Activity
From 06/10/2010 to 07/09/2010
07/09/2010
- 11:24 PM Revision 2b02afd6 (ceph): rbdtool: rename should first check source
- that is, source image doesn't exist error should have priority
over destination already exists. - 11:24 PM Revision 8b96c3ca (ceph): rbdtool: rearrange usage
- 10:51 PM Revision d19f05a4 (ceph): debug: fix debug rank symlink rotate when log_per_instance
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:51 PM Revision e61ceee1 (ceph): debian: override lintian warning unstripped-binary-or-object
- 10:37 PM Revision e0229b0a (ceph): rbdtool: implement copy
- 10:31 PM Revision 8f0da0ae (ceph): rbdtool: use canonical image name (pool/image)
- 10:31 PM Revision 98bdd8da (ceph): rbdtool: can read data using snapshot
- 09:47 PM Revision 3cbf578e (ceph): mds: issue all snap_caps allowed given locks, not by current cap
- For snap_caps, who cares if the live inode has a cap for this client. We
always want to issue the maximum set of cap... - 09:47 PM Revision 372db051 (ceph): mds: fix acquire_lock() calls in handle_client_open()
- We want to acquire_locks exactly once per path through the function.
Don't look at mdr->* yet if we haven't locked ye... - 09:47 PM Revision 8921a18e (ceph): mds: fix up snap cap issue logic comments
- 08:51 PM Revision f5c4fc61 (ceph): fix FCGI detection and specfile
- configure is building radosgw as soon as libfcgi is installed, even
if --without-radosgw is given. Here is a fix for ... - 08:14 PM Revision 878a7de5 (ceph): mon: avoid OOB m->cmd access in auth proprocess_command
- Signed-off-by: Sage Weil <sage@newdream.net>
- 06:27 PM Revision 71b9daa8 (ceph): debug: only truncate log file on open if log_per_instance is set
- Signed-off-by: Sage Weil <sage@newdream.net>
- 06:27 PM Revision c91c8a31 (ceph): msgr: brackets (not braces) for ipv6 addrs
- Sigh
Signed-off-by: Sage Weil <sage@newdream.net> - 05:09 PM Revision 876cca9e (ceph): mds: termiante client sessions before flushign log during shutdown
- We need to close out client sessions, and caps, to empty the open_files
lists, so that we can properly trim the EOpen... - 04:53 PM CephFS Bug #16: mds restart vs dbench
- hopefully fixed by commit:696bab43d66532768a9f85f71a86ddef2bff527f 'ceph: generate request paths only once'?? needs m...
- 04:14 PM CephFS Bug #16: mds restart vs dbench
- aha, when teh rename request is replayed, the target(?) filename changes:...
- 03:50 PM CephFS Bug #16 (In Progress): mds restart vs dbench
- whoops, no, hit it....
- 03:04 PM CephFS Bug #16 (Can't reproduce): mds restart vs dbench
- this has apparently been fixed since april.. can't reproduce it now.
- 04:38 PM Revision 84d4c11f (ceph): ceph.spec.in: create /var/log/ceph directory
- I've missed this one in my previous patch series.
Regards,
Christian
Signed-off-by: Sage Weil <sage@newdream.net> - 04:38 PM Revision bf047a64 (ceph): ceph.spec.in: add /var/lib/ceph/
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:38 PM Revision 8ec5134a (ceph): ceph.spec.in: add a build option for radosgw (--with radosgw)
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:38 PM Revision 19886eb6 (ceph): ceph.spec.in: add logrotate configuration
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:38 PM Revision 293299f0 (ceph): ceph.spec.in: set correct path for rbd classes
- Signed-off-by: Sage Weil <sage@newdream.net>
- 03:18 PM Bug #224 (Resolved): rbdtool copy / rename
- copy implemented at commit:e0229b0a1f9f46a6f6140873c17420d9bd85c87c
- 03:12 PM Feature #87 (Closed): osd: separate interface/messenger for backend (osd to osd) network
- 02:49 PM Linux kernel client Bug #226 (Resolved): kclient can hang waiting for snap caps
- 02:47 PM Linux kernel client Bug #226: kclient can hang waiting for snap caps
- should be fixed by commit:3cbf578e5e4ec6a79c78fc18d9104d4e71aab014
- 11:30 AM Linux kernel client Bug #226 (In Progress): kclient can hang waiting for snap caps
- 12:43 PM CephFS Bug #269 (Closed): mds: don't crash when attempting to write to a snapshotted dir
- I think this is a matter of returning EROFS for any write op if mdr->snapid != CEPH_NOSNAP.
Probably fix this befo... - 12:30 PM CephFS Bug #268 (Closed): cfuse: return EROFS when writing to snaps
- Lots of places to check.. setattr, create, mkdir, mknod, symlink, link, unlink, rename, setxattr... If the inode or d...
- 12:22 PM Linux kernel client Bug #193 (Resolved): protocol error after control-c
- I think this was caused by the message revocation bug fixed by commit:ed98adad3d87594c55347824e85137d1829c9e70, #252....
- 12:11 PM Linux kernel client Bug #139: BUG ceph_dentry_info: Objects remaining on kmem_cache_close()
- Haven't seen this bug for a while, might be resolved by accident?
- 11:30 AM Feature #267 (Resolved): Support IPv6 in monmaptool
- 11:30 AM Feature #267: Support IPv6 in monmaptool
- parsing was broken, fixed by commit:c91c8a3115347b8102ccf6a061b57a3a9c4ebd94
works for me:... - 11:12 AM Feature #267 (Resolved): Support IPv6 in monmaptool
- Adding a IPv6 monitor to the monmap fails:...
- 11:28 AM Bug #263 (Resolved): failed to assign a block name for image (during create)
- 11:17 AM Bug #263: failed to assign a block name for image (during create)
- Seems fixed since today. (unstable branch) (Had to install binutils though)
Had to run "cclass -a" to fix it. - 09:52 AM Linux kernel client Feature #261: Support IPv6 while mounting
- my bad, there was a fix in unstable that wasn't in master. moved that over, and it gets rid of the -97 error for me.
- 05:52 AM Linux kernel client Feature #261: Support IPv6 while mounting
- Tried mounting with IPv6 today, but it failed, the config:...
07/08/2010
- 10:41 PM Revision 9b74eb6f (ceph): osd: print debug write before adding to transaction
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:55 PM Revision 4701e838 (ceph): msgr: return error and dethrottle if message decode fails
- This was broken by the addition of the throttling stuff.
Signed-off-by: Sage Weil <sage@newdream.net> - 09:27 PM Revision b81273d5 (ceph): debian: make helper scripts remember most recent release
- So you don't have to cut&paste it on the command line
Signed-off-by: Sage Weil <sage@newdream.net> - 08:34 PM Revision f456b51d (ceph): osd: fix delayed pg creation use after free
- Use local acting[], not the one stashed in creating_pgs[pgid]. And drop
the duplication .erase().
Signed-off-by: Sa... - 06:34 PM Revision 6612a1f1 (ceph): vstart: specify osd class tmp dir
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:56 PM Revision 9fd3f593 (ceph): monc: make hunt, ping rates configuration
- 3s for hunt rate, 10s for ping rate.
