... Markus Elfring
02:31 AM Feature #101: Conversion of pointer parameters into references
> ... and because it makes the pass-by-reference more explicit.
I find this opinion questionable. I assume that yo...
Markus Elfring
02:10 AM Cleanup #146: Complete build options for Pthread API
... Markus Elfring

06/07/2010

11:03 PM Revision 470a6fde (ceph): mds: wire Connection to Session when Session already exists on connect
Sage Weil
11:03 PM Revision 6d770abe (ceph): mds: funnel mds->client messages through single Session* helper
Simplify callers where possible. Sage Weil
10:52 PM Feature #6 (Rejected): libceph could use a backward-compatible-to function
Usually this is handled via the shared object versioning scheme. The bit that doesn't address (I think) is when the ... Sage Weil
10:50 PM Bug #98: reserved identifier violation
The qemu guys were worried about this when we submitted the rbd driver. Simply changing __FOO_H to CEPH_FOO_H throug... Sage Weil
10:48 PM Bug #99: Check return codes everywhere
Markus Elfring wrote:
> Would you like to reuse any class library?
>
> I do not like "assert" for consistent erro...
Sage Weil
10:42 PM Cleanup #103: Introduction of namespaces
Markus Elfring wrote:
> This issue corresponds to my previous "feature request":https://sourceforge.net/tracker/?fun...
Sage Weil
10:42 PM Revision 29a42efe (ceph): mon: simplify clock drift checks
Ignore lease sent vs lease_ack receive times bc multiple lease msgs may
be in flight and the ack may be from a previo...
Sage Weil
10:40 PM Feature #101 (Rejected): Conversion of pointer parameters into references
Markus Elfring wrote:
> This issue corresponds to my previous "feature request":https://sourceforge.net/tracker/?fun...
Sage Weil
10:38 PM Cleanup #146: Complete build options for Pthread API
Markus Elfring wrote:
> Would you like to integrate the appended changes into your source code repository?
This g...
Sage Weil
10:25 PM Bug #149 (Closed): Stale NFS Handle when copying from snapshot
Still finding bugs with this basic workload, but I haven't seen ESTALE pretty much ever. Closing this one out for no... Sage Weil
10:04 PM Revision 527d5fd7 (ceph): monc: behave in ms_handle_reset if cur_mon is < 0
Sage Weil
10:03 PM Revision 6ff2a876 (ceph): msgr: don't throttle.get 0
Sage Weil
10:00 PM Revision 191cb2e4 (ceph): throttle: allow put(0)
Still returns a consistent value for the count. Sage Weil
09:59 PM Revision e505fb5a (ceph): msgr: don't thottle.put 0
Sage Weil
09:47 PM Revision d2740973 (ceph): Merge remote branch 'origin/msgr' into unstable
Sage Weil
07:05 PM Revision 4ecd8fac (ceph): mds: use cap on head if there is none on the snapped inode
This is needed, in particular, when we're flushing snap data on an inode
that already got COWed.
Sage Weil
06:40 PM Revision 5be26609 (ceph): osd: use low-level helper getting obc in sub_op_push
find_object_context does all sorts of stuff we don't need here: we know
which object the context is for. Just set it...
Sage Weil
03:09 PM Feature #185: mds: set file layout policy on directory hierarchy
If we use an xattr for this, one issue will be keeping the ancestor directly policy consistent across any mds node ma... Sage Weil
03:07 PM Feature #185: mds: set file layout policy on directory hierarchy
Alex Nelson wrote:
> One complication that may arise: If directory xattrs are what are used, what would be the sema...
Sage Weil
03:04 PM Feature #185: mds: set file layout policy on directory hierarchy
One complication that may arise: If directory xattrs are what are used, what would be the semantics of a file hard-l... Alex Nelson
03:03 PM Feature #185 (Resolved): mds: set file layout policy on directory hierarchy
It woud be helpful to have a way to specify multiple files' object sizes. Currently there is an ioctl for controllin... Alex Nelson
02:37 PM CephFS Bug #177: unlinked inode during try_to_expire()
The problem is that the dirty_inodes list assumes the inodes are either linked or base inodes. That should be the ca... Sage Weil
02:32 PM Bug #179 (In Progress): corrupted LogEntry in mon data
Okay, I can't make heads or tails of your core file on my system for some reason. Can you try this on your machine? ... Sage Weil
12:55 PM Revision 61555cce (ceph): throtle: add asserts on max and change parameters where appropriate
Greg Farnum
12:54 PM Revision 8413ed49 (ceph): throttle: fix assert count to actually use count
Greg Farnum
12:04 PM Linux kernel client Bug #182 (Resolved): VFS: Busy inodes after unmount of ceph.
This was actually an mds bug. It wasn't responding to a client_caps flushsnap. Fixed in ceph.git commit:4ecd8facd91... Sage Weil
09:43 AM Linux kernel client Bug #182 (Resolved): VFS: Busy inodes after unmount of ceph.
Am Sun, 06 Jun 2010 21:10:28 -0700 schrieb Sage Weil:
> On Sat, 5 Jun 2010, Thomas Mueller wrote:
>> hi
>>
>> ...
Sage Weil
11:35 AM Feature #184 (Resolved): librados support for truncate, writefull
We need to add librados support for truncate and writefull. We should make sure that the S3 gateway handles object re... Yehuda Sadeh
11:11 AM CephFS Bug #52 (Resolved): mds: dentry versionlock
Sage Weil
11:11 AM Feature #112 (Resolved): osd: snap rollback object op
Sage Weil
11:10 AM Bug #176 (Resolved): osd: make_clone needs to duplicate xattrs
Sage Weil
11:09 AM Feature #183 (Resolved): qa: xfstests workunit
simple script that will run a subset of xfstests in the current directory. Sage Weil
09:49 AM Bug #181 (In Progress): monitor eats 8G of memory before beeing oom killed
Guess I'll look at this a bit more. Greg Farnum
01:22 AM Bug #181: monitor eats 8G of memory before beeing oom killed
Hi, thanks for the fixes.
I just finished testing the new version, and my monitor survived (eating 6.8G memory, mo...
ar Fred
05:15 AM Revision 21a97d1e (ceph): mon: don't leak MAuth
Sage Weil
05:15 AM Revision d57b6296 (ceph): crypto: don't leak memory in CryptoAES::encrypt()
Sage Weil
05:15 AM Revision 520a2c37 (ceph): crypto: don't clean up EVP table on every decrypt()
Don't think that's appropriate? And certainly doesn't happen for the
encrypt() case.
Sage Weil
01:47 AM Revision ba63a7a4 (ceph): Removed all copies of the whoami value
Paul Chiang

06/06/2010

10:24 PM Bug #181 (Resolved): monitor eats 8G of memory before beeing oom killed
fixed two leaks, commit:21a97d1e7ce329fac07b5e69362d27bb7edb31f5 and commit:d57b629699158abacdcc3880d43111291a6fdf77 ... Sage Weil
05:08 AM Bug #181 (Resolved): monitor eats 8G of memory before beeing oom killed
Hi, I installed the latest ceph 0c38b3d63dd24fb8b86283de5e00f260a03d4024, and the latest qemu-rbd e6d8dbce416bfdba880... ar Fred
02:08 PM Feature #138 (In Progress): Try out tcmalloc
Okay, this is definitely something we need to look into more. I tried running with tcmalloc and the standard malloc, ... Greg Farnum
06:23 AM Cleanup #146: Complete build options for Pthread API
Would you like to integrate the appended changes into your source code repository? Markus Elfring

06/05/2010

12:01 AM Revision 989c9ee1 (ceph): throttle: use signed counters and assert that count never drops below 0
Greg Farnum

06/04/2010

11:42 PM Revision 46040a5f (ceph): msgr: switch to get/set functions for Message:throttler
Greg Farnum
11:42 PM Revision 246415b3 (ceph): osd: fix compile issues
Greg Farnum
11:42 PM Revision 3b333f7a (ceph): msgr: put throttler usage on Message destruct
Greg Farnum
11:42 PM Revision 800da082 (ceph): msgr: Fix uses of get_[data, payload, middle] to use throttling-aware f...
Greg Farnum
11:42 PM Revision 0d4bdfac (ceph): osd: add osd_client_message_size_cap option to config; default 500MB
And change the name in cosd to be that Greg Farnum
11:32 PM Revision a76d8fc6 (ceph): objectcacher: cleanup formatting
Sage Weil
11:32 PM Revision dff7cb33 (ceph): objectcacher: fix stat accounting when resizing bufferheads
Must keep stats in mind when adjusting bufferheads! Sage Weil
11:32 PM Revision 0c38b3d6 (ceph): objectcacher: add verify_stats() debugging helper
Sage Weil
11:32 PM Revision 12a5d7b2 (ceph): objectcacher: match states before merging in map_write
The caller is going to set us to dirty, so we don't care what state we
have, so long as the left and right bits we're...
Sage Weil
11:32 PM Revision 462552ab (ceph): objectcacher: fix use of invalid iterator in map_write()
The p points to bh, which is removed by merge_left. Move it back to final,
so we can advance to the new next a few l...
Sage Weil
11:23 PM Revision 522c12e5 (ceph): osd: fix rollback when head points at the rolled back snapshot
Yehuda Sadeh
08:23 PM Revision 33b947cd (ceph): msg: remove copy_payload and copy_data functions; change set to use thr...
Greg Farnum
08:10 PM Revision 8d1e7739 (ceph): Merge branch 'rbd' into unstable
Sage Weil
08:09 PM Revision 7b6aea6a (ceph): osd: clean up rollback debug output
Sage Weil
08:01 PM Revision 1b5920f8 (ceph): uclient: handle inode with no caps from mds
This happens when you readdir and some inodes are in a different snaprealm. Sage Weil
07:57 PM Revision e79a3fae (ceph): osd: filter_xattrs on a rollback op
Greg Farnum
07:55 PM Revision 48555f52 (ceph): osd: fix naughty iterator usage after invalidating it
Greg Farnum
07:49 PM Revision c730b85c (ceph): osd: add filter_xattrs function to remove non-user xattrs from a map of...
Greg Farnum
07:49 PM Revision a70a3668 (ceph): osd: _make_clone now properly duplicates xattrs
Greg Farnum
07:04 PM Revision f60be8e3 (ceph): progress
Greg Farnum
06:07 PM Revision 84b279a4 (ceph): mds: fix straydn->first part deux
9ed0c30ecf6611193db52e1facc1f46b37f04bc4 forgot to remove the old code. Sage Weil
04:45 PM Bug #173: Throttle client requests on OSD
Pushed to msgr, commit 800da082ad8aad032ff5299b5ad0c05bc378a1e3.