Signed-off-by: Sage Weil <sage@newdream.net> - 05:49 PM Revision a396fcb2 (ceph): client: increase client mount timeout
- This needs to be longer than the monclient hunt rate (currently 10s) so
that we succeed if we initially pick a down m... - 05:14 PM Revision 89c7d920 (ceph): filestore: improve lseek64 error checking, and use buffer::list::write_...
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:09 PM Revision a3fa9660 (ceph): buffer: make write_fd() const
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:49 PM Revision 303a1e3c (ceph): mount.ceph: handle ipv6 addrs, colons, braces
- Signed-off-by: Sage Weil <sage@newdream.net>
- 03:38 PM Revision 25ff6e4c (ceph): ceph.spec: require libedit
- Signed-off-by: Sage Weil <sage@newdream.net>
- 03:36 PM Revision e0d443cc (ceph): ceph.spec.in: require binutils
- cclass needs /usr/bin/nm
Signed-off-by: Sage Weil <sage@newdream.net> - 03:33 PM Revision c5d86f9d (ceph): debian: require binutils
- cclass needs 'nm' to extract symbols from rados classes.
Signed-off-by: Sage Weil <sage@newdream.net> - 03:29 PM Revision fd8ba5d5 (ceph): debian: explicit postinst/postrm for shlibs
- The dh_shlibdeps sees the .so in 'ceph' and incorrectly adds ldconfig to
postinst and postrm. Which is useless and u... - 11:06 AM Cleanup #258 (Resolved): make logger output rotatable, cleaner
- fixed by commit:83d1ea6636dd432dcbb6a0c6046d551bee7be5c6
- 11:05 AM Linux kernel client Feature #261 (Resolved): Support IPv6 while mounting
- fixed by commit:54b4fe8b92c7983ccb9b588420951e11aa5aa87c on the kenrel side. there is also a ceph.git patch commit:3...
- 09:04 AM rgw Bug #264 (Resolved): Creating a bucket gives ErrorBucketAlreadyExists
- 08:56 AM rgw Bug #264: Creating a bucket gives ErrorBucketAlreadyExists
- This is actually a bug in the s3 client. Should be fixed with the attached patch.
- 01:43 AM rgw Bug #264 (Resolved): Creating a bucket gives ErrorBucketAlreadyExists
- When trying to create a bucket, you get the message that it already exists, when it doesn't:...
- 08:59 AM CephFS Feature #266 (New): mount.ceph: specify secret via name=foo and keyring=bar
- It can run cauthtool -p keyringfile to extract the secret.
- 01:46 AM rgw Bug #265 (Closed): Removing a bucket doesn't clean up object in .rgw pool
- When removing a bucket, the corresponding object in the .rgw pool doesn't get removed, thus preventing us from creati...
- 01:01 AM Bug #263: failed to assign a block name for image (during create)
- Also fails with qemu-kvm:...
- 12:43 AM Bug #263 (Resolved): failed to assign a block name for image (during create)
- Trying to create a image with rbdtool, this fails:...
07/07/2010
- 11:55 PM Revision 07646308 (ceph): rbdtool: should support files larger than 2GB
- 11:34 PM Revision ae82dd5a (ceph): rbdtool: fix export
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:33 PM Revision 1e08e4bf (ceph): mon: create new pools using rjenkins hash
- Otherwise they get -1, which always maps to an invalid (-1) pgid.
Signed-off-by: Sage Weil <sage@newdream.net> - 10:56 PM Revision b977f4e5 (ceph): debian: _do_ strip cosd
- 10:56 PM Revision cf38e86e (ceph): class: make class tmp directory configurable, not /tmp
- /tmp usually gets mounted with 'noexec', making it a poor choice.
Signed-off-by: Sage Weil <sage@newdream.net> - 10:00 PM Revision d5e3962a (ceph): config: can use '-' as a config option
- 09:41 PM Revision 2096d8d7 (ceph): logger: shut up
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:33 PM Revision 01989903 (ceph): msgr: remove fake orig_source_addr fakery
- This makes get_orig_*() match get_*().
Signed-off-by: Sage Weil <sage@newdream.net> - 09:32 PM Revision 6ae95b6c (ceph): mon: fix message forwarding to use Connection to fake source addr
- This make get_source_addr() work (not just get_orig_source_addr()).
Signed-off-by: Sage Weil <sage@newdream.net> - 07:50 PM Revision 243491ef (ceph): debian: do not strip cosd
- 07:50 PM Revision ed66dd57 (ceph): classhandler: print error when dlopen fails
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:34 PM Bug #262 (Resolved): osd: make sync work on ext4
- FileStore currently does a single fsync() to push all dirty data to disk (data=ordered(/journal?)) behavior. ext4 do...
- 03:24 PM Revision cc5fcb99 (ceph): ceph: drop version from ceph_fs.h, use autoconf VERSION macro instead
- There's no reason to define this in the code anymore. Since the kernel
side doesn't use it it just confuses matters.... - 02:47 PM Revision 6cca139f (ceph): shell script fixes
- 02:38 PM Revision 9432a958 (ceph): mds: fix logger init on startup, rank symlink creation
- Busted by 83d1ea6636dd432dcbb6a0c6046d551bee7be5c6.
Signed-off-by: Sage Weil <sage@newdream.net> - 02:36 PM Revision b0e6e4f1 (ceph): cclass: $libdir/rados-classes
- 02:36 PM Revision 929f6721 (ceph): debian: include rados-classes
- Signed-off-by: Sage Weil <sage@newdream.net>
- 02:36 PM Revision 8d2393c0 (ceph): osd: consolidate osd stats in _refresh_my_stats
- Also keep local copy of osd_stat (send with pg stats update to monitor).
Signed-off-by: Sage Weil <sage@newdream.net> - 02:36 PM Revision 0bf19e5a (ceph): debian: put rbd classes in ceph, not librados1 package
- The cluster classes are a server-side thing, not client lib thing.
Signed-off-by: Sage Weil <sage@newdream.net> - 02:36 PM Revision 4fb67c31 (ceph): Makefile: cleanup
- 02:36 PM Revision a321ae43 (ceph): debian: add postinst, postrm for ceph package
- This will keep debain from using the default, which thinks it needs to run
ldconfig. Which it doesn't. - 02:36 PM Revision f6e1fd53 (ceph): debian: do not strip rados classes
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:04 AM Linux kernel client Feature #261 (Resolved): Support IPv6 while mounting
- Right now the client doesn't support mounting over IPv6 yet, so it's not possible to run with IPv6 only.
In order ... - 07:41 AM CephFS Bug #259 (Resolved): MDS crash during log initialize
- sorry, fixed for real by commit:9432a9588972860aa2fdb3f9ea18eb88073ace9a
- 03:20 AM CephFS Bug #259: MDS crash during log initialize
- Seems to be in commit 83d1ea6636dd432dcbb6a0c6046d551bee7be5c6, reverting to 1ca446dd9ac2a03c47b3b6f8cc7007660da911ec...
- 02:37 AM CephFS Bug #259 (Resolved): MDS crash during log initialize
- Running with the latest unstable (83d1ea6636dd432dcbb6a0c6046d551bee7be5c6) my MDS'es crash while initializing their ...
- 07:08 AM rgw Bug #260 (Closed): Segmentation fault when listing buckets without uid
- When listing buckets without a uid, radosgw_admin segfaults:...
- 04:12 AM Revision 1ca446dd (ceph): auth: rename supported_auth -> auth_supported
- It should be 'auth supported' for naming consistency.
Signed-off-by: Sage Weil <sage@newdream.net> - 04:12 AM Revision 83d1ea66 (ceph): logger: huge rewrite, cleanup
- - name *.log
- name after name, not rank
- reopen on sighup
- remove pointer on shutdown
- clean up interface
- imple...
07/06/2010
- 10:14 PM Revision 0c345a98 (ceph): client: put MDSSession pointers in the msd_session map, rather than the...
- This is a bit cleaner and clears the way to make it more closely mimic the kernel.
- 10:14 PM Revision 74bd8d77 (ceph): client: handle_client_session now careful opening mds sessions while un...
- 10:00 PM Revision 5b097603 (ceph): msgr: immediately drop messages with null dest
- This avoids spawning a new pipe and then failing to connect to a bad
address.
Signed-off-by: Sage Weil <sage@newdrea... - 10:00 PM Revision c39ee594 (ceph): paxos: send summary if observer has fallen behind first_committed
- This avoids a ceph crash like
mon/PGMap.h: In function 'void PGMap::apply_incremental(PGMap::Incremental&)':
mon/PGM... - 09:48 PM Revision a40631fb (ceph): mds: fix handle_dentry_unlink to handle remote unlink (no straydn)
- The straydn is optional, and NULL if we're unlinking a remote dentry.
Signed-off-by: Sage Weil <sage@newdream.net> - 09:34 PM Revision 0fbb8eeb (ceph): mds: be less noisy about memory usage in log
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:02 PM Revision 08f74066 (ceph): ceph: --in-file, not --in-data
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:47 PM Revision 89a40b3f (ceph): osd: track pg_num by type in logger
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:27 PM Revision 013df04a (ceph): librados: add pool set_snap_context
- Set the snap context for a given pool handle.
Signed-off-by: Sage Weil <sage@newdream.net> - 07:02 PM Revision 84bca030 (ceph): client: take the first inode as root, rather than whatever comes out
- with ino=1.
Also, translate root inode properly in fuse_ll. - 06:53 PM Revision 4a80e5e0 (ceph): ceph.spec: install /etc/logrotate.d/ceph
- 05:59 PM Revision cff705b5 (ceph): config: allow optional parameters
- 05:59 PM Revision fdcc2413 (ceph): rbdtool: modify usage
- 05:53 PM Revision de668159 (ceph): osd: document some of the logger stats
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:24 PM Revision 100b6776 (ceph): mds: do not include snapped inodes in EOpen or LogSegment::open_files
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:22 PM Revision 0f8099a0 (ceph): radosgw: fix usage syntax
- That fixes bug #256.
- 05:13 PM Revision a497c616 (ceph): mds: print useful error on malformed EOpen event
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:10 PM Revision 1d450742 (ceph): Makefile: distribute check_version
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:10 PM Revision 29505805 (ceph): debian: simplify release.sh
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:10 PM Revision 26b67ff8 (ceph): Makefile: drop unnecessary dist-hook for make_version
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:27 PM Cleanup #258 (Resolved): make logger output rotatable, cleaner
- 03:45 PM Bug #247 (In Progress): osd: allow separate interface for internal cluster traffic
- I'm just going to begin by setting up the OSD code to accept and work with multiple messengers.
Other parts may be a... - 03:28 PM CephFS Cleanup #236 (Resolved): cfuse: clean up mds session handling
- Done in commit:74bd8d777df932922007ec69d3bd9b8dfe5c1394.
- 12:50 PM Feature #257 (Resolved): osd: separte pg type Logger counts
- 12:17 PM Feature #257 (Resolved): osd: separte pg type Logger counts
- primary, replica, stray
- 12:01 PM CephFS Feature #235 (Resolved): cfuse: allow specifying server path to mount on command line
- Done in commit:84bca03089673985ec9341ae73c53e23932b854b
- 10:28 AM CephFS Bug #255 (Resolved): MDS crash while during journal replay
- fixed by commit:100b6776ddb095c43cf20734b48e399d359d7b1b
- 04:39 AM CephFS Bug #255 (Resolved): MDS crash while during journal replay
- While updating my cluster to the latest unstable i saw a crash on both my MDS'es.
The backtrace (same on both):
... - 10:11 AM Linux kernel client Bug #254 (Resolved): leaked authorizer memory
- fixed by commit:22b1de06c9fe128ca3de72560c3e8c2cabf2927a
- 10:03 AM rgw Cleanup #256 (Resolved): Usage of radosgw_admin reports rgw_admin
- Fixed with commit:0f8099a088cab90c49a4c016c5ec6505ae922d53.
- 09:48 AM rgw Cleanup #256 (Resolved): Usage of radosgw_admin reports rgw_admin
- ...
07/05/2010
- 06:54 PM Revision b0056ad0 (ceph): mount.ceph: ignore noauto, _netdev options
- Signed-off-by: Sage Weil <sage@newdream.net>
- 03:59 PM Revision b4336250 (ceph): debian: include libcls_rbd.so.*
- Signed-off-by: Fred Ar <ar.fred@yahoo.com>
Signed-off-by: Sage Weil <sage@newdream.net> - 03:59 PM Revision e240a277 (ceph): cclsinfo: fixes for dash
- Signed-off-by: Fred Ar <ar.fred@yahoo.com>
Signed-off-by: Sage Weil <sage@newdream.net> - 03:51 PM Revision b150b68c (ceph): ceph.spec.in: make -j and unpackaged files
- * now that make -j<numprocs> works out of the box, add it to the spec
* added new unpackaged files
* the test binarie... - 03:42 PM Linux kernel client Bug #254 (Resolved): leaked authorizer memory
- ...
- 02:11 PM Feature #169: osd: start up despite corrupted pg log(s)
- Dropping the priority on this, now that the corruption in #212 is fixed.
- 12:29 PM Linux kernel client Bug #210 (Resolved): GPF in ceph_con_revoke_message+0x2c/0x152
- I think this is a different manifestation of #252, now fixed.
- 12:28 PM Linux kernel client Bug #1: gpf in tcp_sendpage
- I think this was actually #252, now fixed.
- 12:28 PM Linux kernel client Bug #252 (Resolved): GFP at tcp_sendpage+0x327/0x5d3
- Ah, finally. Fixed by commit:ed98adad3d87594c55347824e85137d1829c9e70
- 11:00 AM Linux kernel client Bug #252 (Resolved): GFP at tcp_sendpage+0x327/0x5d3
- just saw this on both ceph2 and ceph4. running bonnie.sh and .. iozone? and a few times earlier this week.
clie... - 12:09 PM Linux kernel client Bug #253 (Resolved): bad mount option at 'noauto'
- fixed by commit:b0056ad0c09dd4e9cbd46f84a4123cdc9c4b7a02 in ceph.git
- 12:07 PM Linux kernel client Bug #253: bad mount option at 'noauto'
- Same goes for _netdev...