This definitely, definitely does not set a hard m...
Greg Farnum
04:31 PM Bug #178 (Resolved): cfuse fails dbench
fixed this, and some related ObjectCacher bugs. dbench exercised a lot of code that simple tests in the past had not... Sage Weil
09:50 AM Bug #178 (Resolved): cfuse fails dbench
From Thomas Mueller <thomas@chaschperli.ch>:
cfuse fails dbench with ceph.git testing. See logs:
Debian testing...
Sage Weil
02:04 PM Bug #179: corrupted LogEntry in mon data
Doh.. so it looks like the piece of info I need was in the logm directory. If you still have it, great. If not, I c... Sage Weil
11:13 AM Bug #179 (Closed): corrupted LogEntry in mon data
this is after a restart due to the update of all ceph daemons to c4e6482d302aa288031ced6cd845d60ba655e5c8
#0 0x...
ar Fred
12:58 PM Bug #176: osd: make_clone needs to duplicate xattrs
Pushed to unstable; and updated _rollback_to in the rbd branch to filter properly. Greg Farnum
11:50 AM CephFS Bug #165 (Resolved): cmds crash
Sage Weil
11:39 AM CephFS Bug #165: cmds crash
Indeed, can't reproduce the crash with the latest unstable.
I did 3-4 restart of all mds and it worked fine, that'...
ar Fred
11:43 AM Feature #180 (Resolved): Return ENOTEMPTY when trying to remove a directory which has a snapshot
When the following command sequence is used, valuable data in a snapshot could go lost:... Wido den Hollander
10:37 AM CephFS Bug #172: OSD and MDS crash on rm -r
Sage Weil wrote:
> Wido den Hollander wrote:
> > Today i ran the same test again, almost the same result.
> >
> ...
Wido den Hollander
09:53 AM CephFS Bug #172: OSD and MDS crash on rm -r
Wido den Hollander wrote:
> Today i ran the same test again, almost the same result.
>
> Before i ran the test i ...
Sage Weil
06:22 AM CephFS Bug #172: OSD and MDS crash on rm -r
Today i ran the same test again, almost the same result.
Before i ran the test i created a fresh fs with mkcephfs....
Wido den Hollander
03:25 AM CephFS Bug #177 (Resolved): unlinked inode during try_to_expire()
After trying to recover from bug #172 my MDS started to crash on their recovery.
Both mds0 and mds1 crashed while ...
Wido den Hollander
01:22 AM Revision 97f00aec (ceph): debugging output
Greg Farnum
01:22 AM Revision d3863272 (ceph): rados: print out pool instead of object
Greg Farnum
12:33 AM Revision 9ead80f8 (ceph): mds: fix CDir::take_sub_waiting vs dnwaiter pin
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
12:33 AM Revision 074a9b10 (ceph): mds: make discover work for multiversion inodes (e.g. dirs)
If we don't have the specific snap, look up the head and see if it's
multiversion.
This doesn't give us a "range" lo...
Sage Weil
12:33 AM Revision ec0aa43a (ceph): mds: don't export stray (~mdsfoo/stray), and ignore in balancer
We _must_ keep mdsdir and stray on local mds for normal operations.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil
12:33 AM Revision 9ed0c30e (ceph): mds: set straydn first to match inode on unlink
Sage Weil
12:33 AM Revision c4e6482d (ceph): mds: only purge dentries with no extra refs (besides dirty)
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
12:33 AM Revision 551a12f5 (ceph): mds: fix cap clone logic to look at matching first, not last
The cap->client_follows is set to follows+1 by flushsnap, since the real
follows value isn't convenient. But it is e...
Sage Weil
12:33 AM Revision 791ca282 (ceph): mds: kill open_foreign_stray; but open remote mdsdirs instead
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil

06/03/2010

11:45 PM Revision ff0e8715 (ceph): libatomic: fix assert.h compilation
Yehuda Sadeh
11:40 PM Revision 900d4c6c (ceph): msgr: add Throttle pointer to Policy
Greg Farnum
11:20 PM Revision 1facfe0f (ceph): Merge branch 'unstable' into msgr
Greg Farnum
09:14 PM Revision 62b900f5 (ceph): mds: open past snap parents at end of rejoin phase
We really need past parents open before we go active or else anything
that needs to build a snap context will fail.
Sage Weil
09:12 PM Revision 3989ae40 (ceph): osd: make sure we don't return EAGAIN to client
Greg Farnum
08:48 PM Revision 26449e7c (ceph): mdsmap: show individual mds states in summary
Sage Weil
08:26 PM Revision 09185a00 (ceph): osd: improve snap_trimmer debug output
Sage Weil
08:24 PM Revision 2b33d99b (ceph): mds: another cap_exports message/mdcache encoding fix
Signed-off-by: Sage Weil <sage@newdream.net> Sage Weil
08:08 PM Revision 55da048f (ceph): mds: only adjust dn->first on lock msg if !multiversion
The multiversion dn->first references a range of inode versions; don't
drag it forward. Fixes 38cb2403c043e6676b5631...
Sage Weil
07:03 PM Revision 5f905961 (ceph): mds: more fix cap_exports typing
Sage Weil
06:59 PM Revision 054669ab (ceph): mds: fix scatter_nudge infinite loop
Sage Weil
06:08 PM Revision 40b23227 (ceph): mds: fix ESessions type
Sage Weil
06:04 PM Revision 5cd7919a (ceph): mds: drag in->first forward with straydn in handle_dentry_unlink
Sage Weil
05:38 PM Revision 394d9c3d (ceph): mds: fix anchorclient dup lookups, again
Sage Weil
05:17 PM Revision 980f234f (ceph): mds: only log successful requests as completed
Sage Weil
05:09 PM Revision fa1e5603 (ceph): mds: anchor dir on mksnap
Sage Weil
04:45 PM Revision c09d610c (ceph): mkcephfs: error when creating journal file in a directory that differs...
mkcephfs creates osd data directory automatically, but it doesn't create a
directory for the osd journal file.
When ...
CC Lien
04:40 PM Revision 5dd4a2d6 (ceph): mds: fix mismatched cap_exports type between msg and MDCache
The types need to match because they are encoded/decoded interchangeably.
See MMDSCacheRejoin::decode() and MDCache::...
Sage Weil
04:33 PM Revision 609e6572 (ceph): mds: fix trim_unlinked iterator badness
We may remove the next inode in the map. Queue up unlinked roots first,
which we know remove_inode_recursive() won't...
Sage Weil
04:28 PM Revision 915ab3ca (ceph): mds: define MDS_REF_SET in unstable
Sage Weil
04:27 PM Revision ef095e1f (ceph): mds: clear dirtyscattered in remove_inode()
Sage Weil
04:17 PM Revision 26822162 (ceph): mds: allow dup lookups in anchorclient
It's not practical for callers to avoid dups, particularly since they may
be unaware of each other. And it's trivial...
Sage Weil
04:13 PM Bug #176 (Resolved): osd: make_clone needs to duplicate xattrs
Sage Weil
04:01 PM Revision 8a2a9bd6 (ceph): assert: fix assert vs atomic_ops.h breakage
This was causing us to use the system assert, not the ceph one. Sage Weil
03:23 PM Feature #175 (Resolved): Make the system large-object safe