- 12:04 PM Linux kernel client Bug #253 (Resolved): bad mount option at 'noauto'
- Seems that the "noauto" option is missing in "mount.ceph.c".
Could this be added again so i can add my Ceph filesy...
07/04/2010
- 09:52 PM Revision 5338e7dc (ceph): Makefile: fix up ceph_ver.h autogeneration
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:08 PM Revision d724d2ce (ceph): Makefile: fix build when WITH_DEBUG not set
- Signed-off-by: Fred Ar <ar.fred@yahoo.com>
Signed-off-by: Sage Weil <sage@newdream.net> - 11:17 AM Bug #251 (Resolved): osd crash at first start after mkcephfs
- Nope, it came from 640eaad433ec43e77375258714c38733d5bd1638, but it looks like Sage fixed it in d847a4fd. Let us know...
- 04:53 AM Bug #251 (Resolved): osd crash at first start after mkcephfs
- using 67b9fa6147b8b52bf91b6be3d11bdcf8a0974b3d
did a mkcephfs, and started all 3 boxes (each 1 osd, 1 mon, 1 mds)....
07/03/2010
- 04:29 AM Revision 0e70f21a (ceph): debug: don't create rank symlink if log-file
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:28 AM Revision d059aa62 (ceph): client: update ctime on setattr(no mask)
- This makes pjd happy (chown -1 -1 should bump ctime, apparently). The
kclient does the same trick: dirty any excl ca...
07/02/2010
- 11:47 PM Revision cf7d180c (ceph): client: return errors from setattr
- Otherwise fuse just gets confused because the stat structure isn't filled
in and generates its own EIO.
Signed-off-b... - 11:38 PM Revision 8b886df8 (ceph): client: fix lookup error codes
- The fuse glue was making all errors ENOENT, and _lookup didn't return
ENAMETOOLONG.
Signed-off-by: Sage Weil <sage@n... - 11:17 PM Revision 377a531a (ceph): client: better debug output
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:17 PM Revision adf2f980 (ceph): client: return ENAMETOOLONG where appropriate
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:59 PM Revision 525063cc (ceph): client: fix f_namemax returned by statfs
- This was fixed in the kernel last month.
Signed-off-by: Sage Weil <sage@newdream.net> - 10:59 PM Revision 56cc68d1 (ceph): qa: do untar_snap_rm on two different tarballs (medium and big)
- 10:28 PM Revision 1b363dde (ceph): rbdtool: implement import
- still doesn't use fiemap
- 10:13 PM Revision e5cef56e (ceph): Makefile: make more random crap only build with WITH_DEBUG
- This should be everything not packaged.
Signed-off-by: Sage Weil <sage@newdream.net> - 09:46 PM Bug #250 (Resolved): mon: delete old states to avoid filling disk
- We trim the pgmap (which gets the most activity), but not the others: logs, mdsmap, osdmap, etc. Unfortunately the o...
- 09:44 PM CephFS Bug #249 (Resolved): cfuse: pjd failures
- fixed in commit:d059aa62aae35368611038b982c87873114d55d8, using same technique as kclient.
- 04:48 PM CephFS Bug #249 (Resolved): cfuse: pjd failures
- There are only a few left:...
- 06:59 PM Revision 1cb1c25d (ceph): client: remove typo
- 06:46 PM Revision ec2c31d6 (ceph): rbdtool: cleanup
- 06:30 PM Revision 818e7939 (ceph): client: synchronize metadata on fsync, when requested.
- 06:03 PM Revision da9353e6 (ceph): osd: cleanup: move pools can into advance_map()
- Signed-off-by: Sage Weil <sage@newdream.net>
- 06:03 PM Revision d847a4fd (ceph): osd: fix null pg deref, put auid in PGPool, cleanup.
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:14 PM Revision b031d11d (ceph): update authors
- 05:14 PM Revision 86111a0a (ceph): thread: allow setting stacksize when calling create & check return valu...
- Signed-off-by: Paul Chiang <paul_chiang@tcloudcomputing.com>
Signed-off-by: Sage Weil <sage@newdream.net> - 05:14 PM Revision 76d23923 (ceph): thread: force stacksize to be multiple of page size; clean up
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:14 PM Revision 2170c64b (ceph): msgr: add config option to set stacksize of reader&writer threads
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:03 PM Revision 14a871a1 (ceph): rbdtool: implement export
- 04:19 PM Revision 3204f45d (ceph): shift feature supported/required specifications into Policy
- This gets it out of the header, and also makes the previous
"my_features & their_features" logic explicit in the Poli... - 03:45 PM Bug #248 (Resolved): rbdtool import should use fiemap
- At least try to use fiemap where applicable for sparse files.
- 03:44 PM Revision 3253ed42 (ceph): msgr: add set_policy_throttler
- This lets us continue to use the helpers.
Signed-off-by: Sage Weil <sage@newdream.net> - 03:10 PM Bug #225 (Resolved): rbdtool import / export
- import implemented, commit:1b363dde22a4f421c7be14347b7591f814a35950. Need to implement import using fiemap for sparse...
- 09:46 AM Bug #225: rbdtool import / export
- Export implemented at commit:14a871a110724cffa1346f83a4fd24c2a45aa018
- 02:59 PM Revision 340cb060 (ceph): ceph.spec.in: initrddir, not initddir
- Signed-off-by: Sage Weil <sage@newdream.net>
- 02:59 PM Revision efc187e4 (ceph): ceph.spec.in: remove mkmonfs manpage
- 02:58 PM Revision 7eb12d5e (ceph): ceph.spec.in: some fixes
- encountered following errors building an rpm package with the
ceph.spec.in:
RPM build errors:
File not found: /v... - 02:57 PM Revision 9c3fc0ae (ceph): mkmonfs: remove all traces
- It's been replaced by 'cmon --mkfs'
Reported-by: Thomas Mueller <thomas@chaschperli.ch>
Signed-off-by: Sage Weil <sa... - 02:49 PM Revision e63d3f74 (ceph): mount.ceph: add mount options/flags
- noatime, nodiratime, relatime. Some cleanup.
Signed-off-by: Sage Weil <sage@newdream.net> - 02:44 PM Feature #154: support IPv6 addresses
- 02:33 PM Revision 9be97625 (ceph): Makefile: add/fix ceph_ver.h dependencies
- Signed-off-by: Sage Weil <sage@newdream.net>
- 02:02 PM Bug #247 (Resolved): osd: allow separate interface for internal cluster traffic
- One interface for external access (client i/o), one for cluster io (replication, recovery).
- 11:31 AM CephFS Bug #241 (Resolved): cfuse: make sure fsync does the right thing; remove warning
- Done in commit 818e79398f00e21e532c09a7618eea58255807c9.
- 09:21 AM Cleanup #223 (Resolved): msgr: move supported/required feature bits out of ceph_fs.h, into cosd/c...
- added by commit:3204f45d4bc62b4973c866b639422733b651107f
- 07:51 AM Linux kernel client Bug #246 (Resolved): Bad mount option at 'noatime'
- fixed by commit:e63d3f741f6c64d22e090bb6f9bc7f990d1796ce
need to rebuild and reinstall mount.ceph - 12:43 AM Linux kernel client Bug #246 (Resolved): Bad mount option at 'noatime'
- Since a few days i can't mount my filesystem with the "noatime" option.
My mount options:...
07/01/2010
- 11:48 PM Revision 89a65548 (ceph): filejournal: make journal alignment max of block, page sizes
- Alignment must be a multiple of page size. At least currently.
- 10:46 PM Revision 9154b5fc (ceph): msgr: handle ipv4 or ipv6 addresses (untested)
- At some point we may want to bind to both v4 and v6 addrs. Later!
Signed-off-by: Sage Weil <sage@newdream.net> - 10:46 PM Revision 67b9fa61 (ceph): ceph: fix decoding of class incrementals
- 10:19 PM Revision a08c6f76 (ceph): osd: modify caps calculation
- 10:19 PM Revision ece7098f (ceph): osd: pgpool keeps pool name
- 10:19 PM Revision 91088587 (ceph): osd, class: introduce public class methods
- public class methods don't need exec permissions in order to execute
- 10:19 PM Revision c6969f12 (ceph): vstart.sh: added -c to the cclass execution
- 10:19 PM Revision 640eaad4 (ceph): osd: caps configuration file uses pool names
- pool names instead of pool ids
- 09:29 PM Revision 10476ada (ceph): buffer: fix logic in write_fd()
- Reset iovec after finishing writev operation.
This bug occurs when buffer list size is larger than IOV_MAX. - 09:29 PM Revision 139e8209 (ceph): hostname override option for ceph init script
- 09:29 PM Revision 7e5e519a (ceph): libceph: Add check before umount in deinitialize
- Signed-off-by: Paul Chiang <paul_chiang@tcloudcomputing.com>
Signed-off-by: Sage Weil <sage@newdream.net> - 09:29 PM Revision 0233257b (ceph): Makefile: link ssl to libceph
- Signed-off-by: Paul Chiang <paul_chiang@tcloudcomputing.com>
Signed-off-by: Sage Weil <sage@newdream.net> - 09:29 PM Revision 57aeed1f (ceph): debian: add logrotate.d/ceph
- 09:29 PM Revision c2debcc6 (ceph): man: install cclass, cclsinfo man pages; include in ceph.deb
- 09:29 PM Revision ed02afdf (ceph): cfuse: log_per_instance by default
- e.g., if run with --log-to-stdout=0,
lrwxrwxrwx 1 sage sage 11 Jul 1 14:22 cfuse4173 -> fatty.31362 - 08:56 PM Revision 2c250299 (ceph): mon: break loop if config file parsed successfully
- 07:46 PM Revision e006e795 (ceph): msgr: fix dispatch throttler release
- We need to release the same amount back to the throttler as we originally
reserved. Store that amount in the Message... - 06:15 PM Revision bbbf2406 (ceph): cfuse: daemonize by default
- We have to fork, then start client, to avoid killing our pthreads. Use
a socketpair to tell the parent process about... - 06:01 PM Revision a7d4987f (ceph): config: -f just means foreground; do not change log output
- Before it would set log_to_stdout = false, but the default might be true.
- 05:57 PM Revision 21432ec8 (ceph): client: start/stop objectcacher thread in init/shutdown, not constructor
- 04:33 PM Revision e38ed519 (ceph): config: disallow -d|--daemonize
- Either we can daemonize, and do that by default, or we can't, and
shouldn't, even if you pass -d. - 04:25 PM Revision 2c7cd49b (ceph): common: break init into set_defaults and init steps
- This will let us tweak the default daemon/non-daemon settings as needed,
e.g. in the case of cfuse. - 04:10 PM Revision 8043ee27 (ceph): debug: fixup
- 03:55 PM Revision 85e626d1 (ceph): common: disable logger by default; make daemon settings explicit in (3)...
- 03:47 PM Revision 79991ed4 (ceph): debug: revamp debug/logging
- - By default, append to $type.$name.log.
- Get old $hostname.$pid + $type.$name symlink behavior only with
g_conf.l... - 03:47 PM Revision 633af045 (ceph): vstart: normalize pid file names
- 03:47 PM Revision c2538732 (ceph): debug: add max count for name symlinks
- 03:33 PM Bug #243 (Resolved): Need to be able to mark certain class methods as public
- Implemented. Commit 91088587b596b810446dd4e5fdc5fc68f95be3c3.
- 03:20 PM Feature #245 (Resolved): Logging to syslog
- I would like to setup remote syslog on my OSD's so i can run with the highest debug level on all my nodes.
Right n... - 02:38 PM Bug #244 (Resolved): msgr throttler deadlock
- by commit:e006e7951aaa9270efca69848ca17d5d4a660b4e
- 11:54 AM Bug #244 (Resolved): msgr throttler deadlock
- Seeing this on the sepia osds with normal qa workload.
read_message() blocking on dispatch throttler, but dispatch... - 02:31 PM CephFS Feature #238 (Resolved): cfuse: log to file if run as daemon
- commit:ed02afdf798bbe20a92b55c20a9ea659ff204de2
- 02:11 PM Feature #125 (Resolved): log rotation
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.
- 11:10 PM Revision e5b60faa (ceph): client: set inode/dentry fields where available
- 11:10 PM Revision beeb08bb (ceph): client: remove now-unused authority and pick_replica functions
- 11:08 PM Revision fa62e9db (ceph): client: rewrite choose_target_mds to more closely mirror kclient logic ...
- 11:08 PM Revision 60f2672e (ceph): client: add mds_num to MDSSession struct
- 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... - 11:06 PM Revision bfd335c2 (ceph): rbd: some header cleanup
- 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. - 11:06 PM Revision abd26eea (ceph): client: initialize auth_caps in Inode! Prevents bad pointer derefs.
- 11:06 PM Revision 194986a3 (ceph): client: remove Inode::dir_auth data member
- 11:06 PM Revision 060d22d0 (ceph): client: remove dead code
- 11:06 PM Revision 4f2f78dd (ceph): client: move all mds selection code into choose_target_mds
- 11:06 PM Revision 0992001c (ceph): client: clean up Inode::authority
- 11:06 PM Revision 77a1664a (ceph): rbdtool: implement snap rollback
- 10:44 PM Revision 2fdd43e7 (ceph): buffer: handle write_fd() on empty bufferlist
- 09:53 PM Linux kernel client Cleanup #233 (Resolved): replace mount option fsid{major,minor} with fsid=<string>
- 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... - 09:18 PM Revision aa30dd18 (ceph): buffer: make write_fd() tolerate zero length ptrs in the bufferlist
- 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... - 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 ... - 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> - 05:32 PM Revision e76ce441 (ceph): man: add man pages for cclass and cclsinfo
- 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 ...