This will require extensive work throughout the system, especially in OSD recovery code. Right now, Ceph assumes that... Greg Farnum
03:20 PM rgw Feature #174 (Resolved): Support large files better
Right now, the rados gateway just dumps a given file into the RADOS store as a single large dump. If somebody's stori... Greg Farnum
03:19 PM Revision f5ccc662 (ceph): mds: ensure past snap parents get opened before doing file recovery
Otherwise we can fail to get_snaps() when we start the recovery:
#0 0x00007fa037625f55 in *__GI_raise (sig=<value o...
Sage Weil
03:17 PM Bug #173 (In Progress): Throttle client requests on OSD
Yep, working on it now. Greg Farnum
02:44 PM Bug #173 (Resolved): Throttle client requests on OSD
See Jim Schutt's issue on the mailing list and simple patch to illustrate the problem.
Namely, overzealous clients c...
Greg Farnum
03:16 PM Bug #149: Stale NFS Handle when copying from snapshot
Putting this back in the mix since Sage has been handling a lot of bugs from this test case today. Greg Farnum
03:04 PM Revision c0e9d210 (ceph): mds: relax lock state before encoding export (and lock state)
We can't fuss with lock state in the finish method because we already
encoded the old state to the new auth, and we a...
Sage Weil
01:54 PM Linux kernel client Bug #111 (Resolved): handle EAGAIN from osd
Looks to me like this can't actually happen. The function ReplicatedPG::find_object_context can return EAGAIN, and an... Greg Farnum
01:39 PM CephFS Bug #170 (Rejected): null pointer dereference in journal_cow_dentry causes assertion failure
Sage Weil
10:33 AM CephFS Bug #170: null pointer dereference in journal_cow_dentry causes assertion failure
Unfortunately I don't -- on Yehuda's suggestion I recompiled with optimization off and have been trying to reproduce ... Greg Farnum
01:39 PM CephFS Bug #171 (Resolved): mds: MDSTableClient::_logged_ack(version_t) FAILED assert(pending_commit.cou...
Sage Weil
07:42 AM CephFS Bug #171: mds: MDSTableClient::_logged_ack(version_t) FAILED assert(pending_commit.count(tid))
fixed by commit:3768ef941e67d17ecd710994b2c88960ba60627d Sage Weil
06:07 AM Revision 3768ef94 (ceph): mds: do not bother tableserver until it is active
We resend these requests when the TS does go active, and if we send dups
things get all screwed up (see partial log b...
Sage Weil
05:14 AM Revision 7c0df054 (ceph): mds: do not reset filelock state when checking max_size during recovery
This was broken by d5574993 (probably, that commit fixed a similar
problem). The rejoin_ack initializes replica stat...
Sage Weil
05:11 AM CephFS Bug #172 (Closed): OSD and MDS crash on rm -r
I'm still using my test script which unpacks the kernel source and then removes it again with a few steps in between.... Wido den Hollander
04:33 AM Revision 15c6651f (ceph): mds: lock->sync replica state is lock, not sync
It's not readable yet. And after the lock->sync gather completes we send
out a SYNC.
Fixes failed assertion like:
...
Sage Weil
02:37 AM Revision 1c930f9b (ceph): msg: add missing msg_types.cc
Sage Weil