- 04:41 PM CephFS Bug #232 (Resolved): ESTALE on many copies
- Done by 1bd46c0480b2d6b120773b4b122de6cd68861778, along with a number of other issues.
- 03:52 PM Bug #222 (Resolved): add rollback/revert to rbdtool
- 03:52 PM Bug #222: add rollback/revert to rbdtool
- Implemented, commit 77a1664af6ef988c9da7d401fc592043d9bfb4ef.
- 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...
- 03:40 PM rbd Bug #240 (Resolved): update qemu rbd to use block names
- Functionality added, commit 989d1db651aef18aec6c6826dc36cf54ef4615ea.
- 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.
- 03:30 PM Feature #242 (Rejected): fuse rbd driver
- maybe something like,...
- 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
- 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"
- 11:01 AM CephFS Bug #229 (Resolved): cfuse freezes
- 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...
- 10:21 AM Bug #239 (Resolved): create man pages for cclass and cclsinfo
- Done, commit e76ce441314bced42a02a140d15db30d2bd26eb0.
- 05:58 AM Revision 134a0d0f (ceph): rbdtool: fix uninitialized variable
- 12:23 AM Revision 015faa88 (ceph): config: update __isarg before reading config param
- 12:23 AM Revision 06279651 (ceph): rbdtool: implement rename
06/29/2010
- 11:25 PM Revision 4d9f49a7 (ceph): debian: include cclsinfo
- 11:23 PM Revision 013f9e52 (ceph): Makefile: include cclsinfo; lose the old .cc
- 11:08 PM Revision 0812b8f4 (ceph): Makefile: include cclass.in in dist
- 11:00 PM Revision 0f4ddbac (ceph): cls: cls_read, cls_cxx_read return the number of bytes read
- 11:00 PM Revision c9930900 (ceph): cclass.in: LIBDIR=.libs in certain cases
- 11:00 PM Revision 96b1db80 (ceph): rbdtool: init rbd block id, later will be used for rename
- 11:00 PM Revision f9dc4b90 (ceph): buffer: write_fd should skip empty buffers
- 09:40 PM Revision 2ec729d1 (ceph): config: use <<20 for MB
- 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 ... - 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 - 09:38 PM Revision 3e334024 (ceph): osd: removed unused RepGather::indata
- Signed-off-by: Sage Weil <sage@newdream.net>
- 09:38 PM Revision 852ab94a (ceph): osd: change write osd logging timing
- 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... - 09:31 PM Revision def4b40e (ceph): osd: always include osd op result, result code in the first reply
- 09:21 PM Revision ff8df7dc (ceph): osd: add 'logger reset' command
- 09:21 PM Revision e85d98ba (ceph): osd: track open repops in logger
- Signed-off-by: Sage Weil <sage@newdream.net>
- 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... - 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...
- 05:16 PM Bug #224: rbdtool copy / rename
- rename implemented at 0627965198ddd8a0c9af458e15b4da1a8a645b42.
- 05:14 PM Bug #239 (Resolved): create man pages for cclass and cclsinfo
- 04:59 PM Revision 1d517986 (ceph): conf: fix parsing when there's no eol at the end of file
- 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... - 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.
- 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 ... - 03:59 PM CephFS Feature #235 (Resolved): cfuse: allow specifying server path to mount on command line
- 03:34 PM Revision d9dc7cb5 (ceph): msg: fix entity_addr_t::parse() to return false on failure
- 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:... - 09:41 AM Bug #234 (Resolved): conf: skips last line if there's no newline
- fixed by 1d517986a87e89a281eb1529e72add72f9de7e93
- 09:34 AM CephFS Bug #153 (Resolved): mds: fix snap dentry replication vs readdir on frag auth
- This was resolved back in commit:c4bbb0008b2b6dd2a8d377a5c6424592221ca846
- 09:24 AM Bug #202 (Can't reproduce): OSD crash during reads from cluster
- 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...
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...
- 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 ... - 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> - 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...
- 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.
- 09:49 AM Linux kernel client Cleanup #233 (Resolved): replace mount option fsid{major,minor} with fsid=<string>
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...
- 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... - 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.
- 04:47 AM Revision 928512ff (ceph): crushtool: add simple test function
- 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...
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... - 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...
- 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... - 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... - 11:52 AM CephFS Bug #229: cfuse freezes
- yes, unstable from a few days ago: bf3d52a4b725a0f2d3db39ea9ad5b412171ea0ad 2010-06-20 23:41:19
- 09:27 AM CephFS Bug #229: cfuse freezes
- Is this the unstable branch of ceph.git?
- 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... - 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...
- 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.
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, ... - 11:49 PM Revision eeede270 (ceph): qa: read recently written/deleted data back from snap
- 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 ... - 09:45 PM Bug #114 (Resolved): osd: corrupted pglog
- I'm going to chalk this one up to #212.
- 06:51 PM Revision 478fe723 (ceph): ceph_fs: add CEPH_LOCK_IFLOCK so its inclusion elsewhere continues to b...
- 06:37 PM Revision 62827156 (ceph): mds: add IFLOCK to wait bits to prevent collisions with lock branch
- 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 ... - 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... - 05:39 PM Revision 8f7df4ed (ceph): client: resync with kernel's ioctl.h
- This got munged up by the #ifndef/#define guard cleanup.
- 05:39 PM Revision 07cfbad8 (ceph): mds: fix SimpleLock wait_shift()
- DVERSION was missing, others were overlapping...
- 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 ...
- 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... - 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: ... - 09:54 AM Linux kernel client Bug #226 (Resolved): kclient can hang waiting for snap caps
- ...
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...
- 09:12 PM Revision 58f4dceb (ceph): osdmap: negative osd ids do not exist
- Signed-off-by: Sage Weil <sage@newdream.net>
- 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... - 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.
- 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...
- 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...
- 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... - 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...
- 04:19 PM Bug #224 (Resolved): rbdtool copy / rename
- It'd be helpful to be able to copy and/or rename rbd volumes.
- 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...
- 10:55 AM Linux kernel client Bug #220 (Resolved): oops on add
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. - 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...
- 03:49 PM Linux kernel client Bug #220 (Resolved): oops on add
- ...
- 04:19 PM Bug #222 (Resolved): add rollback/revert to rbdtool
- 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... - 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...
- 11:00 AM Linux kernel client Bug #218 (In Progress): fix estale handling to look at auth cap migrate_seq
- 02:11 PM Linux kernel client Bug #200 (Resolved): umount hangs with clustered mds
- Fixed by 364521acb070ab60540f869f4ccd79b468c3d9b0.
- 11:00 AM Bug #215 (Resolved): osd crash: FAILED assert(seq >= last_committed_seq)
- 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...
- 09:25 AM CephFS Feature #45 (Closed): Investigate adding Connection * to mds Session
- This got pulled into unstable a while ago.
06/21/2010
- 11:27 PM Revision 43a7ec4c (ceph): client: properly handle ESTALE by redirecting to auth MDS
- 11:27 PM Revision c89afb4c (ceph): client: don't send cap snap message to MDS if not dirty or writing.
- From Sage.
- 06:43 PM Revision 027b6c3e (ceph): rados: more descriptive ls usage failure, stdout set implicitly
- 06:35 PM Revision 2cd04f47 (ceph): mds: rename handle_client_opent
- 06:35 PM Revision 2e73f737 (ceph): mds: only acquire_locks once in handle_client_open
- Subsequent calls will just return with 'already locked'
- 06:27 PM Revision 4d86180e (ceph): rbdtool: fix --list
- 05:36 PM Revision 90511120 (ceph): osd: fix incorrect logic check on fsid comparison
- 04:46 PM Revision 9bbeec47 (ceph): osd: Warn and shutdown on a mismatched fsid, instead of failing an assert
- 04:38 PM Linux kernel client Bug #217 (Resolved): client needs to open sessions to mds export targets
- 12:43 PM Linux kernel client Bug #217 (Resolved): client needs to open sessions to mds export targets
- 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... - 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... - 04:26 PM Bug #208 (Resolved): Can't create snapshots in cfuse on mds cluster
- Fixed in 43a7ec4c88e5367a6f8faef175e86859b286ae8a
- 04:13 PM Linux kernel client Bug #189: leaked dentry
- Sage Weil wrote:
> this is fixed by commit:01048745dd99bfc21d4e38863ec86597185e57d7
simpler fix in commit:17c688c... - 04:05 PM Linux kernel client Bug #189 (Resolved): leaked dentry
- this is fixed by commit:01048745dd99bfc21d4e38863ec86597185e57d7
- 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... - 10:43 AM Linux kernel client Bug #216 (In Progress): splice_dentry error
- 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 ... - 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... - 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.... - 03:07 PM Linux kernel client Bug #218 (Resolved): fix estale handling to look at auth cap migrate_seq
- 11:07 AM Linux kernel client Bug #144 (Can't reproduce): GPF at con_close_socket+0x40/0x9f
- 11:07 AM Linux kernel client Bug #162 (Can't reproduce): list bug during shrink_dcache_for_umount
- 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...
- 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, ...
- 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...
- 10:51 AM Linux kernel client Bug #210 (In Progress): GPF in ceph_con_revoke_message+0x2c/0x152
- 10:29 AM Linux kernel client Bug #210: GPF in ceph_con_revoke_message+0x2c/0x152
- r12 is 5a5a5a.., on this code...
- 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...
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... - 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> - 04:44 PM Revision 3bfabd41 (ceph): mon: allow 10ms clock drift before complaining
- 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! - 10:39 AM Bug #215 (Resolved): osd crash: FAILED assert(seq >= last_committed_seq)
- this is ceph unstable c626ac384678661b765c1ae1dee8db48b2c70993...
- 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
- 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:...
06/19/2010
- 03:41 PM Revision 775506e9 (ceph): debian: include cclass
- 03:40 PM Revision d4173fa7 (ceph): initscript: fix for dash
- Signed-off-by: Fred Ar <ar.fred@yahoo.com>
- 03:39 PM Revision 1f2725bc (ceph): cclass: fix for dash
- Signed-off-by: Fred Ar <ar.fred@yahoo.com>
- 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 ...
- 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... - 02:12 AM Revision b3dc5ecf (ceph): vstart: only need to load classes once, not for each monitor
06/18/2010
- 11:32 PM Revision c626ac38 (ceph): Merge branch 'rbd-class' into unstable
- 11:31 PM Revision 3a2c9169 (ceph): Revert "class: able to add classes when doing mkfs"
- This reverts commit 65371482dd661c6dc3d251fb9fd4e01812bdaa0e.
- 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... - 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... - 09:30 PM Revision ed768c9a (ceph): buffer: fix includes for writev/iovec stuff in write_fd()
- 09:09 PM Revision a3e906e3 (ceph): filestore: make sync() and friends actually sync!
- 08:56 PM Revision ae90ba18 (ceph): initscripts: fix verbose output for root commands
- 08:06 PM Revision 10d41d2c (ceph): filejournal: only pad to align for data segments above 64 KB
- 08:00 PM Revision f98c0b4f (ceph): filejournal: make alignment optional (<0 == no preferred alignment)
- 07:49 PM Revision 2be1480a (ceph): Merge branch 'unstable' of ceph.newdream.net:git/ceph into unstable
- 07:48 PM Revision 3fbc2a2a (ceph): buffer: remove debug cruft
- 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. - 07:46 PM Revision f59d77be (ceph): objectstore: track offset, alignment of largest data segment [encoding ...
- 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... - 06:38 PM Revision 25116b27 (ceph): client: if checking caps on a snap, return, don't assert
- 05:10 PM Revision bd4188a0 (ceph): filejournal: use buffer::write_fd() instead of open coding
- Avoid dup code, and also handle short writes.
- 04:40 PM Revision ca9b7563 (ceph): osd: implement bench command
- 'bench [bsize] [total bytes]'
Result is reported via logclient. - 04:24 PM Bug #212 (Resolved): osd: journal vs filestore sync in writeahead move
- 04:24 PM Bug #212: osd: journal vs filestore sync in writeahead move
- many commits, culminating in commit:fb1ad6e746a52a99d82d864d4a6efeda09be2440
- 02:39 PM Bug #212 (Resolved): osd: journal vs filestore sync in writeahead move
- The journal is incorrectly dropping entries in writeahead mode
- 04:19 PM Revision e4b9dd4b (ceph): msgr: avoid calculating data crc is peer didn't either
- Otherwise we're just wasting CPU cycles!
- 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> - 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... - 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... - 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....
- 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... - 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...
- 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... - 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...
- 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... - 08:55 AM Bug #98: reserved identifier violation
- Who is responsible for the tool that generates the affected header files?
- 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... - 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_...
06/17/2010
- 08:44 PM Revision 35095434 (ceph): qa: another mds test fix... wait long enough for the previous death to ...
- 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... - 08:09 PM Revision 920b2d89 (ceph): qa: fix mdstable failure tests
- 05:51 PM Revision 4d66a72a (ceph): ceph: fix straggler header ifdef guards
- 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... - 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> - 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... - 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. - 05:13 PM Revision af2d023c (ceph): osd: don't requeue null OSDOp on apply_and_flush_repops
- (this triggers during snap trimming)
- 05:13 PM Revision e6b033ac (ceph): osd: make clean_up_local remove hardlinks from collection dirs
- 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... - 05:13 PM Revision 57d79aaa (ceph): Revert "mkcephfs: cosd mkfs as root, then chown"
- This reverts commit 0383878c4f5133f43ec16067a8917d3080adc690.
- 05:04 PM Revision f6501564 (ceph): Merge branch 'unstable' of ssh://ceph.newdream.net/home/sage/ceph.newdr...
- 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... - 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... - 04:29 PM Revision 583f9f42 (ceph): mkcephfs: error out of journal dev is included in btrfs devs
- 04:29 PM Revision f976bbdc (ceph): filejournal: journal write cache is safe on >= 2.6.33
- 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... - 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 ...
- 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...
- 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!
- 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...