06/02/2010

11:09 PM Linux kernel client Bug #111: handle EAGAIN from osd
I agree. Though we should differentiate between two cases. One is that we initiate the EAGAIN (e.g., when reached a l... Yehuda Sadeh
11:00 PM Linux kernel client Bug #111: handle EAGAIN from osd
Yehuda Sadeh wrote:
> We should make the client handle it, but we should also try to make sure that the osd doesn't ...
Sage Weil
10:51 PM Linux kernel client Bug #111: handle EAGAIN from osd
We should make the client handle it, but we should also try to make sure that the osd doesn't ever return it (at leas... Yehuda Sadeh
10:56 PM CephFS Bug #171 (Resolved): mds: MDSTableClient::_logged_ack(version_t) FAILED assert(pending_commit.cou...
... Sage Weil
10:40 PM Linux kernel client Bug #38 (Resolved): rm -r failure
I'm going to chalk this one up to commit:13a4214cd9ec14d7b77e98bd3ee51f60f868a6e5 (the d_subdirs ordering problem) an... Sage Weil
10:37 PM Linux kernel client Bug #69: ceph: ffff88001976ba50 auth cap (null) not mds0 ???
For a multi-mds system, this can be caused if we are between an export and import on a cap.
But when I saw this th...
Sage Weil
10:24 PM CephFS Bug #165: cmds crash
This looks an awful lot like it might be fixed by commit:15c6651ff57b88722b5c896f5698bf1d033e1f98. And possibly prev... Sage Weil
01:31 AM CephFS Bug #165: cmds crash
just got the same crash of mds2 using b441fbdc9fdca271ed3bd100fc3c98c800b509b1
please find the full logs of each m...
ar Fred
09:36 PM CephFS Bug #170: null pointer dereference in journal_cow_dentry causes assertion failure
this is actually a failed assertion, not a null deref. it looks like gdb is having trouble resolving the symbols pro... Sage Weil
03:04 PM CephFS Bug #170 (Rejected): null pointer dereference in journal_cow_dentry causes assertion failure
I've seen this a few times today.
Using the latest unstable servers(08afc8df680dc0cd5ad26f3f89152aa25a72b639), and m...
Greg Farnum
07:40 PM Revision 5262a96a (ceph): mds: add export_dir command
Sage Weil
07:40 PM Revision 4075b95c (ceph): mds: add MDCache::cache_traverse()
Sage Weil
06:50 PM Revision a3323c98 (ceph): tcp: parse ipv4 and ipv6 addresses
Sage Weil
06:50 PM Revision 0d1e5dbf (ceph): move addr parse() into entity_addr_t
Sage Weil
06:50 PM Revision eac36cb5 (ceph): initscript: unmount btrfs if we mounted it
Sage Weil
06:34 PM Revision 08afc8df (ceph): mon: fix unsynchronized clock logic;
change output for clarity Greg Farnum
11:19 AM Feature #169 (Resolved): osd: start up despite corrupted pg log(s)
Catch decoding, memory alloc exceptions, and skip corrupt pgs so the osd can still start up. Log the errors. Sage Weil
10:02 AM Bug #149 (In Progress): Stale NFS Handle when copying from snapshot
Greg Farnum