- 10:42 AM Bug #179 (Closed): corrupted LogEntry in mon data
- 10:34 AM Linux kernel client Bug #204 (Resolved): crush update crash
- fixed by commit:cebc5be6b6c82a99231e9c9af451e9e3d3399ec6
- 10:18 AM Bug #203 (Rejected): osd journal full deadlock?
- 10:18 AM Bug #173 (Resolved): Throttle client requests on OSD
- 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... - 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... - 09:40 AM Bug #205 (Resolved): remove journal write cache warning?
- warning updated in commit:f976bbdcf700e52c9ef92964551b2c73b014686c
06/16/2010
- 09:15 PM Revision d7b9f39d (ceph): filejournal: log if journal item is larger than journal
- 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
- 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... - 05:14 PM Revision 5c001f4e (ceph): conf: can specify environment variables for substitution
- 05:13 PM Revision ce909c2c (ceph): osd: error out when failing to read journal header
- This fixes bug #201.
- 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 :
... - 09:30 AM Bug #203 (Rejected): osd journal full deadlock?
- 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... - 11:53 AM CephFS Bug #188 (In Progress): cfuse crashes on snapshot file read
- 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.
- 10:03 AM Bug #205 (Resolved): remove journal write cache warning?
- 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...
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... - 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...
- 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 -... - 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...
06/14/2010
- 07:22 PM Revision d971bb06 (ceph): osd: mkfs failures are colored red
- 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));
- 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:
... - 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...
06/13/2010
- 10:45 AM Linux kernel client Bug #194: MOSDMap memory leak?
- fixed by commit:ae32be31341a5fecfa16c5b3eb78095207182cce
- 10:43 AM Linux kernel client Bug #194 (Resolved): MOSDMap memory leak?
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?
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
- 09:05 PM Revision bdda73fd (ceph): monc: handle mon0 or mon.a syntax when pull mon addrs from .conf
- 09:03 PM Revision aabaa065 (ceph): monc: more debug info on monmap receipt
- 08:56 PM Revision 690ea1c1 (ceph): mon: MONNAMES feature is supported by all userland
- 08:34 PM Revision ddf739f6 (ceph): mon: simplify request forwarding
- Use the MonSession to track proxy state, NOT the PaxosServiceMessage header
hackery. - 05:15 PM Revision 8cc096f6 (ceph): monmaptool: don't allow dup names, addrs to be added to the map
- 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 ... - 05:12 PM Revision 658d51da (ceph): mon: make send_reply always consume reply ref (even if not sent); fix c...
- 05:08 PM Revision 6a40008c (ceph): mon: make send_reply always consume reply ref (even if not sent); fix c...
- 04:57 PM Revision 33850a22 (ceph): monmaptool: fix usages tring
- 04:56 PM Revision 9fddee98 (ceph): mkcephfs: behave with new mon naming scheme
- 10:46 AM Bug #197 (Resolved): osd: FAILED assert(state == DELAYED || state == RMW)
- 10:18 AM Bug #197 (Resolved): osd: FAILED assert(state == DELAYED || state == RMW)
- ...
06/10/2010
- 11:01 PM Revision 3336d9d0 (ceph): rgw: put_obj uses write_full
- 10:26 PM Revision 0b0009cf (ceph): cls_rbd: use write_full when writing image header
- 10:26 PM Revision 5d2e85d2 (ceph): class: implement write_full interface
- 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.
- 10:15 PM Bug #192 (Resolved): inconsistent md5sum on repeated read of file
- 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...
- 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....
- 10:14 PM Feature #195 (Resolved): monitor naming and removal support
- see mon-remove branch. let's merge this after v0.21.
- 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... - 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...
- 04:42 PM Linux kernel client Bug #193 (Resolved): protocol error after control-c
- Saw this on wido's machine:...
- 10:11 PM Linux kernel client Bug #194 (Resolved): MOSDMap memory leak?
- Code audit looks ok. Could this be a false alarm somehow?...
- 09:45 PM Revision 80d2afc1 (ceph): cclsinfo: utility to display class information
- 09:45 PM Revision e3b23bd0 (ceph): cclsinfo: some fixes
- 09:45 PM Revision d071cb1c (ceph): cclsinfo: replace error message
- 09:45 PM Revision 203af22e (ceph): cls: export relevant functions
- 09:45 PM Revision 057ccbbf (ceph): cclsinfo.sh: shell script to dump class info
- 09:45 PM Revision d87c057f (ceph): cclsinfo.sh: better architecture detection
- 09:45 PM Revision 65371482 (ceph): class: able to add classes when doing mkfs
- 09:45 PM Revision e737e635 (ceph): class: more flexible class loading, new cclass.sh script
- 09:45 PM Revision 7584fef1 (ceph): class: modify scripts, fix configuration
- 09:45 PM Revision 3bb153c3 (ceph): class: modify startup scripts to add classes on mon startup
- 09:45 PM Revision ae5bb842 (ceph): cclass: add some options
- 09:45 PM Revision 912e3c85 (ceph): osd: fix rollback when head points at the rolled back snapshot
- 09:45 PM Revision f34c5b91 (ceph): cls_rbd: fix snapshots seq number
- 09:45 PM Revision b58e1b9a (ceph): rados: update documentation to mention mkpool and rmpool
- 09:45 PM Revision 4716b486 (ceph): rbd: snapshots management via class mechanism
- 09:45 PM Revision c5abf58d (ceph): class: add CLS_LOG macro
- 09:45 PM Revision 2991c300 (ceph): rbd: add snapshot creation via rbd class
- 09:45 PM Revision a6e50c24 (ceph): rbd: implement snap revert header manipulation via class
- 09:45 PM Revision e297aa0b (ceph): rbd: snap revert header manipulation fixes
- 09:45 PM Revision 94308d13 (ceph): cls-rbd: some adjustments, debug info
- 09:42 PM Revision 7739cafb (ceph): testradospp: add a test for librados trunc
- 09:41 PM Revision 42ff45b4 (ceph): librados: add trunc operation
- 09:12 PM Revision 3de397fc (ceph): testradospp: update test, use write_full
- 09:04 PM Revision d1c779c9 (ceph): librados: implement write_full
- 06:55 PM Revision 92f2ecd3 (ceph): osd: fix null dereference in dout
- 05:17 PM Revision effe5db3 (ceph): mds: be extra careful
- Probably implied by the refs == 0, but be explicit anyway.
- 05:17 PM Revision 607ba5dd (ceph): mds: fix another instance of bad stray trimming code to use proper helper
- 04:10 PM Revision 673fdc7a (ceph): mds: remove erroneous return statement
- 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.
- 03:47 PM Feature #184: librados support for truncate, writefull
- And related rgw commit:
3336d9d0fab7513c12a48879ab9a50cba2ab475e - 03:43 PM Feature #184 (Resolved): librados support for truncate, writefull
- implemented.
commits:
d1c779c96a0afeaf245ade6c5d4c8de818fcd66b
42ff45b4eec31b992a1ecc1cc27a0f513f6cadde - 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...
- 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... - 12:35 PM rbd Feature #41: Support snapshots
- Then kvm-rbd snapshots implementation also needs to include snapshots rollback.
- 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 ...
- 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...
- 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_... - 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
- 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
...
Also available in: Atom