06/01/2010

11:34 PM Revision b441fbdc (ceph): mds: lookup exact snap dn on import
Sage Weil
11:33 PM Revision 38cb2403 (ceph): mds: update dn->first too when lock state adjusts inode->first
This keeps dn->first in sync with inode->first Sage Weil
10:23 PM Revision 9248cd9e (ceph): mds: don't change lock states on replicated inode
The reconnect will infer some client caps, which will affect what lock
states we want. If we're not replicated, fine...
Sage Weil
10:02 PM Revision afadb122 (ceph): mds: fix root null deref in recalc_auth_bits
Root may be null if we don't have any subtrees besides ~mds$id. Sage Weil
09:14 PM Revision 364f3cb0 (ceph): mds: adjust subtree map when unlinking dirs
Otherwise we get subtree bounds in the stray dir and get confused down
the line.
Sage Weil
08:18 PM CephFS Bug #30: multimds: slave_request on getattr
I think the problem is that we authpin anything we rdlock... is that really necessary? Sage Weil
07:57 PM Revision c4bbb000 (ceph): mds: discover snapped paths on retried ops
This is intended to mitigate a livelock issue with traversing to snapped
metadata. The client specifies all snap req...
Sage Weil
06:39 PM Revision 464e46c8 (ceph): mon: add wiggle room for clock synchronization check
Greg Farnum
05:30 PM Revision 7f8a743c (ceph): mds: add case for CEPH_LOCK_DVERSION to LockType
Greg Farnum
03:23 PM CephFS Bug #165: cmds crash
I pushed a fix to unstable that _might_ fix the root cause of this, but it's hard to say. Can you leave 'debug mds =... Sage Weil
12:58 PM CephFS Bug #165: cmds crash
ar Fred wrote:
> A bit later, I restarted the whole cluster, mds0 and mds2 crashed with the same stack trace, mds1 w...
Sage Weil
03:08 PM Linux kernel client Cleanup #168 (Closed): new truncate sequence
The new truncate sequence was merged for 2.6.35-rc1. (->truncate is deprecated?)
We need to see what updates (i...
Sage Weil
03:02 PM CephFS Bug #167 (Resolved): mds crash
fixed by commit:afadb1224516fc3a615d0cc51fe7560fcc0b5e7c Sage Weil
01:21 PM CephFS Bug #167 (Resolved): mds crash
Core was generated by `/usr/bin/cmds -i r1-11 -c /tmp/fetched.ceph.conf.5518'.
Program terminated with signal 11, Se...
ar Fred
12:48 PM Linux kernel client Bug #166 (Can't reproduce): Failing some pjd tests?
Best guess is an unsychronized client/server clock. Greg Farnum
11:55 AM Linux kernel client Feature #42: Resize of rbd image
There is a refresh /sys/class/.. interface, however, resizing of an image should be lock protected, and probably shou... Yehuda Sadeh
10:28 AM Linux kernel client Bug #164 (Resolved): memory leak in statfs
Fixed.
commit: 5d97634a3b824ed746ba0d5441bf3d1d65f490a0
Yehuda Sadeh
 

Also available in: Atom